Learning Perceptive Platform Adaptive Locomotion Controllers for Quadrupedal Robots

2026-06-23

AI Summary

Current quadrupedal robot control strategies suffer from poor generalization, and the manner of perception integration significantly affects terrain adaptability and robustness. This work proposes the MorAL+ method, which incorporates sensory information exclusively into the critic network within a morphology-aware reinforcement learning framework and trains the policy using an adaptive terrain curriculum. Compared to both blind policies and fully perceptual actor-critic architectures (PPAL), MorAL+ demonstrates superior terrain adaptation, trajectory tracking consistency, and robustness to perceptual noise in both simulation and real-world experiments on the ANYmal platform. These results validate the efficacy and advantages of integrating perception solely on the critic side.

Abstract

Universal quadrupedal locomotion remains limited by the difficulty of integrating perception across diverse robot morphologies. State-of-the-art controllers rely on single-robot training or blind policies that omit real-time perception, leading to poor cross-embodiment generalization. Designing locomotion policies that remain robust across related quadruped morphologies while incorporating perception is challenging. Moreover, fully perceptive policies are often sensitive to noise, whereas blind controllers lack terrain awareness. In this work, we study how perception should be integrated into morphology-aware reinforcement learning architectures for deployable quadrupedal control. Building on MorAL, we train morphology-specialized universal controllers on multiple reference quadrupeds using adaptive terrain curricula. We compare a blind baseline, a critic-perceptive variant (MorAL+), and a fully perceptive actor-critic (PPAL). Policies are evaluated in simulation on flat and rough terrains, and deployed on ANYmal hardware. Results show that critic-only perception improves robustness and tracking consistency over blind baselines while remaining more stable than fully perceptive policies under perception noise. These findings highlight that perception placement and curriculum design are key factors for scalable, morphology-aware locomotion.

Problem

• quadrupedal locomotion
• perception integration
• morphology-aware control
• cross-embodiment generalization
• terrain adaptation

Innovation

• perception integration
• morphology-aware control
• quadrupedal locomotion
• reinforcement learning
• adaptive curriculum