Personal tools
You are here: Home / News
CPSLAB
Log in


Forgot your password?
 

News

Eunwoo Kim wins a silver prize in the 23rd Samsung HumanTech Paper Award

[2017/02/07]

Eunwoo Kim wins a silver prize in the 23rd Samsung HumanTech Paper Award.

Here are some photos from the award ceremony.

IMG_0622  IMG_0625 
 IMG_0626  IMG_0631
 IMG_0634  

Document Actions

Our paper on real-time navigation is accepted to Robotics and Autonomous Systems

[2016.12.12]

The following paper is accepted to Robotics and Autonomous Systems:

  • Real-Time Nonparametric Reactive Navigation of Mobile Robots in Dynamic Environments by Sungjoon Choi, Eunwoo Kim, Kyungjae Lee, Songhwai Oh
    • Abstract: In this paper, we propose a nonparametric motion controller using Gaussian process regression for autonomous navigation in a dynamic environment. Particularly, we focus on its applicability to low-cost mobile robot platforms with low-performance processors. The proposed motion controller predicts future trajectories of pedestrians using the partially-observable egocentric view of a robot and controls a robot using both observed and predicted trajectories. Furthermore, a hierarchical motion controller is proposed by dividing the controller into multiple sub-controllers using a mixture-of-experts framework to further alleviate the computational cost. We also derive an efficient method to approximate the upper bound of the learning curve of Gaussian process regression, which can be used to determine the required number of training samples for the desired performance. The performance of the proposed method is extensively evaluated in simulations and validated experimentally using a Pioneer 3DX mobile robot with two Microsoft Kinect sensors. In particular, the proposed baseline and hierarchical motion controllers show over 65% and 51% improvements over a reactive planner and predictive vector field histogram, respectively, in terms of the collision rate.

Document Actions

Our paper on single image 3D pose estimation is accepted to CVIU

[2016.11.01]

The following paper is accepted to Computer Vision and Image Understanding (CVIU):

  • Single Image 3D Human Pose Estimation Using a Procrustean Normal Distribution Mixture Model and Model Transformation by Jungchan Cho, Minsik Lee, and Songhwai Oh
    • Abstract: 3D human pose estimation from a single image is an important problem in computer vision with a number of applications, including action recognition and scene understanding. However, it is still challenging due to its ill-posedness and complex non-rigid shape variations of a human body. In this paper, we use the Procrustean normal distribution mixture model as a 3D shape prior and propose a model transformation method for adjusting limb lengths of the 3D shape prior model, by which the proposed method can be applied to a novel test image. Inaccuracies of 2D part detections are handled by selecting from a diverse set of 2D pose candidates considering both the 2D part model and 3D shape model. Experimental results show that the proposed method performs favorably compared with existing methods, despite inaccuracies of 2D part detections and 3D shape ambiguities.

Document Actions

[Invited Talk] Towards the Humanoid Robots of Science Fiction

Presenter: Aaron Ames, Georgia Tech; Time: 4:00pm-5:30pm, Friday (2016/10/14); Location: Room 202, Building 301

This talk is cancelled due to an urgent family matter of the presenter.

Abstract

The humanoid robot DURUS was unveiled to the public in the midst of the DARPA Robotics Challenge (DRC). While the main competition took place in the stadium, DURUS took part in the Robot Endurance Test with the goal of demonstrating locomotion that is an order of magnitude more efficient than existing bipedal walking on humanoid robots, e.g., the ATLAS robot utilized in the DRC. During this accessible public demonstration of humanoid robotic walking, DURUS walked continuously for over 2½ hours covering over 2 km—all on a single 1.1 kWh battery. At the core of this success was a methodology for designing and realizing dynamic and efficient walking gaits on bipedal robots through a mathematical framework that utilizes hybrid systems models coupled with nonlinear controllers that provably result in stable locomotion. This mathematical foundation allowed for the full utilization of novel mechanical components of DURUS, including: efficient cycloidal gearboxes (allowing for almost lossless transmission of power) and compliant elements at the ankles (absorbing the impacts at foot-strike). Through this combination of formal controller design and novel mechanical design, the humanoid robot DURUS was able to achieve the most efficient walking ever recorded on a humanoid robot. This talk will outline the key elements of the methodology used to achieve this result, present new results on multi-contact humanoid locomotion, demonstrate the extensibility to other bipedal robots and robotic assistive devices, e.g., prostheses, and consider the question: when will the humanoid robots of science fiction become science fact?

Biography

Aaron D. Ames is an Associate Professor at the Georgia Institute of Technology in the Woodruff School of Mechanical Engineering and the School of Electrical and Computer Engineering. Prior to joining Georgia Tech, he was an Associate Professor and Morris E. Foster Faculty Fellow II at Texas A&M University. Dr. Ames received a B.S. in Mechanical Engineering and a B.A. in Mathematics from the University of St. Thomas in 2001, and he received a M.A. in Mathematics and a Ph.D. in Electrical Engineering and Computer Sciences from UC Berkeley in 2006. He served as a Postdoctoral Scholar in Control and Dynamical Systems at the California Institute of Technology from 2006 to 2008. At UC Berkeley, he was the recipient of the 2005 Leon O. Chua Award for achievement in nonlinear science and the 2006 Bernard Friedman Memorial Prize in Applied Mathematics. Dr. Ames received the NSF CAREER award in 2010 for his research on bipedal robotic walking and its applications to prosthetic devices, and is the recipient of the 2015 Donald P. Eckman Award recognizing an outstanding young engineer in the field of automatic control. Ames’ lab designs, builds and tests novel bipedal robots, humanoids and prostheses with the goal of achieving human-like bipedal robotic walking and translating these capabilities to robotic assistive devices. His research has received multiple best paper awards and has appeared in a variety of press ranging from technology news sources, e.g., Gizmodo, CNET, Engadget and Scientific American, to main stream media including the Washington Post, PBS, ESPN and CNN.

Document Actions

Our paper on Procrustean normal distribution (PND) is accepted to PAMI

[2016.07.26]

The following paper is accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI):

  • Procrustean Normal Distribution for Non-Rigid Structure from Motion by Minsik Lee, Jungchan Cho, and Songhwai Oh
    • Abstract: A well-defined deformation model can be vital for non-rigid structure from motion (NRSfM). Most existing methods restrict the deformation space by assuming a fixed rank or smooth deformation, which are not exactly true in the real world, and they require the degree of deformation to be predetermined, which is impractical. Meanwhile, the errors in rotation estimation can have severe effects on the performance, i.e., these errors can make a rigid motion be misinterpreted as a deformation. In this paper, we propose an alternative to resolve these issues, motivated by an observation that non-rigid deformations, excluding rigid changes, can be concisely represented in a linear subspace without imposing any strong constraints, such as smoothness or low-rank. This observation is embedded in our new prior distribution, the Procrustean normal distribution (PND), which is a shape distribution exclusively for non-rigid deformations. Because of this unique characteristic of the PND, rigid and non-rigid changes can be strictly separated, which leads to better performance. The proposed algorithm, EM-PND, fits a PND to given 2D observations to solve NRSfM without any user-determined parameters. The experimental results show that EM-PND gives the state-of-the-art performance for the benchmark data sets, confirming the adequacy of the new deformation model.

