论文信息 - Dependability Issues in AI-Based Autonomous Systems for Space Applications

Dependability Issues in AI-Based Autonomous Systems for Space Applications

We present a literature study of dependability issues raised by the use of artificial intelligence (AI) techniques in critical systems. Hazards specific to such approaches are identified. Drawing on two case studies of AI-based critical systems, the paper concludes by a series of recommendations.

Pascale Thévenod-Fosse | David Powell

[1] Erann Gat,et al. ESL: a language for supporting robust plan execution in embedded autonomous agents , 1997, 1997 IEEE Aerospace Conference.

[2] Benjamin D. Smith,et al. Automatic Generation of Test Oracles—From Pilot Studies to Application , 1999, Automated Software Engineering.

[3] Rachid Alami,et al. An Architecture for Autonomy , 1998, Int. J. Robotics Res..

[4] Peter H. M. Klein,et al. The Safety-Bag Expert System in the Electronic Railway Interlocking System ELEKTRA , 1991 .

[5] Maria Fox,et al. PDDL2.1: An Extension to PDDL for Expressing Temporal Planning Domains , 2003, J. Artif. Intell. Res..

[6] John Fox,et al. Safe and sound - artificial intelligence in hazardous applications , 2000 .

[7] T. L. Johnson,et al. Improving UAV mission success rate through software enabled control design , 2000, 2000 IEEE Aerospace Conference. Proceedings (Cat. No.00TH8484).

[8] P. Pandurang Nayak,et al. Remote Agent: To Boldly Go Where No AI System Has Gone Before , 1998, Artif. Intell..

[9] D. Powell,et al. Software Product Assurance for Autonomy On-Board Spacecraft , 2003 .

[10] Alan Bundy,et al. Benefits and risks of knowledge-based systems , 1989 .

[11] David Robertson,et al. Industrial Use of Safety-Related Expert Systems , 2000 .

[12] P. Pandurang Nayak,et al. A Model-Based Approach to Reactive Self-Configuring Systems , 1996, AAAI/IAAI, Vol. 2.