From the Sea to the Sidewalk: The Evolution of Hexapod Walking Gaits by a Genetic Algorithm

Abstract

Abstract.A simple evolutionary approach to developing walking gaits for a legged robot is presented. Each leg of the robot is given its own controller in the form of a cellular automaton which serves to arbitrate between a number of fixed basis behaviours. Local communication exists between neighbouring legs. Genetic algorithms search for cellular automata whose arbitration results in successful walking gaits. An example simulation of the technique is presented as well as results of application to Kafka, a hexapod robot.

Evolutionary-Based Control Approaches for Multirobot Systems

“…For the walking gait task (Earon et al, 2000); (Barfoot et al, 2006), a network of leg based controllers forming a hexapod robot (Fig. 9) need to find a suitable walking gait pattern that enables the robot to travel forward.…”

“…Although the technique uses a global fitness function, such design intervention requires domain knowledge of the task and ad hoc design choices to facilitate searching for a solution. Alternatively, CA lookup tables could be networked to exploit inherent modularity in a physical system during evolution, such as series of locally coupled leg controllers for a hexapod robot (Earon et al, 2000). This is in contrast to some predefined recurrent neural network solutions such as by (Beer & Gallagher, 1992), (Parker & Li, 2003) that are used to evolve 'leg cycles' and gait coordination in two separate stages.…”

Aggregate Selection in Evolutionary Robotics

“…These include gait evolution in legged robots [44] [7][45] [46], and flying lift generation in a flying robot [25]. Simple actuator coordination tasks do not fall under the heading of environmentally situated intelligent autonomous robot control and do not usually produce complex reactions to environmental sensor stimuli.…”

“…In [44] the authors use embodied evolution to develop gaits for a hexapod robot. An aggregate fitness function was used that measured the distance traveled by the robot while walking on a treadmill.…”

“…The robot was a pneumatic hexapod of minimalist design. The authors used the same aggregate fitness function as did [44]. Distance for the aggregate fitness function was determined using images taken from an overhead camera.…”