Document Actions

Our paper on a new pedestrian detection algorithm is accepted to ECCV 2016

[2016.07.25]

The following paper is accepted to European Conference on Computer Vision (ECCV 2016):

  • Individualness and Determinantal Point Processes for Pedestrian Detection by Donghoon Lee, Geonho Cha, Ming-Hsuan Yang, and Songhwai Oh
    • Abstract: In this paper, we introduce individualness of detection candidates as a complement to objectness for pedestrian detection. The individualness assigns a single detection for each object out of raw detection candidates given by either object proposals or sliding windows. We show that conventional approaches, such as non-maximum suppression, are sub-optimal since they suppress nearby detections using only detection scores. We use a determinantal point process combined with the individualness to optimally select nal detections. It models each detection using its quality and similarity to other detections based on the individualness. Then, detections with high detection scores and low correlations are selected by measuring their probability using a determinant of a matrix, which is composed of quality terms on the diagonal entries and similarities on the o -diagonal entries. For concreteness, we focus on the pedestrian detection problem as it is one of the most challenging problems due to frequent occlusions and unpredictable human motions. Experimental results demonstrate that the proposed algorithm works favorably against existing methods, including non-maximal suppression and a quadratic unconstrained binary optimization based method.

Document Actions

Our paper on informative path planning is accepted to CDC 2016

[2016.07.23]

The following paper is accepted to IEEE Conference on Decision and Control (CDC 2016):

  • Efficient Graph-Based Informative Path Planning Using Cross Entropy by Junghun Suh, Kyunghoon Cho, and Songhwai Oh
    • Abstract: In this paper, we present a novel informative path planning algorithm using an active sensor for efficient environmental monitoring. While the state-of-the-art algorithms find the optimal path in a continuous space using sampling based planning method, such as rapidly-exploring random graphs (RRG), there are still some key limitations, such as computation complexity and scalability. We propose an efficient information gathering algorithm using an RRG and a stochastic optimization method, cross entropy (CE), to estimate the reachable information gain of each node of the graph. The proposed algorithm maintains the asymptotic optimality of the  RRG planner and finds the most informative path satisfying the cost constraint. We demonstrate that the proposed algorithm finds a (near) optimal solution efficiently compared to the state-of-the-art algorithm and show the scalability of the proposed method. In addition, the proposed method is applied to multirobot informative path planning.

Document Actions

Three papers from CPSLAB are accepted to IROS 2016

[2016.07.06]

Following three papers are accepted to the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2016):

  • Inverse Reinforcement Learning with Leveraged Gaussian Processes by Kyungjae Lee, Sungjoon Choi, and Songhwai Oh
    • Abstract: In this paper, we propose a novel inverse reinforcement learning algorithm with leveraged Gaussian processes that can learn from both positive and negative demonstrations. While most existing inverse reinforcement learning (IRL) methods suffer from the lack of information near low reward regions, the proposed method alleviates this issue by incorporating (negative) demonstrations of what not to do. To mathematically formulate negative demonstrations, we introduce a novel generative model which can generate both positive and negative demonstrations using a parameter, called proficiency. Moreover, since we represent a reward function using a leveraged Gaussian process which can model a nonlinear function, the proposed method can effectively estimate the structure of a nonlinear reward function.
    • Video
  • Robust Modeling and Prediction in Dynamic Environments Using Recurrent Flow Networks by Sungjoon Choi, Kyungjae Lee, and Songhwai Oh
    • Abstract: To enable safe motion planning in a dynamic environment, it is vital to anticipate and predict object movements. In practice, however, an accurate object identification among multiple moving objects is extremely challenging, making it infeasible to accurately track and predict individual objects. Furthermore, even for a single object, its appearance can vary significantly due to external effects, such as occlusions, varying perspectives, or illumination changes. In this paper, we propose a novel recurrent network architecture called a recurrent flow network that can infer the velocity of each cell and the probability of future occupancy from a sequence of occupancy grids which we refer to as an occupancy flow. The parameters of the recurrent flow network are optimized using Bayesian optimization. The proposed method outperforms three baseline optical flow methods, Lucas-Kanade, Lucas-Kanade with Tikhonov regularization, and Horn-Schunck methods, and a Bayesian occupancy grid filter in terms of both prediction accuracy and robustness to noise. Furthermore, we have shown that the occupancy flow method can effectively be used for navigation in a dynamic environment without tracking moving objects.
    • Video
  • Gaussian Random Paths for Real-Time Motion Planning by Sungjoon Choi, Kyungjae Lee, and Songhwai Oh
    • Abstract:In this paper, we propose Gaussian random paths by defining a probability distribution over continuous paths interpolating a finite set of anchoring points using Gaussian process regression. By utilizing the generative property of Gaussian random paths, a Gaussian random path planner is developed to safely steer a robot to a goal position. The Gaussian random path planner can be used in a number of applications, including local path planning for a mobile robot and trajectory optimization for a whole body motion planning. We have conducted an extensive set of simulations and experiments, showing that the proposed planner outperforms look-ahead planners which use a predefined subset of egocentric trajectories in terms of collision rates and trajectory lengths. Furthermore, we apply the proposed method to existing trajectory optimization methods as an initialization step and demonstrate that it can help produce more cost-efficient trajectories.
    • Video

Document Actions

Our paper on robust subspace representation is accepted to IEEE Transactions on Image Processing

[2016.07.01]

The following paper is accepted to the IEEE Transactions on Image Processing:

  • Robust Elastic-Net Subspace Representation by Eunwoo Kim, Minsik Lee, and Songhwai Oh

  • Abstract: Recently, finding the low-dimensional structure of high-dimensional data has gained much attention. Given a set of data points sampled from a single subspace or a union of subspaces, the goal is to learn or capture the underlying subspace structure of the dataset. In this paper, we propose elastic-net subspace representation, a new subspace representation framework using elastic-net regularization of singular values. Due to the strong convexity enforced by elastic-net, the proposed method is more stable and robust in the presence of heavy corruptions compared to existing lasso-type rank minimization approaches. For discovering a single low-dimensional subspace, we propose a computationally efficient low-rank factorization algorithm, called FactEN, using a property of the nuclear norm and the augmented Lagrangian method. Then, ClustEN is proposed to handle the general case, in which data samples are drawn from a union of multiple subspaces, for joint subspace clustering and estimation. The proposed algorithms are applied to a number of subspace representation problems to evaluate the robustness and efficiency under various noisy conditions, and experimental results show the benefits of the proposed method compared to existing methods.

Document Actions

[ICRA 2016] Best Conference Paper Award Finalist

[2016.05.19]

Our paper on robust learning from demonstration (LfD) is the Best Conference Paper Award finalist at the IEEE International Conference on Robotics and Automation (ICRA 2016), a flagship international conference on robotics.

