Title :
Terrain mapping for outdoor robots: robust perception for walking in the grass
Author :
Hoffman, Regis ; Krotkov, Eric
Author_Institution :
Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
The perception system for the Ambler, an autonomous legged mobile robot that operates in rugged environments, is described. Its performance during a 500-m autonomous outdoor walking experiment is analyzed. The perception system aggressively verifies sensor data and uses feedback from terrain contact to increase accuracy. Characteristics of a robust perception system, are identified, and the authors´ experiences in studying outdoor perception are summarized
Keywords :
distance measurement; image processing; mobile robots; 500 m; Ambler; autonomous legged mobile robot; feedback; grass; outdoor perception; outdoor robots; robust perception; sensor data verification; terrain contact; terrain mapping; walking; Computer science; Feedback; Leg; Legged locomotion; Pixel; Reflectivity; Robustness; Sensor systems; Terrain mapping; Testing;
Conference_Titel :
Robotics and Automation, 1993. Proceedings., 1993 IEEE International Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
0-8186-3450-2
DOI :
10.1109/ROBOT.1993.292033
