A hybrid mobile robot architecture with integrated planning and control

ABSTRACT

Research in the planning and control of mobile robots has received much attention in the past two decades. Two basic approaches have emerged from these research efforts: deliberative vs.\ reactive. These two approaches can be distinguished by their different usage of sensed data and global knowledge, speed of response, reasoning capability, and complexity of computation. Their strengths are complementary and their weaknesses can be mitigated by combining the two approaches in a hybrid architecture. This paper describes a method for goal-directed, collision-free navigation in unpredictable environments that employs a behavior-based hybrid architecture with asynchronously operating behavioral modules. It differs from existing hybrid architectures in two important ways: (1) the planning module produces a sequence of checkpoints instead of a conventional complete path, and (2) in addition to obstacle avoidance, the reactive module also performs target reaching under the control of a self-organizing neural network. The neural network is trained to perform fine, smooth motor control that moves the robot through the checkpoints. These two aspects facilitate a tight integration between high-level planning and low-level control, which permits real-time performance and easy path modification even when the robot is en route to the goal position.

REFERENCES

• 1: Ronald C. Arkin, An Behavior-based Robotics, MIT Press, Cambridge, MA, 1998
• 2: R. C. Arkin and T. Balch.AuRA: Principles and practices in review. J. Experimental and Theoretical AI, 2-3:175--189, 1997.
• 3: R. P. Bonasso, R. J. Firby, E. Gat, D. Kortenkamp, D. Miller, and M. Slack. Experiences with an architecture for intelligent, reactive agents. J. Experimental and Theoretical AI, 9(1), 1997.
• 4: V. Braitenberg. Vehicles: Experiments in Synthetic Psychology. MIT Press, Cambridge, MA, 1984.
• 5: O. Brock and L. E. Kavraki. Decomposition-based motion planning: A framework for real-time motion planning in high-dimensional configuration spaces. In Proc. ICRA, volume 2, pages 1469--1474, 2001.
• 6: O. Brock and O. Khatib. Executing motion plans for robots with many degrees of freedom in dynamic environments In Proc. ICRA, volume 1, pages 1--6, 1998.
• 7: O. Brock and O. Khatib. High-speed navigation using the global dynamic window approach. In Proc. ICRA, pages 341--346, 1999.
• 8: R. Brooks. A robust layered control system for a mobile robot. IEEE J. Robotics and Automation, 2(1):14--23, 1986.
• 9: R. Chatila and J.-C. Laumon. Position referencing and consistent world modeling for mobile robots. In Proc. ICRA, 1985.
• 10: W. Choi and J.-C. Latombe. A reactive architecture for planning and executing robot motions with incomplete knowledge. In Proc. IROS, volume 1, pages 24--29, 1991.
• 11: Jonathan H. Connell, Minimalist mobile robotics: a colony-style architecture for an artificial creature, Academic Press Professional, Inc., San Diego, CA, 1990
• 12: J. H. Connell. SSS: A hybrid architecture applied to robot navigation. In Proc. ICRA, pages 2719--2724, 1992.
• 13: Vincent Decugis , Jacques Ferber, Action selection in an autonomous agent with a hierarchical distributed reactive planning architecture, Proceedings of the second international conference on Autonomous agents, p.354-361, May 10-13, 1998, Minneapolis, Minnesota, United States [doi>10.1145/280765.280859]
• 14: Erann Gat, Three-layer architectures, Artificial intelligence and mobile robots: case studies of successful robot systems, MIT Press, Cambridge, MA, 1998
• 15: G. Giralt, R. Chatila, and M. Vaisset. An integrated navigation and motion control system for autonomous multi-sensory mobile robots. In Proc. 1st Int. Symp. on Robotics Research, 1983.
• 16: Karen Zita Haigh , Manuela M. Veloso, High-level planning and low-level execution: towards a complete robotic agent, Proceedings of the first international conference on Autonomous agents, p.363-370, February 05-08, 1997, Marina del Rey, California, United States [doi>10.1145/267658.267741]
