Abstract
In this paper we present a biologically inspired two-layered neural network for trajectory formation and obstacle avoidance. The two topographically ordered neural maps consist of analog neurons having continuous dynamics. The first layer, the sensory map, receives sensory information and builds up an activity pattern which contains the optimal solution (i.e. shortest path without collisions) for any given set of current position, target positions and obstacle positions. Targets and obstacles are allowed to move, in which case the activity pattern in the sensory map will change accordingly. The time evolution of the neural activity in the second layer, the motor map, results in a moving cluster of activity, which can be interpreted as a population vector. Through the feedforward connections between the two layers, input of the sensory map directs the movement of the cluster along the optimal path from the current position of the cluster to the target position. The smooth trajectory is the result of the intrinsic dynamics of the network only. No supervisor is required. The output of the motor map can be used for direct control of an autonomous system in a cluttered environment or for control of the actuators of a biological limb or robot manipulator. The system is able to reach a target even in the presence of an external perturbation. Computer simulations of a point robot and a multi-joint manipulator illustrate the theory.
Similar content being viewed by others
References
Amari S (1977) Dynamics of pattern formation in lateral-inhibition type neural fields. Biol Cybern 27:77–87
Barraquand J, Latombe J (1989) Robot motion planning with many degrees of freedom and dynamic constraints. In: Proceedings of the 5th International Symposium on Robotics Research (Tokyo) pp 74–83
Barraquand J, Latombe JC (1990) A Monte-Carlo algorithm for path-planning with many degrees of freedom. In: Proceedings of the IEEE International Conference on Robotics and Automation (Cincinnati, Ohio). IEEE Computer Society Press, Los Alamitos, 1712–1717
Barraquand J, Langlois B, Latombe J (1992) Numerical potential field techniques for robot path planning. IEEE Trans Syst Man Cybern 22:224–241
Bizzi E, Accornero N, Chapelle N, Hogan N (1982) Arm trajectory formation in monkeys. Exp Brain Res 46:139–143
Caminiti R, Johnson PB, Burnod Y, Galli C, Ferraina S (1990) Shifts of preferred directions of premotor cortical cells with arm movements performed across the work-space. Exp Brain Res 83:228
Connolly C, Burns J, Weiss R (1991) Path planning using Laplace's equation. In: Proceedings of the IEEE International Conference on Robotics and Automation. IEEE Computer Society Press, Los Alamitos, pp 2102–2106
Dorst L, Mandhyan I, Trovato K (1991) The geometrical representation of path planning problems. Robotics Autonomous Syst 7:181
Droulez J, Berthoz A (1991) A neural network model of sensoritopic maps with predictive short term memory properties. Proc Nat Acad Sci USA 88:9653–9657
Feldman AG (1986) Once more on the equilibrium-point hypothesis (λ model) for motor control. J Mot Behav 18:17–54
Fritzke B (1991) Unsupervised clustering with growing cell structures. Proceedings of the International Joint Conference on Neural Networks (Seatle, Wash) vol II. Piscataway NJ, IEEE, pp 531–536
Georgopoulos AP, Ashe J, Smyrnis N, Taira M (1992) The motor cortex and the coding of force. Science 256:1692–1695
Glasius R, Komoda A, Gielen CCAM (1994) Population coding in a neural net for trajectory formation. Network: Comput Neural Syst 5:549–563
Glasius R, Komoda A, Gielen CCAM (1995) Neural network dynamics for trajectory formation and obstacle avoidance. Neural Networks 8:125–133
Grossberg S (1984) Nonlinear neural networks: principles mechanisms and architectures. Neural Networks 1:17
Hogan N (1984) An organizing principle for a class of voluntary movements. J Neural Sci 4:2745–2754
Hopfield JJ (1984) Neurons with graded response have collective computational properties like those of two-state neurons. Proc Natl Acad Sci USA 81:3088
Jarris RA (1985) Collision-free trajectory planning using distance transforms. Mech Eng Trans IE Aust ME 10:187
Kalaska JF, Cohen DAD, Prud'homme M, Hyde ML (1992) Comparision of cell discharge in motor, premotor and parietal cortex during reaching: load direction-related activity in primate motor cortex using a two dimensional reaching task. Springer Berlin Heidelberg New York
Kathib O (1986) Real-time obstacle avoindance for manipulators and mobile robots. Int J Robotics Res 5:90–98
Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biol Cybern 43:59–69
Kopecz K, Schöner G (1995) Saccadic motor planning by integrating visual information and pre-information on neural dynamic fields. Biol Cybern 73:49–60
Krogh BH, Thorpe CE (1986) Integrated path planning and dynamic steering control for autonomous vehicles. Proceedings of the IEEE International Conference on Robotics and Automation (Washington, DC). Computer Society Press of the IEEE, Los Angeles, pp 1664–1669
Latombe J (1991) Robot motion planning. Kluwer Academic, Boston
Linsker R (1986a) From basic network principles to neural architecture: emergence of spatial-opponents cells. Proc Natl Acad Sci USA 83:7508–7512
Linsker R (1986b) From basic network principles to neural architecture: emergence of orientation-selective cells. Proc Natl Acad Sci USA 83:8779–8783
Linsker R (1986c) From basic network principles to neural architecture: emergence of orientation columns. Proc Natl Acad Sci USA 83: 7508–7512
Lozano-Perez T (1983) Spatial planning: a configuration space approach. IEEE Trans Comput 32:108–120
Martinetz TM (1993) Competitive Hebbian learning rule forms perfectly topology preserving maps. In: Proceedings of the International Conference on Artificial Neural Networks (Amsterdam, The Netherlands). North-Holland/Springer-Verlag, Amsterdam/Berlin Heidelberg New York, pp 427–434
Newman W, Hogan N (1987) High speed robot control and obstacle avoidance using dynamic potential function. In: Proceedings of the IEEE International Conference on Robotics and Automation (Raleigh, NC). Computer Society Press of the IEEE, Los Angeles, pp 14–24
Prassler E (1989) Electrical networks and a connectionist approach to path-finding. In: Connectionism in perspective. North-Holland, Amsterdam, p 421
Ritter HJ, Martinetz TM, Schulten KJ (1989) Topology-conserving maps for learning visuo-motor-coordination. Neural Networks 2:159–168
Schwartz JT, Sharir M (1983) On the ‘piano’ mover's problem. II. General techniques for computing topological properties of real algeraic manifolds. Adv Appl Math 4:298–351
Warren C (1989) Global path planning using artificial potential fields. In: Proceedings of the IEEE International Conference on Robotics and Automation (Scottsdale, Ariz). Computer Society Press of the IEEE, Los Angeles, pp 316–321
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Glasius, R., Komoda, A. & Gielen, S.C.A.M. A biologically inspired neural net for trajectory formation and obstacle avoidance. Biol. Cybern. 74, 511–520 (1996). https://doi.org/10.1007/BF00209422
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00209422