067 Towards a co-pilot architecture based on embedded real-time expert systems: N. Le Fort, E. Piat, D. Ramamonjisoa, pp 403–408
- Publisher
- Elsevier Science
- Year
- 1994
- Tongue
- English
- Weight
- 121 KB
- Volume
- 2
- Category
- Article
- ISSN
- 0967-0661
No coin nor oath required. For personal study only.
✦ Synopsis
It has been implemented in a van and successfully tested on German Autobahnen. It can operate m either autonomous or copilot mode. Knowledge processing at the higher levels for the autonomous mode is presented here.
It covers the dialogues between user and system, planning and monitoring of missions, situation representation, situation assessment, and behaviour decision. The higher levels are at present being integrated in the VaMoRs system; first results are presented.
tasks to be efficiently executed in partially unknown or changing environments. The time-critical reflexive level is computationally less expensive than in previous approaches.
Control Architecture for Mobile Robots in A
Multi
-Robot Environment: An Expectation-Driven Approach M. Rude, K. Htrmann, pp 397-402 062 Preference Planning: A Reactive Approach to Robot Task Planning PJ.S. Knightbrldge, D.M. Lane, pp 373-378
Autonomous vehicles capable of operating in unstructured and partially defined environments should exhibit several characteristics, including reactivity to external events and re-assessment of the task at hand. This paper overviews previous artificial intelligence approaches to planning and introduces the preference planning architecture, which supports both reactivity and re-planning as inherent characteristics. The importance of differentiation between referential and causal knowledge is highlighted and mechanisms for providing late binding of specific data are described.