Model based vehicle detection and tracking for autonomous urban driving
- 3.4k Downloads
Situational awareness is crucial for autonomous driving in urban environments. This paper describes the moving vehicle detection and tracking module that we developed for our autonomous driving robot Junior. The robot won second place in the Urban Grand Challenge, an autonomous driving race organized by the U.S. Government in 2007. The module provides reliable detection and tracking of moving vehicles from a high-speed moving platform using laser range finders. Our approach models both dynamic and geometric properties of the tracked vehicles and estimates them using a single Bayes filter per vehicle. We present the notion of motion evidence, which allows us to overcome the low signal-to-noise ratio that arises during rapid detection of moving vehicles in noisy urban environments. Furthermore, we show how to build consistent and efficient 2D representations out of 3D range data and how to detect poorly visible black vehicles. Experimental validation includes the most challenging conditions presented at the Urban Grand Challenge as well as other urban settings.
KeywordsVehicle tracking Autonomous driving Urban driving Bayesian model Particle filter Laser range finders
Unable to display preview. Download preview PDF.
- Burgard, W., Fox, D., Hennig, D., & Schmidt, T. (1996). Estimating the absolute position of a mobile robot using position probability grids. In Proceedings of the national conference on artificial intelligence (pp. 896–901). Google Scholar
- DARPA (2007). Urban challenge rules, revision oct. 27, 2007. http://www.darpa.mil/grandchallenge/rules.asp.
- Dellaert, F., & Thorpe, C. (1998). Robust car tracking using Kalman filtering and Bayesian templates. In Proceedings of SPIE (Vol. 3207, p. 72). Google Scholar
- Dietmayer, K., Sparbert, J., & Streller, D. (2001). Model based object classification and object tracking in traffic scenes from range images. In Proceedings of IV 2001, IEEE intelligent vehicles symposium (pp. 25–30). Google Scholar
- Doucet, A., Freitas, Nd., Murphy, K., & Russell, S. (2000). Rao-blackwellised filtering for dynamic Bayesian networks. In Proceedings of the sixteenth conference on uncertainty in artificial intelligence, San Francisco, CA (pp. 176–183). Google Scholar
- Gerkey, B., Vaughan, R., & Howard, A. (2003). The player/stage project: Tools for multi-robot and distributed sensor systems. In Proceedings of the 11th international conference on advanced robotics (pp. 317–323). Google Scholar
- Ibeo Automobile Sensor GmbH (2008). IBEO AlascaXT brochure. http://www.ibeo-as.com/english/press_downloads_brochures.asp.
- Mäkynen, A. (2000). Position-sensitive devices and sensor systems for optical tracking and displacement sensing applications. PhD thesis, Department of Electrical Engineering, Oulu University, Oulu, Finland. Google Scholar
- Mitchell, T., Hutchinson, R., Just, M., Newman, S., Stefan, R., Francisco, N., & Wang, P. X. (2002). Machine learning of fmri virtual sensors of cognitive states. In The 16th annual conference on neural information processing systems, computational neuroimaging: Foundations, concepts and methods workshop, 2002 (p. 87). Cambridge: MIT Press. Google Scholar
- Montemerlo, M. (2003). Fastslam: A factored solution to the simultaneous localization and mapping problem with unknown data association. PhD thesis, Robotics Institute, Carnegie Mellon University. Google Scholar
- Moravec, H. (1988). Sensor fusion in certainty grids for mobile robots. AI Magazine, 9(2), 61. Google Scholar
- Petrovskaya, A., & Thrun, S. (2008a). Efficient techniques for dynamic vehicle detection. In ISER, Athens, Greece. Google Scholar
- Petrovskaya, A., & Thrun, S. (2008b). Model based vehicle tracking for autonomous driving in urban environments. In RSS, Zurich, Switzerland. Google Scholar
- Petrovskaya, A., Khatib, O., Thrun, S., & Ng, A. Y. (2006). Bayesian estimation for autonomous object manipulation based on tactile sensors. In Robotics and automation. Proceedings of IEEE international conference (pp. 707–714). Google Scholar
- Schulz, D., Burgard, W., Fox, D., & Cremers, A. (2001). Tracking multiple moving targets with a mobile robot using particle filters and statistical data association. In IEEE international conference on robotics and automation, 2001. Proceedings 2001 ICRA (Vol. 2). Google Scholar
- Sick Optics (2003). LMS 200/211/220/221/291 laser measurement systems technical description. http://www.sickusa.com/Publish/docroot/Manual(s)/LMSTechnicalDescription.pdf.
- Streller, D., Furstenberg, K., & Dietmayer, K. (2002). Vehicle and object models for robust tracking in traffic scenes using laser range images. In The IEEE 5th international conference on intelligent transportation systems, 2002. Proceedings (pp. 118–123). Google Scholar
- Velodyne Lidar, Inc. (2008). High definition lidar HDL-64E S2 specifications. http://www.velodyne.com/lidar/products/specifications.aspx.
- Wang, C. C. (2004). Simultaneous localization, mapping and moving object tracking. PhD thesis, Robotics Institute, Carnegie Mellon University, Pittsburgh, PA. Google Scholar
- Zhao, L., & Thorpe, C. (1998). Qualitative and quantitative car tracking from a range image sequence. In 1998 IEEE computer society conference on computer vision and pattern recognition. Proceedings (pp. 496–501). Google Scholar