Versatile modular neural locomotion control with fast learning

Legged robots have significant potential to operate in unstructured environments. The design of locomotion control is, however, still challenging. Currently, controllers must be manually designed for specific robots and tasks, or automatically designed via machine learning methods that require long training times and yield large opaque controllers. Drawing inspiration from animal locomotion, we propose a simple yet versatile modular neural control structure with fast learning. The key advantages of our approach are that behaviour-specific control modules can be added incrementally to obtain increasingly complex emergent locomotion behaviours, and that neural connections can be quickly and automatically learned. In a series of experiments, we show how eight modules can be quickly learned and added to a base control module to obtain emergent adaptive behaviours allowing a hexapod robot to navigate in complex environments. We also show that modules can be added and removed during operation without affecting the functionality of the remaining controller. Finally, the controller is successfully demonstrated on a physical robot. Taken together, our study reveals a significant step towards fast automatic design of versatile neural locomotion control. Controllers for robotic locomotion patterns deal with complex interactions and need to be carefully designed or extensively trained. Thor and Manoonpong present a modular approach for neural pattern generators that allows incremental and fast learning.