  • Sungjoon Choi, Kyungjae Lee, and Songhwai Oh, "Robust Learning from Demonstration Using Leveraged Gaussian Processes and Sparse-Constrained Optimization," in Proc. of the IEEE International Conference on Robotics and Automation (ICRA), May 2016. (Best Conference Paper Award Finalist)
    • Abstract: In this paper, we propose a novel method for robust learning from demonstration using leveraged Gaussian process regression. While existing learning from demonstration (LfD) algorithms assume that demonstrations are given from skillful experts, the proposed method alleviates such assumption by allowing demonstrations from casual or novice users. To learn from demonstrations of mixed quality, we present a sparse-constrained leveraged optimization algorithm using proximal linearized minimization. The proposed sparse constrained leverage optimization algorithm is successfully applied to sensory field reconstruction and direct policy learning for planar navigation problems. In experiments, the proposed sparse-constrained method outperforms existing LfD methods.

About Best Conference Paper Award

  • Description: To recognize the most outstanding paper presented at the annual IEEE International Conference on Robotics and Automation (ICRA)
  • Basis for Judging: Technical merit, originality, potential impact on the field, clarity of the written paper, and quality of the oral or other presentation.

About ICRA

The International Conference on Robotics and Automation (ICRA) is the IEEE Robotics and Automation Society’s biggest conference and one of the leading international forums for robotics researchers to present their work.

Document Actions

Our paper on a new NRSfM method is accepted to CVPR 2016 as oral presentation

[2016/03/06]

The following paper is accepted to IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016):

  • Consensus of Non-Rigid Reconstructions by Minsik Lee, Jungchan Cho, and Songhwai Oh
    • Abstract: Recently, there have been many progresses for the problem of non-rigid structure reconstruction based on 2D trajectories, but it is still challenging to deal with complex deformations or restricted view ranges. Promising alternatives are the piecewise reconstruction approaches, which divide trajectories into several local parts and stitch their individual reconstructions to produce an entire 3D structure. These methods show the state-of-the-art performance, however, most of them are specialized for relatively smooth surfaces and some are quite complicated. Meanwhile, it has been reported numerously in the field of pattern recognition that obtaining consensus from many weak hypotheses can give a strong, powerful result. Inspired by these reports, in this paper, we push the concept of part-based reconstruction to the limit: Instead of considering the parts as explicitly-divided local patches, we draw a large number of small random trajectory sets. From their individual reconstructions, we pull out a statistic of each 3D point to retrieve a strong reconstruction, of which the procedure can be expressed as a sparse l1-norm minimization problem. In order to resolve the reflection ambiguity between weak (and possibly bad) reconstructions, we propose a novel optimization framework which only involves a single eigenvalue decomposition. The proposed method can be applied to any type of data and outperforms the existing methods for the benchmark sequences, even though it is composed of a few, simple steps. Furthermore, it is easily parallelizable, which is another advantage.

Document Actions

Two papers from CPSLAB are accepted to ICRA 2016

[2016/01/22]

Following two papers are accepted to the IEEE International Conference on Robotics and Automation (ICRA 2016):

  • Robust Learning from Demonstration Using Leveraged Gaussian Processes and Sparse-Constrained Optimization by Sungjoon Choi, Kyungjae Lee, and Songhwai Oh
    • Abstract: In this paper, we propose a novel method for robust learning from demonstration using leveraged Gaussian process regression. While existing learning from demonstration (LfD) algorithms assume that demonstrations are given from skillful experts, the proposed method alleviates such assumption by allowing demonstrations from casual or novice users. To learn from demonstrations of mixed quality, we present a sparse-constrained leveraged optimization algorithm using proximal linearized minimization. The proposed sparse constrained leverage optimization algorithm is successfully applied to sensory field reconstruction and direct policy learning for planar navigation problems. In experiments, the proposed sparse-constrained method outperforms existing LfD methods.
  • Multiple-Hypothesis Chance-Constrained Target Tracking Under Identity Uncertainty by Yoonseon Oh and Songhwai Oh
    • Abstract: We propose a robust target tracking algorithm for a mobile robot under identity uncertainty, which arises in crowded environments. When a mobile robot has a sensor with a fan-shaped field of view and finite sensing region, the proposed algorithm aims to minimize the probability of losing a moving target. We predict the next position of a moving target in a crowded environment using a multiple-hypothesis prediction algorithm which combines the motion model and appearance model of the target. When the distribution of the target’s next position follows a Gaussian mixture model, the proposed tracking algorithm can track a target with a guaranteed tracking success probability. If the tracking success probability is sufficiently good, the method minimizes the moving distance of the mobile robot. The performance of the method is extensively validated in simulation and experiments using a Pioneer robot with a Microsoft Kinect sensor.
    • Video

Document Actions

Our paper on 3D shape recovery of complex non-rigid objects is accepted to IJCV

[2015/09/21]

The following paper is accepted to International Journal of Computer Vision (IJCV):

  • Complex Non-Rigid 3D Shape Recovery Using a Procrustean Normal Distribution Mixture Model by Jungchan Cho, Minsik Lee, and Songhwai Oh

  • Abstract: Recovering the 3D shape of a non-rigid object is a challenging problem. Existing methods make the low-rank assumption and do not scale well with the increased degree of freedom found in complex non-rigid deformations or shape variations. Moreover, in general, the degree of freedom of deformation is assumed to be known in advance, which limits the applicability of non-rigid structure from motion algorithms in a practical situation. In this paper, we propose a method for handling complex shape variations based on the assumption that complex shape variations can be represented probabilistically by a mixture of primitive shape variations. The proposed model is a generative probabilistic model, called a Procrustean normal distribution mixture model, which can model complex shape variations without rank constraints. Experimental results show that the proposed method significantly outperforms existing methods.

Document Actions

Our paper on random projection forests is accepted to ICCV 2015

[2015/09/12]

The following paper is accepted to International Conference on Computer Vision (ICCV 2015):

  • Fast and Accurate Head Pose Estimation via Random Projection Forests by Donghoon Lee, Ming-Hsuan Yang, and Songhwai Oh
    • Abstract: In this paper, we consider the problem of estimating the gaze direction of a person from a low-resolution image. Under these conditions, reliably extracting facial features is very difficult. We propose a novel head pose estimation algorithm based on compressive sensing. Head image patches are mapped to a large feature space using the proposed extensive, yet efficient filter bank. The filter bank is designed to generate sparse responses of color and gradient information, which can be compressed using random projection, and classified by a random forest. Extensive experiments on challenging datasets show that the proposed algorithm performs favorably against the state-of-the-art methods on head pose estimation in low-resolution images degraded by noise, occlusion, and blurring.

Document Actions

Our paper on high-dimensional motion planning is accepted to Humanoids 2015

[2015/09/12]
  • Energy-Efficient High-Dimensional Motion Planning for Humanoids Using Stochastic Optimization by Junghun Suh, Joonsig Gong, and Songhwai Oh

    • Abstract: This paper presents a method for planning a motion for a humanoid robot performing manipulation tasks in a high dimensional space such that the energy consumption of the robot is minimized. While sampling-based path planning algorithms, such as rapidly-exploring random tree (RRT) and its variants, have been highly effective for complex path planning problems, it is still difficult to find the minimum cost path in a high dimensional space since RRT-based algorithms extend a search tree locally, requiring a large number of samples to find a good solution. This paper presents an efficient nonmyopic motion planning algorithm for finding a minimum cost path by combining RRT* and cross entropy (CE). The proposed method constructs two RRT trees: the first tree is a standard RRT tree which is used to determine the nearest node in the ftree to a randomly chosen point and the second tree contains the first tree with additional long extensions. By maintaining two separate trees, we can grow the search tree non-myopically to improve efficiency while ensuring the asymptotic optimality of RRT*. We first identify and demonstrate the limitation of RRT* when it is applied to energy-efficient path planning in a high dimensional space. Results from experiments show that the proposed method consistently achieves the lowest energy consumption against other algorithms.

