Runtime plan adaptation in structured reactive controllers

Autonomous robots that perform complex jobs in changing env ironments must be capable of adapting their plans as the envir onmental conditions or their tasks change. This raises the pro blem of deciding whether, when, where, and how to revise the plans as the robots’ beliefs change. This paper investigates an approach to execution time plan a d ptation in which the plans themselves specify the plan adapta tion processes. In this approach the robot makes strategical (fa rsighted) adaptations while it executes a plan using tactical (immediate) decisions and overwrites tactical adaptations after strat egical decisions have been reached (if necessary). We present experime nts in which the plan adaptation technique is used for the control o f tw autonomous mobile robots. In one of them it controlled the co urse of action of a museums tourguide robot that has operated for t hirteen days and performed about 3200 plan adaptations reliabl y. 1 Introdu tion

[1]  Michael Beetz,et al.  Improving Robot Plans During Their Execution , 1994, AIPS.

[2]  Gerald Jay Sussman,et al.  A Computer Model of Skill Acquisition , 1975 .

[3]  Marcel Schoppers,et al.  Universal Plans for Reactive Robots in Unpredictable Environments , 1987, IJCAI.

[4]  Wolfram Burgard,et al.  GOLEX - Bridging the Gap between Logic (GOLOG) and a Real Robot , 1998, KI.

[5]  Sven Koenig.  Agent-Centered Search: Situated Search with Small Look-Ahead , 1996, AAAI/IAAI, Vol. 2.

[6]  D. McDermott.  Transformational Planning of Reactive Behavior , 1992 .

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

[8]  Edmund H. Durfee,et al.  Development of Iterative Real-time Scheduler to Planner Feedback , 1997, IJCAI.

[9]  Michael Beetz,et al.  Fast Probabilistic Plan Debugging , 1997, ECP.

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

[11]  Craig Boutilier,et al.  Decision-Theoretic Planning: Structural Assumptions and Computational Leverage , 1999, J. Artif. Intell. Res..

[12]  Martha E. Pollack,et al.  Introducing the Tileworld: Experimentally Evaluating Agent Architectures , 1990, AAAI.

[13]  Drew McDermott,et al.  A reactive plan language , 1991 .

[14]  Michael Beetz.  Structured reactive controllers: controlling robots that perform everyday activity , 1999, AGENTS '99.

[15]  Michael Beetz,et al.  Local Planning of Ongoing Activities , 1996, AIPS.

[16]  Erann Gat,et al.  An Autonomous Spacecraft Agent Prototype , 1997, AGENTS '97.

[17]  Shlomo Zilberstein,et al.  Using Anytime Algorithms in Intelligent Systems , 1996, AI Mag..

[18]  Mark S. Fox,et al.  Intelligent Scheduling , 1998 .

[19]  Dirk Schulz.  Template-based state estimation of dynamic objects , 1999, 1999 Third European Workshop on Advanced Mobile Robots (Eurobot'99). Proceedings (Cat. No.99EX355).

[20]  Wolfram Burgard,et al.  The Interactive Museum Tour-Guide Robot , 1998, AAAI/IAAI.

[21]  Michael Beetz,et al.  Probabilistic, Prediction-Based Schedule Debugging for Autonomous Robot Office Couriers , 1999, KI.

[22]  Michael Beetz,et al.  Planning, Scheduling, and Plan Execution for Autonomous Robot Office Couriers , 1998 .

[23]  Karen Zita Haigh,et al.  Xavier: experience with a layered robot architecture , 1997, SGAR.

[24]  Anand S. Rao,et al.  An Abstract Architecture for Rational Agents , 1992, KR.

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

[26]  Michael P. Georgeff,et al.  Decision-Making in an Embedded Reasoning System , 1989, IJCAI.

[27]  Michael Beetz,et al.  Expressing Transformations of Structured Reactive Plans , 1997, ECP.

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