Volume 26 Issue 9 - Publication Date: 1 September 2007
Simultaneous Localization, Mapping and Moving Object Tracking
C.-C. Wang, Department of Computer Science and Information Engineering and Graduate Institute of Networking and Multimedia National Taiwan University Taipei 106, Taiwan C. Thorpe, Qatar Campus Carnegie Mellon University Pittsburgh, PA 15289, USA S. Thrun, The AI group Stanford University Stanford, CA 94305, USA M. Hebert, The Robotics Institute Carnegie Mellon University Pittsburgh, PA 15213, USAand H. Durrant-Whyte The ARC Centre of Excellence for Autonomous Systems The University of Sydney NSW 2006, Australia
Simultaneous localization, mapping and moving object tracking (SLAMMOT) involves both simultaneous localization and mapping (SLAM) in dynamic environments and detecting and tracking these dynamic objects. In this paper, a mathematical framework is established to integrate SLAM and moving object tracking. Two solutions are described: SLAMwith generalized objects, and SLAM with detection and tracking of moving objects (DATMO). SLAM with generalized objects calculates a joint posterior over all generalized objects and the robot. Such an approach is similar to existing SLAM algorithms, but with additional structure to allow for motion modeling of generalized objects. Unfortunately, it is computationally demanding and generally infeasible. SLAM with DATMOdecomposes the estimation problem into two separate estimators. By maintaining separate posteriors for stationary objects and moving objects, the resulting estimation problems are much lower dimensional than SLAM with generalized objects. Both SLAM and moving object tracking from a moving vehicle in crowded urban areas are daunting tasks. Based on the SLAM with DATMO framework, practical algorithms are proposed which deal with issues of perception modeling, data association, and moving object detection. The implementation of SLAM with DATMO was demonstrated using data collected from the CMU Navlab11 vehicle at high speeds in crowded urban environments. Ample experimental results shows the feasibility of the proposed theory and algorithms.
Multimedia Key
= Video = Data = Code = Image
Example 1: video that illustrates the processing of the SLAM with DATMO approach. (390 MB) avi
Example 2: video that shows the processing of loop closing. (159 MB) mpg
Example 3: video illustratrating the processing of multiple vehicle tracking. (4.6 MB) avi
Example 4: video illustrating multiple pedestrian tracking. (2.5 MB) avi
Example 5: video shows the 3D city modeling results. (19.6 MB) avi
Return to Contents