Automated Decision-Making for Mars Rover Onboard Science

This paper presents technology for performing autonomous commanding of a planetary rover. Through the use of AI planning, scheduling and execution techniques, the OASIS autonomous science system provides capabilities for the automated generation of a rover activity plan based on science priorities, the handling of opportunistic science, including new science targets identified by onboard data analysis software, other dynamic decision-making such as modifying the rover activity plan in response to problems or other state and resource changes. We first describe some of the particular challenges this work has begun to address and then describe our system approach. Finally, we report on our experience testing this software with a Mars rover prototype.

[1]  Erann Gat,et al.  Experiences with an architecture for intelligent, reactive agents , 1997, J. Exp. Theor. Artif. Intell..

[2]  E. D. Smith,et al.  Increased Flexibility and Robustness of Mars Rovers , 1999 .

[3]  R. Castano,et al.  Opportunistic rover science: finding and reacting to rocks, clouds and dust devils , 2006, 2006 IEEE Aerospace Conference.

[4]  Nicola Muscettola,et al.  Planning in Interplanetary Space: Theory and Practice , 2000, AIPS.

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

[6]  Reid G. Simmons,et al.  A task description language for robot control , 1998, Proceedings. 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems. Innovations in Theory, Practice and Applications (Cat. No.98CH36190).

[7]  Rob Sherwood,et al.  Using Autonomy Flight Software to Improve Science Return on Earth Observing One , 2005, J. Aerosp. Comput. Inf. Commun..

[8]  Rob Sherwood,et al.  Using Iterative Repair to Improve the Responsiveness of Planning and Scheduling , 2000, AIPS.

[9]  Tara Estlin,et al.  CLARAty: an architecture for reusable robotic software , 2003, SPIE Defense + Commercial Sensing.