An implemented architecture integrating onboardplanning , scheduling , execution , diagnosis , monitoring and control for autonomous spacecraftBarney

NASA has recently announced the New Millennium Program (NMP) to develop \faster, better, cheaper" spacecraft in order to establish a \virtual presence" in space. A crucial element in achieving this vision is onboard spacecraft autonomy, requiring us to automate functions which have traditionally been achieved on ground by humans. These include planning activities, sequencing spacecraft actions, tracking spacecraft state, ensuring correct functioning, recovering in cases of failure and reconnguring hardware. In response to these challenging requirements, we analyzed the spacecraft domain to determine its unique properties and developed an architecture which provided the required functionality. This architecture integrates traditional real-time monitoring and control with constraint-based planning and scheduling, robust multi-threaded execution , and model-based diagnosis and reconnguration. In a ve month eeort we successfully demonstrated this implemented architecture in the context of an autonomous insertion of a simulated spacecraft into orbit around Saturn, trading oo science and engineering goals, and achieving the mission goals in the face of any single point of hardware failure. This scenario turned out to be among the most complex handled by each of the component technologies. As a result of this success, the integrated architecture has been selected to control the rst NMP ight, Deep Space One, in 1998. It will be the rst AI system to autonomously control an actual spacecraft.

[1]  A. S. Aljabri,et al.  Demonstration of On-Board Maneuver Planning using Autonomous S/W Architectures , 1994 .

[2]  Johan de Kleer,et al.  Readings in qualitative reasoning about physical systems , 1990 .

[3]  Erann Gat,et al.  Integrating Planning and Reacting in a Heterogeneous Asynchronous Architecture for Controlling Real-World Mobile Robots , 1992, AAAI.

[4]  David J. Musliner,et al.  CIRCA: a cooperative intelligent real-time control architecture , 1993, IEEE Trans. Syst. Man Cybern..

[5]  Robert James Firby,et al.  Adaptive execution in complex dynamic worlds , 1989 .

[6]  Richard Levinson,et al.  A General Programming Language for Unified Planning and Control , 1995, Artif. Intell..

[7]  Barbara Hayes-Roth,et al.  An Architecture for Adaptive Intelligent Systems , 1995, Artif. Intell..

[8]  Robert D. Rasmussen,et al.  The Cassini spacecraft: Object oriented flight control software , 1993 .

[9]  John L. Bresina,et al.  Just-In-Case Scheduling , 1994, AAAI.

[10]  David P. Miller,et al.  Experiences with an architecture for intelligent, reactive agents , 1995, J. Exp. Theor. Artif. Intell..

[11]  David E. Wilkins,et al.  A Common Knowledge Representation for Plan Generation and Reactive Execution , 1995, J. Log. Comput..

[12]  M.P. Georgeff,et al.  Procedural knowledge , 1986, Proceedings of the IEEE.

[13]  Allen Newell,et al.  SOAR: An Architecture for General Intelligence , 1987, Artif. Intell..

[14]  Luca Console,et al.  Readings in Model-Based Diagnosis , 1992 .

[15]  Brian C. Williams,et al.  Diagnosing Multiple Faults , 1987, Artif. Intell..

[16]  Nicola Muscettola,et al.  HSTS: Integrating Planning and Scheduling , 1993 .

[17]  G. M. Brown,et al.  Attitude and articulation control for the Cassini spacecraft: a fault tolerance overview , 1995, Proceedings of 14th Digital Avionics Systems Conference.

[18]  Brian C. Williams,et al.  Diagnosis with Behavioral Modes , 1989, IJCAI.

[19]  Raja Chatila,et al.  Plan execution monitoring and control architecture for mobile robots , 1995, IEEE Trans. Robotics Autom..

[20]  Milind Tambe,et al.  Intelligent Agents for Interactive Simulation Environments , 1995, AI Mag..