• 17: J. Heikkonen, P. Koikkalainen, and E. Oja. From situations to actions: Motion behavior learning by self-organization In Proc. ICANN, pages 262--267, 1993.
• 18: Huosheng Hu , Michael Brady, A Bayesian approach to real-time obstacle avoidance for a mobile robot, Autonomous Robots, v.1 n.1, p.69-92, 1994 [doi>10.1007/BF00735343]
• 19: R. Jamisola, M. H. Ang Jr., D. N. Oetomo, T. M. Lim, O. Khatib, and S. Y. Lim. Operational space formulation implementation to aircraft canopy polishing application using a mobile manipulator. In Proc. ICRA, 2002.
• 20: O. Khatib. A unified approach to motion and force control of robot manipulators: The operational space formulation. IEEE J. Robotics and Automation, 3(1):43--53, 1987.
• 21: O. Khatib. Mobile manipulation: The robotic assistant. Robotics and Autonomous Systems, 26:175--183, 1999.
• 22: D. E. Koditschek. Exact robot navigation by means of potential functions: Some topological considerations. In Proc. ICRA, pages 1--6, 1987.
• 23: B. H. Krogh and C. E. Thorpe. Integrated path planning and dynamic steering control for autonomous vehicles. In Proc. ICRA, pages 1664--1669, 1986.
• 24: J. E. Laird and P. S. Rosenbloom. Integrating, execution, planning, and learning in soar for external environments. In Proc. AAAI, pages 1022--1029, 1990.
• 25: Jean-Claude Latombe, Robot Motion Planning, Kluwer Academic Publishers, Norwell, MA, 1991
• 26: K. H. Low. Integrated planning and control of mobile robot with Extended Kohonen Maps. Master's thesis, National University of Singapore, 2002.
• 27: K. H. Low, W. K. Leow, and M. H. Ang Jr. Enhancing the reactive capabilities of integrated planning and control with self-organizing neural networks. In Proc. IROS, 2002. (submitted).
• 28: H. P. Moravec and D. W. Cho. A bayesian method for certainty grids. In Proc. AAAI Spring Symp. on Robot Navigation, pages 57--60, 1989.
• 29: Larry D. Pyeatt , Adele E. Howe, Integrating POMDP and reinforcement learning for a two layer simulated robot architecture, Proceedings of the third annual conference on Autonomous Agents, p.168-174, April 1999, Seattle, Washington, United States [doi>10.1145/301136.301185]
• 30: Sean Quinlan , Oussama Khatib, Towards Real-Time Execution of Motion Tasks, The 2nd International Symposium on Experimental Robotics II, p.241-254, June 25-27, 1991
• 31: H. Ritter , K. Schulten, Extending Kohonen's self-organizing mapping algorithms to learn ballistic movements, Proceedings of the NATO Advanced Research Workshop on Neural computers, p.393-406, March 1988, Neuss, Germany
• 32: Reid Simmons , Richard Goodwin , Karen Zita Haigh , Sven Koenig , Joseph O'Sullivan, A layered architecture for office delivery robots, Proceedings of the first international conference on Autonomous agents, p.245-252, February 05-08, 1997, Marina del Rey, California, United States [doi>10.1145/267658.267723]
• 33: Ignacio Soto , Mercedes Garijo , Carlos A. Iglesias , Manuel Ramos, An agent architecture to fulfill real-time requirements, Proceedings of the fourth international conference on Autonomous agents, p.475-482, June 03-07, 2000, Barcelona, Spain [doi>10.1145/336595.337574]
• 34: Sebastian Thrun , Arno Bücken , Wolfram Burgard , Dieter Fox , Thorsten Fröhlinghaus , Daniel Hennig , Thomas Hofmann , Michael Krell , Timo Schmidt, Map learning and high-speed navigation in RHINO, Artificial intelligence and mobile robots: case studies of successful robot systems, MIT Press, Cambridge, MA, 1998
• 35: Cristina Versino , Luca Maria Gambardella, Learning the Visuomotor Coordination of a Mobile Robot by Using the Invertible Kohonen Map, Proceedings of the International Workshop on Artificial Neural Networks: From Natural to Artificial Neural Computation, p.1084-1091, June 07-09, 1995

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning
          Subjects: Connectionism and neural nets
      I.2.9 Robotics

General Terms:
Algorithms, Design, Experimentation, Performance, Reliability, Theory

Keywords:
hybrid agent architectures, learning, mobile agents, perception and action in agents, performance, self-organizing systems