Handling uncertainty in control of autonomous robots

Autonomous robots need the ability to move purposefully and without human intervention in real-world environments that have not been speci cally engineered for them. These environments are characterized by the pervasive presence of uncertainty: the need to cope with this uncertainty constitutes a major challenge for autonomous robots. In this note, we discuss this challenge, and present some speci c solutions based on our experience on the use of fuzzy logic in mobile robots. We focus on three issues: how to realize robust motion control; how to exibly execute navigation plans; and how to approximately estimate the robot's location. 1 I had a dream It is Monday morning, and it is raining. I enter my o ce. Edi, my purple personal robot, promptly realizes my presence, and happily rolls out to get me some co ee. Down the corridor, it slips over the water left by somebody's shoes, and has to correct its trajectory by sensing the walls. The cafeteria's main door is closed, so...

• Type: Conference
• Year: 1998
• Where: DRUMS
• Authors: Alessandro Saffiotti
• Keywords: Autonomous Robots, DRUMS 1998, Purple Personal Robot, Robust Motion Control, Theoretical Computer Science