ATRos: Learning Energy-Efficient Agile Locomotion for Wheeled-legged Robots

2025-10-10

AI Summary

To address the low energy efficiency and poor terrain adaptability of wheeled-legged robots under hybrid locomotion modes, this paper proposes an end-to-end deep reinforcement learning framework that autonomously coordinates wheel rolling and legged stepping without predefined gait templates. The method adopts an Actor-Critic architecture, integrating proprioceptive sensing to estimate environmental states in real time and directly generate joint-level control commands, enabling online, adaptive switching between locomotion modalities. Extensive experiments in simulation and on a physical robot demonstrate strong robustness and cross-terrain generalization across flat ground, stairs, and grassy surfaces, significantly improving both agility and energy efficiency. The key innovation lies in the first integration of environment state prediction into the policy network, achieving unified perception-decision-control for adaptive hybrid locomotion.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• 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
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Hybrid locomotion of wheeled-legged robots has recently attracted increasing attention due to their advantages of combining the agility of legged locomotion and the efficiency of wheeled motion. But along with expanded performance, the whole-body control of wheeled-legged robots remains challenging for hybrid locomotion. In this paper, we present ATRos, a reinforcement learning (RL)-based hybrid locomotion framework to achieve hybrid walking-driving motions on the wheeled-legged robot. Without giving predefined gait patterns, our planner aims to intelligently coordinate simultaneous wheel and leg movements, thereby achieving improved terrain adaptability and improved energy efficiency. Based on RL techniques, our approach constructs a prediction policy network that could estimate external environmental states from proprioceptive sensory information, and the outputs are then fed into an actor critic network to produce optimal joint commands. The feasibility of the proposed framework is validated through both simulations and real-world experiments across diverse terrains, including flat ground, stairs, and grassy surfaces. The hybrid locomotion framework shows robust performance over various unseen terrains, highlighting its generalization capability.

Problem

• Develops energy-efficient hybrid locomotion for wheeled-legged robots
• Coordinates simultaneous wheel and leg movements without predefined gaits
• Improves terrain adaptability across diverse environments like stairs

Innovation

• Reinforcement learning enables hybrid walking-driving locomotion
• Policy network estimates environment states from proprioceptive sensors
• Actor critic network generates optimal joint movement commands