Document Actions

Autonomous Robot Navigation Challenge

[2015/06/23]

Navigation Challenge

This contest will show off the autonomous navigation in dynamic environments. Winners will be chosen based on time and accuracy of navigation to specific points within the contest environment.

Document Actions

Our paper on robust orthogonal matrix factorization is accepted to Neurocomputing

[2015/04/29]

The following paper is accepted to Neurocomputing:

  • Robust Orthogonal Matrix Factorization for Efficient Subspace Learning by Eunwoo Kim and Songhwai Oh
  • Abstract: Low-rank matrix factorization plays an important role in the areas of pattern recognition, computer vision, and machine learning. Recently, a new family of methods, such as l1-norm minimization and robust PCA, has been proposed for low-rank subspace analysis problems and has shown to be robust against outliers and missing data. But these methods suffer from heavy computation loads and can fail to find a solution when highly corrupted data are presented. In this paper, a robust orthogonal matrix approximation method using fixed-rank factorization is proposed. The proposed method finds a robust solution efficiently using orthogonality and smoothness constraints. The proposed method is also extended to handle the rank uncertainty issue by a rank estimation strategy for practical real-world problems. The proposed method is applied to a number of low-rank matrix approximation problems and experimental results show that the proposed method is highly accurate, fast, and efficient compared to the existing methods.

Document Actions

Our paper on low-rank approximation using elastic-net is accepted to CVPR 2015

[2015/03/09]

The following paper is accepted to IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015):

  • Elastic-Net Regularization of Singular Values for Practical Subspace Learning by Eunwoo Kim, Minsik Lee, and Songhwai Oh
    • Abstract: Learning a low-dimensional structure plays an important role in computer vision. Recently, a new family of methods, such as l1 minimization and robust principal component analysis, has been proposed for low-rank matrix approximation problems and shown to be robust against outliers and missing data. But the methods often require a heavy computational load and can fail to find a solution when highly corrupted data are presented. In this paper, an elastic-net regularization based low-rank matrix factorization method for practical subspace learning is proposed. The proposed method finds a robust solution efficiently by enforcing a strong convex constraint to improve algorithm’s stability. It is shown that any stationary point of the proposed algorithm satisfies the Karush-Kuhn-Tucker (KKT) optimality conditions. The proposed method is applied to a number of low-rank matrix approximation problems to demonstrate its efficiency in the presence of heavy corruptions and to show its effectiveness and robustness compared to the existing methods.

Document Actions

Our paper on VibePhone is accepted to Pattern Analysis and Applications

[2015/02/09]

The following paper is accepted to Pattern Analysis and Applications:

  • VibePhone: Efficient Surface Recognition for Smartphones Using Vibration by Jungchan Cho, Inhwan Hwang, and Songhwai Oh
  • Abstract: With various sensors in a smartphone, it is now possible to obtain information about a user and her surroundings, such as the location and the activity of the smartphone user, and the obtained context information is being used to provide new services to the users. In this paper, we propose VibePhone, which uses a built-in vibrator and accelerometer, for efficiently recognizing the type of surfaces contacted by a smartphone, enabling the sense of touch to smartphones. In particular, this paper focuses on developing a succinct set of features that are useful for recognizing surface types for reducing computation and memory requirements, which will in turn reduce the power consumption of the device. For humans and animals, the sense of touch, which is obtained from the texture of an object by scrubbing its surface, is fundamental for both recognizing and learning the properties of objects. Since a smartphone cannot physically scrub the contacting surface, we emulate the touch by generating vibrations and analyzing accelerometer readings. While the recognition of the object type by vibration alone is an extremely difficult task, even for a human, we demonstrate that it is possible to distinguish object types into broad categories where a phone is usually placed. For efficiency, VibePhone uses only a small subset of the most informative features of accelerometer readings using feature selection and reduces the computation time by 92% by using only 15% of features, while maintaining performance.We believe that our analysis of vibrations about contacted surfaces can provide an important insight for the haptic perception in future smartphones, enabling new experiences to the users.
  • Video

Document Actions

Three papers from CPSLAB are accepted to ICRA 2015

[2015/02/05]

Following three papers are accepted to the IEEE International Conference on Robotics and Automation (ICRA 2015):

  • Leveraged Non-Stationary Gaussian Process Regression for Autonomous Robot Navigation by Sungjoon Choi, Eunwoo Kim, Kyungjae Lee, and Songhwai Oh
    • Abstract: In this paper, we propose a novel regression method that can incorporate both positive and negative training data into a single regression framework. In detail, a leveraged kernel function for non-stationary Gaussian process regression is proposed. This kernel function can not only vary the correlation between two inputs in the positive direction but also to the negative direction by adjusting a leverage parameter. By using this property, the resulting leveraged non-stationary Gaussian process regression can anchor the regressor to the positive data while avoiding the negative data. We first prove the positive semi-definiteness of the leveraged kernel function using Bochner’s theorem. The mathematical interpretation of the leveraged non-stationary Gaussian process regression using the leveraged kernel function is also addressed. Finally, we apply the leveraged non-stationary Gaussian process regression to the real-time motion control problem. In this case, the positive data refer to what to do and the negative data indicate what not to do. The results show that the controller using both positive and negative data outperforms the controller using positive data only in terms of the collision rate given training sets of the same size.
    • Video
  • Chance-Constrained Target Tracking for Mobile Robots by Yoonseon Oh, Sungjoon Choi, and Songhwai Oh
    • Abstract: This paper presents a robust target tracking algorithm for a mobile robot. A mobile robot is equipped with a sensor with a fan-shaped field of view and finite sensing range. The goal of the mobile robot is to track a moving target such that the probability of losing the target is minimized. We assume that the distribution of the next position of a moving target can be estimated using a motion prediction algorithm. If the next position of a moving target has the Gaussian distribution, the proposed algorithm can guarantee the tracking success probability, i.e., the probability that the next position of the target is within the sensing region of the mobile robot. In addition, the proposed method minimizes the moving distance of the mobile robot based on a bound on the tracking success probability. While the problem considered in this paper is a non-convex optimization problem, we derive analytical solutions which can be easily solved in real-time. The performance of the proposed method is evaluated extensively in simulation and validated in pedestrian following experiments using a Pioneer mobile robot with a Microsoft Kinect sensor.
    • Video
  • Robust Structured Low-Rank Matrix Approximation in Autoregressive Gaussian Process Regression for Autonomous Robot Navigation by Eunwoo Kim, Sungjoon Choi, and Songhwai Oh
    • Abstract: This paper considers the problem of approximating a kernel matrix in an autoregressive Gaussian process regression (AR-GP) in the presence of measurement noises or natural errors for modeling complex motions of pedestrians in a crowded environment. While a number of methods have been proposed to robustly predict future motions of humans, it still remains as a difficult problem in the presence of measurement noises. This paper addresses this issue by proposing a robust structured low-rank matrix approximation method using nuclear-norm regularized l1-norm minimization in AR-GP for robust motion prediction of dynamic obstacles. The proposed method approximates a kernel matrix by finding an orthogonal basis using low-rank symmetric positive semidefinite matrix approximation assuming that a kernel matrix can be well represented by a small number of dominating basis vectors. The proposed method is suitable for predicting the motion of a pedestrian, such that it can be used for safe autonomous robot navigation in a crowd environment. The proposed method is applied to well-known regression data sets and motion prediction problems to demonstrate its robustness and excellent performance compared to existing approaches.
    • Video

