Papers
Intoduction:
After visiting at MIT CSAIL, I had learned how to implement probabilistic algorithms. Then, I developed steam field based tracking algorithms for occlusion problems. However, To track an occlusion object is very difficult when a robot is moving in complex environment. Therefore, I developed stream field based tracking algorithms to cope with occlusion cases. I was devoted to research and develop algorithms which can make robots self-localization, mapping, searching and tracking people. These research results are accepted by IROS 2010, EURASIP journal, ICRA 2009 workshop and ICARCV 2008. Moreover, I applied the patents based on this concepts [1].
Reference:
1. Kuo-Shih Tseng, Hsiang-Wen Hsieh, Wei-Han Wang, “A Prediction and Alarms of Moving Objects in the Hidden Blind Spot System and its Method”.
R.O.C. Patent No: I314115 (licensed)
U.S Patent No: 2009/0058,677 (pending)
Stream Field Based Tracking Algorithm:
Instead of traditional tracking algorithms, steam field based tracking algorithm is to construct a stream field, consisted of sink flow and doublet flow.
The sink flow is a virtual goal of the object and generates an attractive force for object. The doublet flow is an obstacle generated by map infomration and generates a repulsive force for object. Therefore, the algorithm considers not only environments but also the goal of the object.
Inorder to predict the goal of the obejct, we adopt Rao-Blackwellised Particle Filter (RBPF).
Here is the animation to display how stream field based tracking algorithm works.
[Goal-oriented and Map-based People Tracking Using Virtual Force Field]
Abstract:
Estimation of people tracking may become divergent in the presence of occlusion. Since the interactions between people and environments can be mathematically modeled and probabilistically estimated, stream field based tracking provides the solution where the state of the occluded people is estimated by inferring the interactive force between the virtual goal of a person and environmental features. Such tracker suffers from high computation complexity because of the multi-hypotheses of the person’s goal and feature-based map. Therefore, this paper proposes a novel virtual force field (VFF) based tracking algorithm that can be realized with a single hypothesis for the person’s goal and grid-based map. The occupied grids generate repulsive forces while the person’s goal generates attractive force in the virtual force field. Since the virtual force field based tracking integrates map, person, and the person’s goal, the position of the person sheltered by the environment can be accurately estimated in unknown environments. Compared with the Kalman filter with constant acceleration (CA) model and stream field based algorithms, our proposed scheme significantly improves the tracking accuracy in case of occlusion.
Reference:
1. Kuo-Shih Tseng and Chih-Wei Tang, "Goal-oriented and Map-based People Tracking Using Virtual Force Field," IEEE/RSJ International Conference on Intelligent Robots and System (IROS'10), Taipei, Oct. 2010. [pdf] [IROS10_presentation]
[Stream Field Based People Searching and Tracking Conditioned on SLAM]
Abstract:
People searching and tracking (SAT) is a key technology for interactive robots since the tracked people are sheltered by environments frequently. For robots, it is a tracking problem given that the target is observable, but otherwise it is a searching problem. Traditional tracking algorithms may lead to divergent estimation of object position when moving objects are unobservable. Moreover, SAT conditioned on simultaneous localization and mapping (SLAM) is complex since it aims at estimating people position, robot position, and map under sensor uncertainty. Motivated by this, we propose a novel stream functions and Rao-Blackwellised particle filter based SAT algorithm in this paper. This laser based algorithm is conditioned on simultaneous localization and mapping (SLAMSAT) to search and track people. With this, the position of the targeted person sheltered by the environment can be successfully estimated by the virtual stream field in a mapped environment. Our experimental results show that this algorithm can search and track people effectively.
A larger version video is here.
Reference:
1. Kuo-Shih Tseng and Chih-Wei Tang, "Stream Field Based People Searching and Tracking Conditioned on SLAM", IEEE International Conference on Robotics and Automation (ICRA'09) Workshop on People Detection and Tracking, Kobe, May 2009. [pdf]
[Self-Localization and Stream Field based Partially Observable Moving Object Tracking]
Abstract:
Self-localization and object tracking are key technologies for human-robot interactions. Most previous tracking algorithms focus on how to correctly estimate the position, velocity, and acceleration of a moving object based on the prior state and sensor information. What has been rarely studied so far is how a robot can successfully track the partially observable moving object with laser range finders if there is no preanalysis of object trajectories. In this case, traditional tracking algorithms may lead to the divergent estimation. Therefore, this paper presents a novel laser range finder based partially observable moving object tracking and self-localization algorithm for interactive robot applications. Dissimilar to the previous work, we adopt a stream field-based motion model and combine it with the Rao-Blackwellised particle filter (RBPF) to predict the object goal directly. This algorithm can keep predicting the object position by inferring the interactive force between the object goal and environmental features when the moving object is unobservable. Our experimental results show that the robot with the proposed algorithm can localize itself and track the frequently occluded object. Compared with the traditional Kalman filter and particle filter-based algorithms, the proposed one significantly improves the tracking accuracy.
Reference:
1. Kuo-Shih Tseng, Angela Chih-Wei Tang, “Self-Localization and Stream Field based Partially Observable Moving Object Tracking”, EURASIP Journal on Advances in Signal Processing, Special issue on Robots and Autonomy, Feb, 2009. (SCI Impact Factor = 1.055, 2008) [pdf]
[A Stream Field Based Partially Observable Moving Object Tracking Algorithm]
Abstract:
Self-localization and tracking a moving object is a key technology for service robot interactive applications. Most tracking algorithms focus on how to correctly estimate the acceleration, velocity, and position of the moving objects based on the prior states and sensor information. What has not been studied so far is tracking the partially observable moving object which is often hidden from a robot's view using lasers. Applying the traditional tracking algorithms will lead to the divergent estimation of the object's position. Therefore, in this paper, we propose a novel laser based partially observable moving object tracking and self-localization algorithm. We adopt stream functions and Rao-Blackwellised particle filter (RBPF) to predict where the partially observable moving object will go in previously mapped environmental features. Moreover, a robot can localize itself and track such a moving object according to stream field. Our experimental results show the proposed algorithm can localize itself and track the partially observable moving object effectively.
Reference:
1. Kuo-Shih Tseng, “A Stream Field Based Partially Observable Moving Object Tracking Algorithm”, 10th International Conference on Control, Automation, Robotics and Vision (ICARCV 2008) Dec. 17-20, 2008, Hanoi, Vietnam. [pdf] [ICARCV08_presentation]