Speed control on an hexapod robot driven by a CNN-CPG structure

Locomotion control in legged robots is an interesting research field thatcan take inspiration from biology to design innovative bio-inspired control systems.Central Pattern Generators (CPGs) are well known neural structures devoted to generateactivation signals to allow a coordinated movement in living beings. Lookingin particular in the insect world, and taking as a source of inspiration the Drosophilamelanogaster, a hierarchical architecturemainly developedwithin the paradigmof aCellular non-linear Network (CNN) has been developed and applied to control locomotionin a fruit fly-inspired simulated hexapod robot. The modeled neural structureis able to show different locomotion gaits depending on the phase locking amongthe neurons responsible for the motor activities at the level of the leg joints and theoreticalconsideration about the generated pattern stability are discussed. Moreoverthe phase synchronization, altering the locomotion, can be used to modify the speedof the robot that can be controlled using a reference signal. To find the suitable transitionsamong patterns of coordinated movements, a reward-based learning processhas been considered. Simulation results obtained in a dynamical environment arereported analyzing the performance of the system.