Document Actions

Team SCARAB has successfully competed in the IROS 2014 Kinect Navigation Contest

Here are some photos from the contest.
2.JPG 3.JPG
4.png  5.png
 6.png  7.JPG
8.JPG
9.png
10.png
11.png
12.jpg
13.jpg
14.jpg
15.jpg

Document Actions

Our paper on coordinated localization is accepted to IEEE Transactions on Automation Science and Engineering

[2014/08/30]

The following paper is accepted to IEEE Transactions on Automation Science and Engineering:

  • Vision-Based Coordinated Localization for Mobile Sensor Networks by Junghun Suh, Seungil You, Sungjoon Choi, and Songhwai Oh
  • Abstract: In this paper, we propose a coordinated localization algorithm for mobile sensor networks with camera sensors to operate under GPS denied areas or indoor environments. Mobile robots are partitioned into two groups. One group moves within the field of views of remaining stationary robots. The moving robots are tracked by stationary robots and their trajectories are used as spatio-temporal features. From these spatio-temporal features, relative poses of robots are computed using multi-view geometry and a group of robots is localized with respect to the reference coordinate based on the proposed multi-robot localization. Once poses of all robots are recovered, a group of robots moves from one location to another while maintaining the formation of robots for coordinated localization under the proposed multi-robot navigation strategy. By taking the advantage of a multi-agent system, we can reliably localize robots over time as they perform a group task. In experiment, we demonstrate that the proposed method consistently achieves a localization error rate of 0.37% or less for trajectories of length between 715 cm and 890 cm using an inexpensive off-the-shelf robotic platform.

Document Actions

Our paper on distributed GPR under localization uncertainty is accepted to the ASME Journal of Dynamic Systems, Measurement, and Control.

[2014/06/24]

The following paper is accepted to ASME Journal of Dynamic Systems, Measurement, and Control:

  • Distributed Gaussian Process Regression Under Localization Uncertainty by Sungjoon Choi, Mahdi Jadaliha, Jongeun Choi, and Songhwai Oh
  • Abstract: In this paper, we propose distributed Gaussian process regression for resource-constrained distributed sensor networks under localization uncertainty. The proposed distributed algorithm, which combines Jacobi over-relaxation and discrete-time average consensus, can effectively handle localization uncertainty as well as limited communication and computation capabilities of distributed sensor networks. We also extend the proposed method hierarchically using sparse Gaussian process regression to improve its scalability. The performance of the proposed method is verified in numerical simulations against the centralized maximum a posteriori solution and a quick-and-dirty solution. We show that the proposed method outperforms the quick-and-dirty solution and achieves an accuracy comparable to the centralized solution.

Document Actions

Our paper on robust navigation using l1-norm low rank approximation is accepted to IROS 2014.

[2014/05/19]

The following paper is accepted to the IEEE International Conference on Intelligent Robots and Systems (IROS 2014):

  • A Robust Autoregressive Gaussian Process Motion Model Using l1-Norm Based Low-Rank Kernel Matrix Approximation by Eunwoo Kim, Sungjoon Choi, and Songhwai Oh

  • Abstract: This paper considers the problem of modeling complex motions of pedestrians in a crowded environment. A number of methods have been proposed to predict a motion of a pedestrian or an object. However, it is still difficult to make a good prediction due to challenges, such as the complexity of pedestrian motions and outliers in a training set. This paper addresses these issues by proposing a robust autoregressive motion model based on Gaussian process regression using l1-norm based low-rank kernel approximation, called PCGP-l1. The proposed method approximates a kernel matrix assuming that the kernel matrix can be well represented using a small number of dominating principal components, eliminating erroneous data. The proposed motion model is robust against outliers present in a training set and can reliably predict a motion of a pedestrian, such that it can be used by a robot for safe navigation in a crowded environment. The proposed method is applied to a number of regression and motion prediction problems to demonstrate its robustness and efficiency. The experimental results show that the proposed method considerably improves the motion prediction rate compared to other Gaussian process regression methods.
  • Video

Document Actions

Call for Papers: ICCPS 2015

April 14-16, 2015 (Seattle, USA)

ICCPS 2015 Preliminary Call for Papers

The 6th ACM/IEEE International Conference on Cyber-Physical Systems.

April 14-16, 2015, Seattle, Washington (as part of CPSWeek 2015)

URL: http://iccps.acm.org/2015/

As digital computing and communication becomes faster, cheaper and available in packages which are smaller and use less power, these capabilities are becoming embedded in many objects and structures in the physical environment. Cyber-physical systems (CPS) are physical and engineered systems whose operations are monitored, coordinated, controlled and integrated by such computing and communication. Broad deployment of cyber-physical systems is transforming how we interact with the physical world as profoundly as the world wide web transformed how we interact with one another, and harnessing their capabilities holds the possibility of enormous societal and economic impact.

ICCPS is the premier single-track conference for reporting advances in all aspects of cyber-physical systems, including theory, tools, applications, systems, testbeds and field deployments. This year, the conference features two focus areas for submissions: one on CPS foundations (the traditional focus of ICCPS), and one on secure and resilient infrastructure CPS (the focus of the former HiCoNS conference). The entire program committee is eligible to review in both areas, but authors will be asked to specify one of the two areas during submission in order to aid with reviewer selection.

The CPS foundations (CPSF) area focuses on core science and technology for developing fundamental principles that underpin the integration of cyber and physical elements. Application domains include transportation, energy, water, agriculture, ecology, supply-chains, medical and assistive technology, sensor and social networks, and robotics. Among the relevant research areas are security, control, optimization, machine learning, game theory, mechanism design, mobile and cloud computing, model-based design, verification, data mining / analytics, signal processing, and human-in-the-loop shared or supervisory control.

The secure and resilient infrastructure CPS (HiCoNS) area focuses on the confluence of cyber-security, privacy, and CPS that impacts the operation of critical infrastructures such as the smart grid, water distribution, transportation, healthcare, building automation, and process control. Of particular interest is foundational work that cuts across multiple application areas or advances the scientific understanding of underlying principles for the development of high confidence (secure, reliable, robust, and trustworthy) networked CPS. Beginning this year, this focus area of ICCPS replaces the High Confidence Networked Systems (HiCoNS) conference.

Submissions and Key Dates:
---------------------------------------

New this year: In concert with the other CPSWeek conferences, ICCPS will require that authors register paper titles and abstracts by October 13 (one week before the full paper submission deadline).

Abstract Registration: October 13, 2014 (mandatory)

Full Paper Submission deadline: October 20, 2014 (no extensions possible)

Manuscripts should be no more than 10 pages in two-column ACM conference style. Formatting and submission instructions will be made available at the website.

