Development of a Vision-Based Robotic Follower Vehicle
J. Giesbrecht
- Year
- 2009
- Citations
- 5
Abstract
Abstract : This report provides an overview of the development of a vision-based leader/follower robotic vehicle at Defence R&D Canada - Suffield, with the eventual goal of autonomous convoying for military logistics. The experimental system uses a pan/tilt/zoom camera to track a lead vehicle or human, estimating the leader's path and following it autonomously. This vision-based approach frees the system from reliance on GPS, radios, and active sensing equipment necessary for current leader/follower systems. Included in this report are the details of the computer vision, camera control, and vehicle control algorithms, as well as the results of field trials of the camera tracking system. Finally, it reports on experiments with the complete follower system following other vehicles and even dismounted humans.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002