Evolving Neural Network Controllers to Produce Leg Cycles for Gait Generation
نویسندگان
چکیده
The generation of gaits for hexapod locomotion controllers can be divided into two main parts: the cyclic action of a single leg (leg cycles) and the coordination of all legs to combine individual leg cycles to produce forward movement. In this paper, we use a genetic algorithm (GA) to evolve the structure of an artificial neural network (NN) that produces leg cycles in a hexapod robot. The movement of the robot’s leg is controlled by a horizontal servo and vertical servo. The servos are controlled by a NN that generates a cycle of pulses. With minimal restrictions on the structure of the NN a GA is used to find the parameters of neurons and the connections between them. The pulse sequences generated by the evolved NNs resulted in leg cycles that produced efficient forward movement.
منابع مشابه
Evolving neural networks for hexapod leg controllers
The incremental evolution of neural networks to control hexapod robot locomotion can be separated into two main parts: the evolution of leg controllers that produce the cyclic action of single legs (leg cycles) and the evolution of the coordination of these individual leg controllers to produce a gait. In this paper, we use a genetic algorithm to do the first of these steps, to evolve the struc...
متن کاملEvolving Gaits for the Lynxmotion Hexapod II Robot
Gait generation for hexapod robots can be accomplished with a two-phase process, whereby leg cycles that effectively provide thrust are learned and then the proper selection and coordination of these cycles needed to produce a gait are learned. Genetic algorithms can be used to learn both the leg cycles and the coordination. In previous work, this technique was used successfully to generate gai...
متن کاملBilateral Decoupling in the Neural Control of Biped Locomotion
In this paper, a bilaterally decoupled neural controller was used to achieve stable locomotion in a 6 DOF biped robot with 5 links, implemented in a virtual physics-based simulation environment. The neural controller consists of an independent neural rhythm generator for each leg. The rhythm generator is a recurrent neural network, whose weights are optimized by a genetic algorithm and are iden...
متن کاملSynchronization and Gait Adaptation in Evolving Hexapod Robots
In this paper we present a distributed control architecture for a simulated hexapod robot with twelve degrees of freedom consisting of six homogeneous neural modules controlling the six corresponding legs that only have access to local sensory information and that coordinate by exchanging signals that diffuse in space like gaseous neuro-trasmitters. The free parameters of the neural modules are...
متن کاملHexapodal robot locomotion over uneven terrain
This paper presents a novel gait generation approach which combines a reactionary and a central pattern generator (CPG) system. The former couples isolated leg controllers by simple gait generation rules that ensure static stability and produce a continuum of gait patterns across the full speed range. The CPG system is based on six coupled oscillators and complements the reactionary system to f...
متن کامل