Organizers
---------------

General Co-Chairs

Alexandre Bayen (UC Berkeley)
Michael Branicky (University of Kansas)

Technical Program Committee Co-Chairs

Xenofon Koutsoukos (Vanderbilt University)
Ian M. Mitchell (University of British Columbia)

Poster / Demo / WiP Chair

Meeko Oishi (University of New Mexico)

Publications Chair

Georgios Fainekos (Arizona State University)

Publicity Co-Chairs

Dimos Dimarogonas (KTH)
Songhwai Oh (Seoul National University)
Jonathan Sprinkle (University of Arizona)

 

Document Actions

CPSLAB is qualified to compete at the IROS 2014 Kinect Navigation Contest.

[2014/06/26]

CPSLAB is qualified the first round to compete at the Kinect Navigation Contest along with nine other teams at IROS 2014.

Document Actions

Two papers are accepted to the IEEE CPSNA 2014.

[2014/06/10]

Following papers are accepted to the IEEE International Conference on Cyber-Physical Systems, Networks, and Applications (CPSNA 2014):

  • SmartPTA: A Smartphone-Based Human Motion Evaluation System by Geonho Cha, Joonsig Gong, and Songhwai Oh
    • Abstract: This paper considers a human motion evaluation system (HMES) using two smartphones and a server. An HMES user wears retro-reflective markers on her 13 joints and follows a motion demonstrated by an expert. Two smartphones detect markers and transmit detected 2D marker positions to the server which reconstructs 3D motion of the user. The server performs a spatio-temporal alignment between the motion of the user and the motion demonstrated by an expert to evaluate the quality of the user’s motion. The proposed system is applicable for physical therapy and sports education as an inexpensive alternative. We demonstrate that the 3D motion of the HMES user can be reconstructed reliably in real-time and successfully aligned with the reference motion of an expert, providing real-time feedback to the user.
  • Smartphone-Controlled Telerobotic Systems by Hyemin Ahn, Hyunjun Kim, Yoonseon Oh, and Songhwai Oh
    • Abstract: This paper proposes a telerobotic system based on a smartphone and Nao, a humanoid robot from Aldebaran Robotics. A user can control the robot using her smartphone and interact with people and surroundings around the robot in a remote location. The overall system includes two servers to facilitate the connection between the user’s smartphone and the robot. We have particularly focused on providing a user-friendly interface such that a user who is unfamiliar with the robot platform can control the robot intuitively. Users of the system reported that they felt that they were aboard the robot platform and they were able to understand the surroundings of the robot easily using the developed smartphone application.

Document Actions

[Invited Talk] Gangnam Style in Microbiorobotics: Biologically Inspired Microscale Robotic Systems

Presenter: MinJun Kim, Drexel University; Time: 5pm-6pm, Tuesday (2014/04/29); Location: Room 201, Building 301

Abstract

One of the challenges in microrobotics is to find suitable and simplistic ways to swim in low Reynolds number. For such work, magnetically controlled achiral microswimmers with the simplest possible body structures were shown to swim in low Reynolds number environment. Most previous works on artificial microswimmers had always focused on using chiral or flexible structures to generate non-reciprocal swimming motions in low Reynolds numbers; this inevitably brings complicity to the swimmers’ shapes and structures. However, an achiral and rigid structure can swim under the proper conditions, as demonstrated by this work. An achiral microswimmer consists of three magnetic micro-particles conjugated through avidin-biotin chemistry and magnetic self-assembly. A magnetic control system of approximate Helmholtz coils was used to control the microswimmers. Both directional and velocity control were successfully implemented to navigate the swimmers through low Reynolds number environment. Furthermore, multi-robot manipulation, modular robot control, and PIV characterization had been employed. The implication of the swimming phenomenon and the robust control demonstrated herein serves as great potential to revision future developments of microrobots, especially for therapeutic targeting and minimally invasive surgical procedures.

Biography

Dr. MinJun Kim is presently an associate professor at Drexel University with a joint appointment in both the Department of Mechanical Engineering & Mechanics and the School of Biomedical Engineering, Science & Health System. He received his B.S. and M.S. degrees in Mechanical Engineering from Yonsei University in Korea and Texas A&M University, respectively. Dr. Kim completed his Ph.D. degree in Engineering at Brown University, where he held the prestigious Simon Ostrach Fellowship. Following his graduate studies, Dr. Kim was a postdoctoral research fellow at the Rowland Institute in Harvard University. For the past several years, Dr. Kim has been exploring biological transport phenomena including cellular/molecular mechanics and engineering in novel nano/microscale architectures to produce new types of nanobiotechology, such as nanopore technology and nano/micro robotics. His notable awards include the National Science Foundation CAREER Award (2008), Drexel Career Development Award (2008), Human Frontier Science Program Young Investigator Award (2009), Army Research Office Young Investigator Award (2010), Alexander von Humboldt Fellowship (2011), KOFST Brain Pool Fellowship (2013), Bionic Engineering Outstanding Contribution Award (2013), and Louis & Bessie Stein Fellowship (2014).

Document Actions

Our paper on l1-norm low-rank matrix approximation is accepted to IEEE Transactions on Neural Networks and Learning Systems

[2014/03/17]

The following paper is accepted to IEEE Transactions on Neural Networks and Learning Systems:

  • Efficient l1-Norm-Based Low-Rank Matrix Approximations for Large-Scale Problems Using Alternating Rectified Gradient Method by Eunwoo Kim, Minsik Lee, Chong-Ho Choi, Nojun Kwak, and Songhwai Oh

  • Abstract: Low-rank matrix approximation plays an important role in the area of computer vision and image processing. Most conventional low-rank matrix approximation methods are based on the l2-norm (Frobenius norm) with principal component analysis (PCA) being the most popular among them. However, this can give a poor approximation for data contaminated by outliers (including missing data), because the l2-norm exaggerates the negative effect of outliers. Recently, in order to overcome this problem, various methods based on the l1-norm, such as robust principal component analysis methods, have been proposed for low-rank matrix approximation. Despite the robustness of the methods, they require heavy computational effort and substantial memory for high dimensional data, which is impractical for real-world problems. In this paper, we propose two efficient low-rank factorization methods based on the l1-norm that finds proper projection and coefficient matrices using the alternating rectified gradient method. The proposed methods are applied to a number of low-rank matrix approximation problems to demonstrate their efficiency and robustness. The experimental results show that our proposals are efficient in both execution time and reconstruction performance unlike other state-of-the-art methods.

Document Actions

Our paper on tracking and identification of people in a smart space is accepted to Machine Vision and Applications

[2014/03/07]

The following paper is accepted to Machine Vision and Applications:

  • OPTIMUS: Online Persistent Tracking and Identification of Many Users for Smart Spaces by Donghoon Lee, Inhwan Hwang, and Songhwai Oh
  • Abstract: A smart space, which is embedded with networked sensors and smart devices, can provide various useful services to its users. For the success of a smart space, the problem of tracking and identification of smart space users is of paramount importance. We propose a system, called Optimus, for persistent tracking and identification of users in a smart space, which is equipped with a camera network. We assume that each user carries a smartphone in a smart space. A camera network is used to solve the problem of tracking multiple users in a smart space and information from smartphones is used to identify tracks. For robust tracking, we first detect human subjects from images using a head detection algorithm based on histograms of oriented gradients (HOG). Then, human detections are combined to form tracklets and delayed track-level association is used to combine tracklets to build longer trajectories of users. Lastly, accelerometers in smartphones are used to disambiguate identities of trajectories. By linking identified trajectories, we show that the average length of a track can be lengthened by over six times. The performance of the proposed system is evaluated extensively in realistic scenarios.

