Path Planning for Autonomous Robots Using Neural Networks

The realization that some forms of artificial potential fields (APF) for path planning can be developed by parallel distributed means has prompted research efforts in applying neural networks to the problem of generating these fields. This paper presents a neural network paradigm capable of exhibiting behavior that is useful for developing a variety of artificial potential fields for evaluating paths for autonomous robots. The neural network is called the Wave Expansion Neural Network or WENN. The WENN develops a topologically ordered neural map of the robot's environment, specifying the obstacles and the target configuration. The WENN neuron activity distribution is used as an APF to evaluate paths for the robot. The results are supported by computer simulations to illustrate the performance of the network.

[1]  Narendra Ahuja,et al.  Gross motion planning—a survey , 1992, CSUR.

[2]  Mohamad H. Hassoun,et al.  Locally interconnected layered neural network for path optimization , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[3]  B. V. K. Vijaya Kumar,et al.  The wave expansion neural network , 1997, Neurocomputing.

[4]  B.V.K.V. Kumar,et al.  A neural network architecture for path planning , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[5]  Michael Lemmon,et al.  Real-Time Optimal Path Planning Using a Distributed Computing Paradigm , 1991, 1991 American Control Conference.

[6]  Chee-Keng Yap,et al.  A "Retraction" Method for Planning the Motion of a Disc , 1985, J. Algorithms.

[7]  Michael Lemmon,et al.  2-Degree-of-freedom Robot Path Planning using Cooperative Neural Fields , 1991, Neural Computation.

[8]  Jean-Claude Latombe,et al.  Numerical potential field techniques for robot path planning , 1991, Fifth International Conference on Advanced Robotics 'Robots in Unstructured Environments.

[9]  Narendra Ahuja,et al.  A potential field approach to path planning , 1992, IEEE Trans. Robotics Autom..

[10]  Tomás Lozano-Pérez,et al.  Spatial Planning: A Configuration Space Approach , 1983, IEEE Transactions on Computers.

[11]  Sukhan Lee,et al.  Neural computation for collision-free path planning , 1991, J. Intell. Manuf..

[12]  O. Khatib,et al.  Real-Time Obstacle Avoidance for Manipulators and Mobile Robots , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[13]  Ashraf A. Kassim,et al.  Using the wave expansion neural network for path generation , 1994, Defense, Security, and Sensing.

[14]  Yoram Koren,et al.  Real-time obstacle avoidance for fast mobile robots in cluttered environments , 1990, Proceedings., IEEE International Conference on Robotics and Automation.

[15]  Pradeep K. Khosla,et al.  Superquadric artificial potentials for obstacle avoidance and approach , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[16]  Jean-Claude Latombe,et al.  Robot Motion Planning: A Distributed Representation Approach , 1991, Int. J. Robotics Res..

[17]  Oussama Khatib,et al.  Real-Time Obstacle Avoidance for Manipulators and Mobile Robots , 1985, Autonomous Robot Vehicles.