A distributed model for mobile robot environment-learning and navigation
MIT Artificial Intelligence Laboratory, 1990 - Artificial intelligence - 128 pages
This thesis presents a method for robust mobile robot navigation, large space learning, and path planning, based on a totally distributed architecture. The described methods were implemented and tested on a physical robot. The robot, Toto, consists of an omnidirectional base supplied with a ring of twelve ultrasonic ranging sensors and a compass. It is fully autonomous with all power and processing onboard. All experimental data were gathered in unaltered office environments with static and dynamic obstacles. Toto is an example of incremental design methodology. The robot was programmed in the Behavior Language, based on the subsumption architecture. Its behavior consists of three real-time, reactive layers of competence: collision-free boundary tracing, landmark detection, and environment learning and path planning. Low-level navigation consists of a collection of simple reflex-like rules which, when acting in parallel, result in an emergency boundary-tracing behavior. This behavior is used by the landmark detector which dynamically extracts features from the environment using the way the robot is moving as it is moving. The landmarks are used to construct a distributed map of the environment. The map is represented as a graph of landmarks. The links in the graph are used to indicate topological adjacency, and are assigned dynamically. The structure of the environment is used to bound the outdegree of the graph nodes resulting in linear graph connectivity. (KR).
5 pages matching Chatila in this book
Results 1-3 of 5
What people are saying - Write a review
We haven't found any reviews in the usual places.
A Review of Related Work
Philosophy and Motivation
7 other sections not shown
30 degrees active node AFSMs allows the robot approach boundary tracing boundary-tracing Brooks chapter Chatila classical planning cognitive map collision-free compass bearing computation connections Connell consists corridor deactivated described direction distributed Drumheller dynamic edging distance edging-distance emergent behaviors example explored fanout Figure Flynn global goal goal-call goal-directed navigation goal-oriented navigation graph nodes graph representation graph topology grid Hippocampus IEEE implementation inputs Kuipers landmark detection landmark disambiguation landmark matching landmark types lateral inhibition layers of competence learning linear list liquid crystal display localization low-level navigation Lozano-Perez Mataric method Mobile Robot Moravec navigation algorithm navigation rules neighbor object obstacle office environments optimal outdegree path planning performed physical robot processor propagated qualitative rats resulting robot is moving robot's current routing simple simulation sonar data space spatial static structure subsumption architecture switchboard task tested thesis topological adjacency Toto's transducers turn ultrasonic ranging sensors utilizes world model XX*o uo