Title

Selective Perception For Robot Driving

Abstract

Robots performing complex tasks in rich environments need very good perception modules in order to understand their situation and choose the best action. Robot planning systems have typically assumed that perception was so good that it could refresh the entire world model whenever the planning system needed it, or whenever anything in the world changed. Our research is aimed at showing how a robot can reason about perception, how task knowledge can be used to select perceptual targets, and how this selection dramatically reduces the computational cost of perception. The domain addressed in this videotape is driving in traffic. We have developed a microscopic traffic simulator called PHAROS that defines the street environment for our research. PHAROS contains detailed representations of streets, markings, signs, signals, and cars. It can simulate perception and implement commands for a vehicle controlled by a separate program. We have also developed a computational model of driving called Ulysses that defines the driving task. The model describes how various traffic objects in the world determine what actions that a robot must take. These tools have allowed us to implement robot driving programs that request sensing actions in PHAROS, reason about right-of-way and other traffic laws, and then command acceleration and lane changing actions to control a simulated vehicle. The videotape shows three selective perception techniques that we have implemented in driving programs. Each program builds upon the concepts in the previous programs. When run in the PHAROS world, the techniques included in Ulysses-3 reduced the computational cost for perception by 9 to 12 orders of magnitude when compared to an uncontrolled, general perception system.

Publication Date

12-1-1993

Publication Title

Proceedings of the National Conference on Artificial Intelligence

Document Type

Article; Proceedings Paper

Identifier

scopus

Personal Identifier

scopus

Socpus ID

0027706081 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/0027706081

This document is currently not available here.

Share

COinS