Document Actions

Call for Papers: ICCAS 2014

October 22-25, 2014 KINTEX (near the downtown of Seoul), Korea

2014 International Conference on Control, Automation, and Systems

ICCAS 2014 will be held at KINTEX (near the downtown of Seoul), Korea on October 22-25, 2014 jointly with Robot World 2014. The aim of the ICCAS is to bring together researchers and engineers worldwide to present their latest works, and disseminate the state-of-the-art technologies related to control, automation, robotics, and systems. The conference program will include Technical Workshops & Tutorials on Tuesday, October 21. The workshops and tutorials of this year will be specially interesting to those who want to learn about the latest trends and subjects.

[Call for papers]

Important dates:

  • April 4, 2014 - Submission of organized session proposals 
  • April 18, 2014- Submission of full papers
  • June 20, 2014 - Notification of paper acceptance
  • July 18, 2014 - Submission of final camera-ready papers

Document Actions

Our paper on real-time navigation is accepted to ICRA 2014.

[2014/01/14]

The following paper is accepted to the IEEE International Conference on Robotics and Automation (ICRA 2014):

  • Real-Time Navigation in Crowded Dynamic Environments Using Gaussian Process Motion Control by Sungjoon Choi, Eunwoo Kim, and Songhwai Oh

  • Abstract: In this paper, we propose a novel Gaussian process motion controller that can navigate through a crowded dynamic environment. The proposed motion controller predicts future trajectories of pedestrians using an autoregressive Gaussian process motion model (AR-GPMM) from the partially observable egocentric view of a robot and controls a robot using an autoregressive Gaussian process motion controller (AR-GPMC) based on predicted pedestrian trajectories. The performance of the proposed method is extensively evaluated in simulation and validated experimentally using a Pioneer 3DX mobile robot with a Microsoft Kinect sensor. In particular, the proposed method shows over 68% improvement on the collision rate compared to a reactive planner and vector field histogram (VFH). 
  • Video

Document Actions

Our paper on robust action recognition is accepted to Pattern Recognition

[2013/12/09]

The following paper is accepted to Pattern Recognition:

  • Robust Action Recognition Using Local Motion and Group Sparsity by Jungchan Cho, Minsik Lee, Hyung Jin Chang, and Songhwai Oh

  • Abstract: Recognizing actions in a video is a critical step for making many vision-based applications possible and has attracted much attention recently. However, action recognition in a video is a challenging task due to wide variations within an action, camera motion, cluttered background, and occlusions, to name a few. While dense sampling based approaches are currently achieving the state-of-the-art performance in action recognition, they do not perform well for many realistic video sequences since, by considering every motion found in a video equally, the discriminative power of these approaches are often reduced due to clutter motions, such as background changes and camera motions. In this paper, we robustly identify local motions of interest in an unsupervised manner by taking advantage of group sparsity. In order to robustly classify action types, we emphasize local motion by combining local motion descriptors and full motion descriptors and apply group sparsity to the emphasized motion features using the multiple kernel method. In experiments, we show that different types of actions can be well recognized using a small number of selected local motion descriptors and the proposed algorithm achieves the state-of-the-art performance on popular benchmark datasets, outperforming existing methods. We also demonstrate that the group sparse representation with the multiple kernel method can dramatically improve the action recognition performance.

 

Document Actions

Our paper on 3D shape modeling is accepted to Computer Vision and Image Understanding

[2013/07/26]

The following paper is accepted to Computer Vision and Image Understanding:

  • EM-GPA: Generalized Procrustes Analysis with Hidden Variables for 3D Shape Modeling by Jungchan Cho, Minsik Lee, Chong-Ho Choi, and Songhwai Oh

  • Abstract: Aligning shapes is essential in many computer vision problems and generalized Procrustes analysis (GPA) is one of the most popular algorithms to align shapes. However, if some of the shape data are missing, GPA cannot be applied. In this paper, we propose EM-GPA, which extends GPA to handle shapes with hidden (missing) variables by using the expectation-maximization (EM) algorithm. For example, 2D shapes can be considered as 3D shapes with missing depth information due to the projection of 3D shapes into the image plane. For a set of 2D shapes, EM-GPA finds scales, rotations and 3D shapes along with their mean and covariance matrix for 3D shape modeling. A distinctive characteristic of EM-GPA is that it does not enforce any rank constraint often appeared in other work and instead uses GPA constraints to resolve the ambiguity in finding scales, rotations, and 3D shapes. The experimental results show that EM-GPA can recover depth information accurately even when the noise level is high and there are a large number of missing variables. By using the images from the FRGC database, we show that EM-GPA can successfully align 2D shapes by taking the missing information into consideration. We also demonstrate that the 3D mean shape and its covariance matrix are accurately estimated. As an application of EM-GPA, we construct a 2D+3D AAM (active appearance model) using the 3D shapes obtained by EM-GPA, and it gives a similar success rate in model fitting compared to the method using real 3D shapes. EM-GPA is not limited to the case of missing depth information, but it can be easily extended to more general cases.

Document Actions

Our paper on distributed GP regression is accepted to CDC 2013

[2013/07/22]

The following paper is accepted to the IEEE Conference on Decision and Control (CDC 2013):

  • Distributed Gaussian Process Regression for Mobile Sensor Networks Under Localization Uncertainty by Sungjoon Choi, Mahdi Jadaliha, Jongeun Choi, and Songhwai Oh

Document Actions

Our paper on human place interaction is accepted to IEEE CPSNA 2013

[2013/05/30]

The following paper is accepted to the IEEE International Conference on Cyber-Physical Systems, Networks, and Applications (CPSNA 2013):

  • Understanding Human-Place Interaction from Tracking and Identification of Many Users by Donghoon Lee and Songhwai Oh

     

Document Actions

Our paper on human behavior prediction is accepted to RO-MAN 2013

[2013/05/03]

The following paper is accepted to the IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN 2013):

  • Human Behavior Prediction for Smart Homes Using Deep Learning by Sungjoon Choi, Eunwoo Kim and Songhwai Oh

Document Actions

Our paper on path planning is accepted to IROS 2012.

[2012/07/03]

The following paper is accepted to the IEEE International Conference on Intelligent Robots and Systems (IROS 2012):

  • A Cost-Aware Path Planning Algorithm for Mobile Robots by Junghun Suh and Songhwai Oh

Document Actions

Two papers on mobile sensor networks are accepted to CASE 2012.

