Abstract
Neural networks can be evolved to control robot manipulators in tasks like target tracking and obstacle avoidance in complex environments. Neurocontrollers are robust to noise and can be adapted to different environments and robot configurations. In this paper, neurocontrollers were evolved to position the end effector of a robot arm close to a target in three different environments: environments without obstacles, environments with stationary obstacles, and environments with moving obstacles. The evolved neurocontrollers perform qualitatively like inverse kinematic controllers in environments with no obstacles and like path-planning controllers based on Rapidly-exploring random trees in environments with obstacles. Unlike inverse kinematic controllers and path planners, the approach reliably generalizes to environments with moving obstacles, making it possible to use it in natural environments.
Similar content being viewed by others
References
Buehrmann T, Paolo ED (2004) Closing the loop: Evolving a model-free visually-guided robot arm. Proceedings of the Ninth International Conference on the Simulation and Synthesis of Living Systems 9: 63–68
Feddema JT, Lee GCS (1990) Adaptive image feature prediction and control for visual tracking with a hand-eye coordinated camera. IEEE Trans Syst Man Cybern 20(5): 1172–1183
Henrich D, Wurll C, Worn H (1998) On-line path planning by heuristic hierarchical search. The 24th Annual Conference of the IEEE Industrial Electronics Society 4: 2239–2244
Kohl N, Stanley KO, Miikkulainen R, Samples M, Sherony R (2006) Evolving a Real-World Vehicle Warning System. Proceedings of the Genetic and Evolutionary Computation Conference 1681–1688
LaValle S (1998) Rapidly-exploring random trees: A new tool for path planning, TR 98-11. Computer Science Department, Iowa State University, Ames
LaValle S (2009) Motion Strategy Library. http://msl.cs.uiuc.edu/msl
Lewis FL, Dawson DM, Abdallah CT (2003) Robot Manipulator Control. CRC, New York
Mao Z, Hsia TC (1997) Obstacle avoidance inverse kinematics solution of redundant robots by neural networks. Robotica 15: 3–10
Moriarty DE, Miikkulainen (1996) Evolving obstacle avoidance behavior in a robot arm. From Animals to Animats: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior 4: 468–475
Nolfi S, Parisi D (1997) Learning to adapt to changing environments in evolving neural networks. Adapt Behav 5: 75–98
Shibata T, Abe T, Tanie K, Nose M (1997) Motion planning by genetic algorithm for a redundant manipulator using a model of criteria of skilled operators. Inf Sci 102: 171–186
Spong SHM, Vidyasagar M (2006) Robot Modelling and Control. Wiley, Hoboken
Stanley KO (2004) Efficient Evolution of Neural Networks through Complexification. PhD thesis, Department of Computer Science, University of Texas at Austin
Stanley KO, Miikkulainen R (2002) Evolving neural networks through augmenting topologies. Evol Comput 10(2): 99–127
Stanley KO, Miikkulainen R (2004) Evolving a Roving Eye for Go. Proceedings of the Genetic and Evolutionary Computation Conference 3103: 1226–1238
Stanley KO, Miikkulainen R (2004) Competitive coevolution through evolutionary complexification. J Artif Intell Res 21: 63–100
Stanley KO, Bryant BD, Miikkulainen R (2005) Real-time neuroevolution in the NERO video game. IEEE Trans Evol Comput 9(6): 653–668
Tian L, Collins C (2004) An effective robot trajectory planning method using a genetic algorithm. Mechatronics 14: 455–470
van der Smagt P (1994) Simderella: A robotic simulator for neuro-controller design. Neurocomputing 6(2): 281–285
Werbos PJ (1992) Neurocontrol and supervised learning: An overview and evaluation. Van Nostrand, New York
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
D’Silva, T., Miikkulainen, R. Learning Dynamic Obstacle Avoidance for a Robot Arm Using Neuroevolution. Neural Process Lett 30, 59–69 (2009). https://doi.org/10.1007/s11063-009-9111-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-009-9111-7