# Puppeteer and Marionette: Learning Anticipatory Quadrupedal Locomotion Based on Interactions of a Central Pattern Generator and Supraspinal Drive

## TL;DR

This paper explores how supraspinal drive interacts with central pattern generators in quadrupedal robots to improve anticipatory obstacle crossing, revealing that direct brain signals enhance success while CPGs improve gait efficiency.

## Contribution

It introduces a deep reinforcement learning approach to model supraspinal drive, demonstrating its role in high gap crossing success and providing insights into biological control mechanisms.

## Key findings

- Direct supraspinal contribution improves gap crossing success.
- CPG dynamics enhance gait smoothness and energy efficiency.
- Sensing front foot distance is key for obstacle avoidance.

## Abstract

Quadruped animal locomotion emerges from the interactions between the spinal central pattern generator (CPG), sensory feedback, and supraspinal drive signals from the brain. Computational models of CPGs have been widely used for investigating the spinal cord contribution to animal locomotion control in computational neuroscience and in bio-inspired robotics. However, the contribution of supraspinal drive to anticipatory behavior, i.e. motor behavior that involves planning ahead of time (e.g. of footstep placements), is not yet properly understood. In particular, it is not clear whether the brain modulates CPG activity and/or directly modulates muscle activity (hence bypassing the CPG) for accurate foot placements. In this paper, we investigate the interaction of supraspinal drive and a CPG in an anticipatory locomotion scenario that involves stepping over gaps. By employing deep reinforcement learning (DRL), we train a neural network policy that replicates the supraspinal drive behavior. This policy can either modulate the CPG dynamics, or directly change actuation signals to bypass the CPG dynamics. Our results indicate that the direct supraspinal contribution to the actuation signal is a key component for a high gap crossing success rate. However, the CPG dynamics in the spinal cord are beneficial for gait smoothness and energy efficiency. Moreover, our investigation shows that sensing the front feet distances to the gap is the most important and sufficient sensory information for learning gap crossing. Our results support the biological hypothesis that cats and horses mainly control the front legs for obstacle avoidance, and that hind limbs follow an internal memory based on the front limbs' information. Our method enables the quadruped robot to cross gaps of up to 20 cm (50% of body-length) without any explicit dynamics modeling or Model Predictive Control (MPC).