Learning Omnidirectional Locomotion for a Salamander-Like Quadruped Robot

2025-11-11

AI Summary

Existing salamander-inspired quadrupedal robot controllers rely on predefined gaits or joint trajectories, limiting exploitation of morphological potential and resulting in insufficient locomotor flexibility and behavioral diversity. To address this, we propose a distributed phase-based control framework grounded in deep reinforcement learning: a phase variable is introduced to uniformly model limb coordination; a phase-coverage reward is designed to encourage exploratory gait discovery; and morphological symmetry-aware data augmentation is integrated to improve sample efficiency. The approach eliminates dependence on reference motions, enabling prior-free, omnidirectional autonomous gait learning. Experimental results demonstrate successful acquisition of 22 dynamically symmetric gaits—including forward, backward, lateral, and turning patterns—significantly enhancing locomotor adaptability and behavioral repertoire generation for complex morphological robots.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Salamander-like quadruped robots are designed inspired by the skeletal structure of their biological counterparts. However, existing controllers cannot fully exploit these morphological features and largely rely on predefined gait patterns or joint trajectories, which prevents the generation of diverse and flexible locomotion and limits their applicability in real-world scenarios. In this paper, we propose a learning framework that enables the robot to acquire a diverse repertoire of omnidirectional gaits without reference motions. Each body part is controlled by a phase variable capable of forward and backward evolution, with a phase coverage reward to promote the exploration of the leg phase space. Additionally, morphological symmetry of the robot is incorporated via data augmentation, improving sample efficiency and enforcing both motion-level and task-level symmetry in learned behaviors. Extensive experiments show that the robot successfully acquires 22 omnidirectional gaits exhibiting both dynamic and symmetric movements, demonstrating the effectiveness of the proposed learning framework.

Problem

• Developing flexible locomotion without predefined gait patterns for salamander-like robots
• Enabling omnidirectional movement through learned phase-controlled body coordination
• Incorporating morphological symmetry to improve motion diversity and learning efficiency

Innovation

• Learning framework without reference motions
• Phase variable control with coverage reward
• Morphological symmetry via data augmentation