# DeepCPG Policies for Robot Locomotion

## TL;DR

This paper introduces DeepCPG policies that embed biological-inspired CPGs into neural networks for efficient, end-to-end learning of robot locomotion, demonstrating successful transfer from simulation to real-world insectoid robots.

## Contribution

The work develops novel DeepCPG policies integrating CPGs into neural networks, enabling scalable, sample-efficient learning of complex locomotion behaviors in multi-legged robots.

## Key findings

- DeepCPG policies outperform traditional methods in sample efficiency.
- Successful transfer of learned policies from simulation to real robots.
- Scalable approach using modular and multi-agent DRL.

## Abstract

Central Pattern Generators (CPGs) form the neural basis of the observed rhythmic behaviors for locomotion in legged animals. The CPG dynamics organized into networks allow the emergence of complex locomotor behaviors. In this work, we take this inspiration for developing walking behaviors in multi-legged robots. We present novel DeepCPG policies that embed CPGs as a layer in a larger neural network and facilitate end-to-end learning of locomotion behaviors in deep reinforcement learning (DRL) setup. We demonstrate the effectiveness of this approach on physics engine-based insectoid robots. We show that, compared to traditional approaches, DeepCPG policies allow sample-efficient end-to-end learning of effective locomotion strategies even in the case of high-dimensional sensor spaces (vision). We scale the DeepCPG policies using a modular robot configuration and multi-agent DRL. Our results suggest that gradual complexification with embedded priors of these policies in a modular fashion could achieve non-trivial sensor and motor integration on a robot platform. These results also indicate the efficacy of bootstrapping more complex intelligent systems from simpler ones based on biological principles. Finally, we present the experimental results for a proof-of-concept insectoid robot system for which DeepCPG learned policies initially using the simulation engine and these were afterwards transferred to real-world robots without any additional fine-tuning.

---
Source: https://tomesphere.com/paper/2302.13191