An intelligent terrain-based navigation system for planetary rovers

A fuzzy logic framework for onboard terrain analysis and guidance towards traversable regions. An onboard terrain-based navigation system for mobile robots operating on natural terrain is presented. This system utilizes a fuzzy-logic framework for onboard analysis of the terrain and develops a set of fuzzy navigation rules that guide the rover toward the safest and the most traversable regions. The overall navigation strategy deals with uncertain knowledge about the environment and uses the onboard terrain analysis to enable the rover to select easy-to-traverse paths to the goal autonomously. The navigation system is tested and validated with a set of physical rover experiments and demonstrates the autonomous capability of the system.

[1]  Steven Dubowsky,et al.  Rapid physics-based rough-terrain rover planning with sensor and control uncertainty , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[2]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[3]  William Whittaker,et al.  Experience with rover navigation for lunar-like terrains , 1995, Proceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots.

[4]  Stephen Yurkovich,et al.  Fuzzy Control , 1997 .

[5]  Homayoun Seraji,et al.  Vision-based terrain characterization and traversability assessment , 2001, J. Field Robotics.

[6]  Homayoun Seraji,et al.  Fuzzy traversability index: A new concept for terrain-based navigation , 2000, J. Field Robotics.