Abstract
A model calculation is presented simulating the coordinated interaction between the walking legs of a multi-legged animal. The neural network consists of separate modules with oscillatory capabilities. It has the ability to adjust the necessary parameters for producing a coordinated interaction between the modules in a self-organizing fashion. Some sort of reinforcement comparison learning is used to train the network. It starts oscillations in a completely uncoupled state. After about 100 learning steps, the generation of a stable alternating pattern is usually terminated. Then, the network is able to maintain synchronization, even when disturbances are applied to single agents or to the network as a whole.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bässler U (1986) On the definition of central pattern generator and its sensory control. Biol Cybern 54:65–69
Barto AG, Sutton RS, Anderson CW (1984) Neuron-like elements that can solve difficult learning control problems. IEEE Trans Syst Man Cybern 13:835–846
Brodfuehrer PD, Friesen WO (1986) Initiation of swimming activityby trigger neurons in the leech subesophageal ganglion. I. Output connections of Tr1 and Tr2. J Comp Physiol A 159:489–502
Brown TG (1914) On the nature of the fundamental activity of the nervous centres; together with an analysis of the conditioning of rhythmic activity in progression, and a theory of the evolution of function in the nervous system. J Physiol (London) 48:18–46
Chapman D, Kaelbling LP (1990) Learning from Delayed Reinforcement in a Complex Domain. Teleos Research, Technical Report No. TR-90-11
Cruse H (1980) A quantitative model of walking incorporating central and peripheral influences. II. The connections between the different legs. Biol Cybern 37:137–144
Cruse H (1990) What mechanisms coordinate leg movements in walking arthropods? TINS 13:15–21
Cruse H, Epstein S (1982) Peripheral influences on the movement of the legs in a walking insect Carausius morosus. J Exp Biol 101:161–170
Cruse H, Graham D (1985) Models for the Analysis of Walking in Arthropods. In: Bush BMH, Clarac F (eds) Coordination of motor behavior, Cambridge University Press, Cambridge, pp 281–301
Cruse H, Müller U (1986) Two coupling mechanisms which determine the coordination of ipsilateral legs in the walking crayfish. J Exp Biol 121:349–369
Cruse H, Müller-Wilm U, Dean J (1993) Artificial Neural Nets for Controlling a Six-Legged Walking System. Proceedings of the 2nd International Conference on Simulation of Adaptive Behavior. Meyer JA, Roitblat H, Wilson SW (eds). MIT Press, Cambridge
Clarac F (1985) Stepping Reflexes and the Sensory Control of Walking in Crustacea. In: Barnes WJP, Gladden MH (eds) Feedback and motor control in invertebrates and vertebrates. Croom Helm, London, pp 379–400
Dean J (1991) A model of leg coordination in the stick insect Carausius morosus. II. Description of the kinematic model and simulation of normal step patterns. Biol Cybern 64:403–411
Dean J, Wendler (1983) Stick insect locomotion on a walking wheel: interleg coordination of leg position. J Exp Biol 103:75–94
Doya K, Yoshizawa S (1989) Adaptive neural oscillator using continuous-time back-propagation learning. Neural Networks 2:375–385
Graham D (1977) Simulation of a model for the coordination of leg movement in free walking insects. Biol Cybern 26:187–198
Graham D (1985) Pattern and control of walking in insects. In: Advances in insect physiology, vol 18. Academic Press, London, pp 31–140
Harmon LD (1964) Neuromimes; action of a reciprocally inhibiting pair. Science 146:1323–1325
Heger M, Berns K (1992) Reinforcement-Lernen unter Berücksichtigung des Worst-Case (in preparation)
Matsuoka K (1987) Mechanisms of frequency and pattern control in the neural rhythm generators. Biol Cybern 56:345–35
Morishita I, Yajima A (1972) Analysis and simulation of networks of mutually inhibiting neurons. Kybernetik 11:154–165
Müller U, Clarac F (1990) Dactyl sensory influences on rock lobster locomotion. II. Role in interleg coordination. J Exp Biol 148:113–128
Müller U, Cruse H (1991a) The contralateral coordination of walking legs in the crayfish Astacus leptodactylus. I. Experimental Results. Biol Cybern 64:429–436
Müller U, Cruse H (1991b) The contralateral coordination of walking legs in the crayfish Astacus leptodactylus. II. Model Calculations. Biol Cybern 64:437–446
Müller-Wilm U, Dean J, Cruse H, Weidemann HJ, Eltze J, Pfeiffer F (1992) Kinematic model of a stick insect as an example of a 6-legged walking system. J Adap Behav 1:155–169
Pearlmutter BA (1989) Learning state space trajectories in recurrent neural networks. Neural Comput 1:263–269
Rowat PF, Selverston AI (1991) Learning algorithms for oscillatory networks with gap junctions and membrane currents. Network 2:17–41
Rumelhart DE, McClelland JL (1986) Parallel distributed processing, MIT Press, Cambridge
Selverston AI, Moulins M (1987) The crustacean stomatogastric system. Springer, Berlin Heidelberg New York
Sutton RS (1984) Temporal credit assignment in reinforcement learning. COINS PhD Thesis, University of Massachusetts
Sutton RS (1990) Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. Proceedings of the Seventh International Conference of Machine earning. Kaufmann M (ed) Austin, Texas
Watkins CJCH (1989) Learning from delayed rewards. PhD Thesis, King's College, Cambridge
Williams RJ, Zipser D (1989) A learning algorithm for continually running fully recurrent neural networks. Neural Comput 1:270–280
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Müller-Wilm, U. A neuron-like network with the ability to learn coordinated movement patterns. Biol. Cybern. 68, 519–526 (1993). https://doi.org/10.1007/BF00200811
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00200811