Title:
Rule-based reasoning and neural network perception for safe off-road robot mobility
Rule-based reasoning and neural network perception for safe off-road robot mobility
Author(s)
Tunstel, Edward
Howard, Ayanna M.
Seraji, Homayoun
Howard, Ayanna M.
Seraji, Homayoun
Advisor(s)
Editor(s)
Collections
Supplementary to
Permanent Link
Abstract
Operational safety and health monitoring are critical matters for autonomous field mobile robots such as planetary rovers operating on challenging terrain. This paper describes relevant rover safety and health issues and presents an approach to maintaining vehicle safety in a mobility and navigation context. The proposed rover safety module is composed of two distinct components: safe attitude (pitch and roll) management and safe traction management. Fuzzy logic approaches to reasoning about safe attitude and traction management are presented, wherein inertial sensing of safety status and vision-based neural network perception of terrain quality are used to infer safe speeds of traversal. Results of initial field tests and laboratory experiments are also described. The approach provides an intrinsic safety cognizance and a capacity for reactive mitigation of robot mobility and navigation risks.
Sponsor
Date Issued
2002-09
Extent
Resource Type
Text
Resource Subtype
Article
Pre-print
Pre-print