Self-Localization and Stream Field Based Partially Observable Moving Object Tracking

Abstract

Recommended by Fredrik GustafssonSelf-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.

A review and framework of laser-based collaboration support

“…In this application, a distributed data fusion algorithm was used to combine the local maps produced by each robot into a shared global map. Multi robot collaborative localization using data fusion from laser scanners was investigated in a number of studies (Jiang & Chen, 2008;Tseng & Tang, 2009).…”

Goal-oriented and map-based people tracking using virtual force field

“…In [9], the social force motion model was integrated into a multi-hypothesis tracker for crowed people tracking. In [10], a person's motion is deemed as passive in a stream field, where the attractive and repulsive forces are resulted from the person's goal and an environment, respectively. The stream field based tracking algorithm can use a known map and an estimated goal even if a person is occluded [10].…”

“…In [10], a person's motion is deemed as passive in a stream field, where the attractive and repulsive forces are resulted from the person's goal and an environment, respectively. The stream field based tracking algorithm can use a known map and an estimated goal even if a person is occluded [10]. In [11], SLAMSAT further extends the stream field base tracking to estimate the robot and the person's position and the map, even if the person is occluded.…”

“…In [10], the computational complexity of the stream field based tracking increases with the size of the map and the number of goals. The reason is that a multi-hypotheses tracking system will become more complex if it simultaneously considers a person's goal, other persons, and an environment.…”

“…The reason is that a multi-hypotheses tracking system will become more complex if it simultaneously considers a person's goal, other persons, and an environment. Another problem of [10] is that the aliasing of obstacle shape arises due to the feature based map. For example, the object shape is modeled as a circle ( Fig.…”