Market-based Co-evolution Planning for Multiple Autonomous Vehicles

In a highly dynamic environment, an adaptive real-time mission planner is essential for controlling a team of autonomous vehicles to execute a set of assigned tasks. The optimal plan computed prior to the start of the operation might be no longer optimal when the vehicles execute the plan. This paper proposes a framework and algorithms for solving real-time task and path planning problems by combining Evolutionary Computation (EC) based techniques with a Market-based planning architecture. The planning system takes advantage of the flexibility of EC-based techniques and the distributed structure of Market-based algorithms. This property allows the vehicles to evolve their task plans and routes in response to the changing environment in real time.

[1]  T. Glenn Bailey,et al.  Reactive Tabu Search in unmanned aerial reconnaissance simulations , 1998, 1998 Winter Simulation Conference. Proceedings (Cat. No.98CH36274).

[2]  Anthony Stentz,et al.  A Market Approach to Multirobot Coordination , 2001 .

[3]  Brian Capozzi,et al.  EVOLUTIONARY APPROACHES TO PATH PLANNING THROUGH UNCERTAIN ENVIRONMENTS , 2002 .

[4]  Michael P. Wellman.  Market-aware agents for a multiagent world , 1997, Robotics Auton. Syst..

[5]  Reid G. Smith,et al.  The Contract Net Protocol: High-Level Communication and Control in a Distributed Problem Solver , 1980, IEEE Transactions on Computers.

[6]  Tara Estlin,et al.  Three Coordinated Planning Methods for Cooperating Rovers , 2000 .

[7]  Marios M. Polycarpou,et al.  A cooperative search framework for distributed agents , 2001, Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206).

[8]  Barry Brumitt,et al.  Dynamic mission planning for multiple mobile robots , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[9]  D. Rathbun,et al.  An evolution based path planning algorithm for autonomous motion of a UAV through uncertain environments , 2002, Proceedings. The 21st Digital Avionics Systems Conference.

[10]  Arthur C. Sanderson,et al.  Planning multiple paths with evolutionary speciation , 2001, IEEE Trans. Evol. Comput..

[11]  Zbigniew Michalewicz,et al.  Adaptive evolutionary planner/navigator for mobile robots , 1997, IEEE Trans. Evol. Comput..

[12]  Eduardo F. Camacho,et al.  Introduction to Model Based Predictive Control , 1999 .

[13]  Carles Sierra,et al.  Evolutionary Computing and Negotiating Agents , 1998, AMET.

[14]  Juris Vagners,et al.  EVOLVING (SEMI)-AUTONOMOUS VEHICLES , 2001 .

[15]  Anthony Stentz,et al.  A Free Market Architecture for Distributed Control of a Multirobot System , 2000 .

[16]  Cees Witteveen,et al.  Cooperation by iterated plan revision , 2000, Proceedings Fourth International Conference on MultiAgent Systems.

[17]  Jörg P. Müller,et al.  A Model for Cooperative Transportation Scheduling , 1995, ICMAS.

[18]  M. Golfarelli,et al.  Multi-agent Path Planning Based on Task-swap Negotiation , 1997 .

[19]  Tuomas Sandholm,et al.  An Implementation of the Contract Net Protocol Based on Marginal Cost Calculations , 1993, AAAI.

[20]  D. B. Fogel,et al.  Optimal routing of multiple autonomous underwater vehicles through evolutionary programming , 1990, Symposium on Autonomous Underwater Vehicle Technology.