[2012/05/14]

Papers accepted to the IEEE International Conference on Automation Science and Engineering (CASE 2012):

  1. A Cooperative Localization Algorithm for Mobile Sensor Networks by Junghun Suh, Seungil You, and Songhwai Oh.
  2. Actionable Topological Mapping for Navigation Using Nearby Objects by Junyoung Kim, Juyong Kim, Seungil You, Yoonseon Oh, and Songhwai Oh

Document Actions

Yoonseon Oh is awarded prestigious Global Ph.D. Fellowship from NRF

[2012/04/25]

Yoonseon Oh won the Global Ph.D. Fellowship despite fierce competition. She is one of 167 winners selected this year from a total of 1,580 applicants . Congratulations!!!

Document Actions

Call for Papers: CPSNA 2012

August 19, 2012 Seoul, Korea

International Workshop on Cyber-Physical Systems, Networks  and Applications (CPSNA'12)

in conjunction with the 18th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA'12)

Cyber-physical systems represent a next generation of embedded systems featuring a tight integration of computational and physical elements. Emerging applications of cyber-physical systems include transportation, healthcare, energy, manufacturing, entertainment, consumer electronics, environmental monitoring, and aerospace, all of which will be essential pieces of our social infrastructure. A grander vision of cyber-physical systems, however, faces a core challenge of multidisciplinary research collaborations, as their relevant technologies appear in diverse areas of science and engineering. The objective of this workshop is to explore innovative, exciting, and fresh ideas for cyber-physical systems. Contributions should emphasize on the design, implementation, and evaluation of systems, networks, and applications. The scope of CPSNA'12 will give due consideration in all areas of research that facilitate collaborations between cyber-physical systems and existing technologies. Topics of special interest include, but are not limited to, the following:

  • Embedded and real-time systems
  • Sensor networks
  • Timing analysis and verification methods and tools
  • Dependable computing
  • Ubiquitous and pervasive computing, ambient intelligence
  • Cloud and distributed computing
  • Data-intensive computing, data mining
  • Multicore and GPU programming
  • Architecture, compiler, and OS support
  • Experimental prototype systems
  • Project report on multidisciplinary research collaborations
  • Emerging applications of cyber-physical systems: autonomous vehicles, healthcare robots, smart buildings, smart grids, medical devices, virtual reality interfaces, infrastructure monitoring systems, etc.

CPSNA 2012 especially seeks papers from, but not limited to, students and young researchers. Case studies and evaluation of existing technologies are also welcome.

Date and Place

Paper Submission

CPSNA'12 invites submissions of full and short papers. Full papers must present complete work, while short papers may include work in progress. Submitted papers must adhere to page limits of 6 pages for full papers and 4 pages for short papers. The paper formats must follow 8.5-inch by 11-inch with two columns using a font size of 10 pt. In order to avoid violation of these instructions, authors are encouraged to use the IEEE proceedings template available on the following website: http://www.ieee.org/conferences_events/conferences/publishing/

Important Dates

  • Submission deadline: May 20, 2012 (11:59pm Pacific Time)
  • Notification: June 19, 2012
  • Camera-ready version: TBD
  • Workshop: August 19, 2012

Program Co-Chairs

  • Insik Shin, KAIST, Korea
  • Songhwai Oh, Seoul National University, Korea

Organizers

  • Arvind Easwaran, Honeywell, USA
  • Li-Pin Chang, National Chiao-Tung University, Taiwan
  • Jian-Jia Chen, Karlsruhe Institute of Technology, Germany
  • Shinpei Kato, University of California, Santa Cruz, USA
  • Sung-Soo Lim, Kookmin University, Korea
  • Hiroki Matsutani, Keio University, Japan
  • Songhwai Oh, Seoul National University, Korea
  • Insik Shin, KAIST, Korea

Program Committee

  • Benny Akesson, Eindhoven University of Technology, Netherlands
  • Lars Bauer, Karlsruhe Institute of Technology, Germany
  • Moris Behnam, Malardalen University, Portugal
  • Konstantinos Bletsas, Polytechnic Institute of Porto, Portugal
  • Tommaso Cucinotta, Bell Labs, Ireland
  • Yaser Fallah, West Virginia University, USA
  • Jen-Wei Hsieh, National Taiwan University of Science and Technology, Taiwan
  • Kanghee Kim, Soongsil University, Korea
  • Kyong Hoon Kim, Kyoungsang National University, Korea
  • Jinkyu Lee, University of Michigan, USA
  • Kyoungwoo Lee, Yonsei University, Korea
  • Naoya Maruyama, Tokyo Institute of Technology, Japan
  • Sibin Mohan, University of Illinois at Urbana-Champaign, USA
  • Thomas Nolte, Malardalen University, Sweden
  • Kyung-Joon Park, DGIST, Korea
  • Rodolfo Pellizzoni, University of Waterloo, Canada
  • Linh Thi Xuan Phan, University of Pennsylvania, USA
  • Hyunok Oh, Hanyang University, Korea
  • Anthony Rowe, Carnegie Mellon University, USA
  • Hiroshi Sasaki, Kyushu University, Japan
  • Yi Wang, Hong Kong Polytech University, China

Steering Committee

  • Tei-Wei Kuo, National Taiwan University, Taiwan
  • Tatsuo Nakajima, Waseda University, Japan
  • Joseph K. Ng, Hong Kong Baptist University, China
  • Seongsoo Hong, Seoul National University, Korea
  • Sang H. Son, University of Virginia, USA

Document Actions

Junghun Suh appears in ECE Life

[2012/03/01] Junghun Suh's interview with ECE Life at his graduation.

ecelife.png

Document Actions

Junghun Suh wins the Outstanding Master's Thesis Award.

[2011/08/01] Awarded from the Department of Electrical Engineering, Seoul National University.

Document Actions

A paper on camera sensor networks is accepted to CPSNA 2011.

[2011/06/10]

virtuallock

Virtual Lock: A Smartphone Application for Personal Surveillance Using Camera Sensor Networks

Sangseok Yoon, Hyeongseok Oh, Donghoon Lee, and Songhwai Oh, CPSNA 2011, Toyama, Japan

Document Actions

Seungil You's guardian robot system wins the third place award.

[2010/11/16] 2010 Electrical Exhibition at the Seoul National University

Seungil You and Professor Songhwai Oh designed and implemented new concept of a home safety system using smartphones. When an object is chosen on the iPhone screen, a robot follows that object with a tracking algorithm based on a computer vision algorithm, and the iPhone screen shows an image from webcam on the robot. This system can help parents to protect their babies when they have to do other thing. Parents can track their babies status from a remote area using a  smartphone. In addition, elders can be protected by similar ways. This, so called a 'guardian robot system', was presented at the 2010 Electronics Exhibition at the Seoul National University, and won the third place award.

Document Actions

Minsu Kang wins the gold best paper award.

[2010/12/04] 2010 IEEE Seoul Section Student Paper Contest

Title : An Interactive Co-Simulation System for Virtual and Real Robots using the Player Project

Abstract:
An interactive co-simulation system for virtual and real robots is proposed in this paper. The proposed system is based on the Player project which is open source software for robotics research, which enables the rapid development of algorithms for robotic systems. The proposed co-simulation system seamlessly combines real-world robots and virtual robots in a single simulation environment so that the simulation of multi mobile robots can be more realistically performed. By using the system, robots in real-world and robots in virtual-world can interact with each other. The system has been successfully tested in an experiment with 2 real-world robots interacting with 20 virtual robots.

Document Actions

Document Actions