A biologically inspired approach to feasible gait learning for a hexapod robot

Abstract

The objective of this paper is to develop feasible gait patterns that could be used to control a real hexapod walking robot. These gaits should enable the fastest movement that is possible with the given robot's mechanics and drives on a flat terrain. Biological inspirations are commonly used in the design of walking robots and their control algorithms. However, legged robots differ significantly from their biological counterparts. Hence we believe that gait patterns should be learned using the robot or its simulation model rather than copied from insect behaviour. However, as we have found tahula rasa learning ineffective in this case due to the large and complicated search space, we adopt a different strategy: in a series of simulations we show how a progressive reduction of the permissible search space for the leg movements leads to the evolution of effective gait patterns. This strategy enables the evolutionary algorithm to discover proper leg co-ordination rules for a hexapod robot, using only simple dependencies between the states of the legs and a simple fitness function. The dependencies used are inspired by typical insect behaviour, although we show that all the introduced rules emerge also naturally in the evolved gait patterns. Finally, the gaits evolved in simulations are shown to be effective in experiments on a real walking robot.

An autonomous vehicle sequencing problem at intersections: A genetic algorithm approach

“…Genetic Algorithms (GAs), which mimic the evolutionary process in nature, have shown many successful applications to many fields, for example, to solve optimization problems (Akpinar and Bayhan, 2010;Xing et al, 2008), control problems (Witkowska et al, 2007;Belter and Skrzypczyński, 2010), operational problems (Aytug et al, 2003;Hart et al, 2005;Kashan et al, 2008;Wang et al, 1999) and transportation problems (Dridi and Kacem, 2004), etc.…”

Customized crossover in evolutionary sets of safe ship trajectories

“…EAs may be successfully combined with neural networks (Styrcz et al, 2011), reinforcement learning (Krawiec et al, 2011), ensemble machine learning methods (Troć and Unold, 2010) or heuristics which reduce the search space (Belter and Skrzypczyński, 2010). Hybrid approaches may also be utilised at various stages of EAs, including crossover (Jóźwiak and Postula, 2002).…”

Dynamic Simulation of Legged Robots Using a Physics Engine

“…We applied the simulator to a method which allows to evolutionary optimize the gait of a six-legged robot 1 . The simulator is used to test various solutions (trajectories of the robot) found by the algorithm.…”

“…However, increasing the integration time step decreases the accuracy of the simulation and can even render the simulation unstable. To solve the stability problem and preserve accuracy of the simulation, we first optimize for the parameters of the simulation, and moreover, for the physical parameters of the robot 1 . As a result, the parameters of the simulated world and robot model differ from the real parameters.…”