🤖 AI Summary
This work addresses the challenge of achieving cost-effective omnidirectional mobility in mobile robots, a capability traditionally difficult to attain with conventional actively driven wheeled systems. The authors propose a novel quadrupedal robot that leverages passive universal wheels—standard caster wheels—to enable efficient omnidirectional locomotion. By introducing an asymmetric Actor-Critic reinforcement learning framework, the system integrates privileged information regarding caster wheel orientation and velocity, combined with base-pose regulation and a multimodal propulsion strategy. This approach significantly reduces hardware complexity and cost while markedly improving energy efficiency. Experimental results demonstrate that the robot exhibits exceptional omnidirectional agility and achieves an 89.1% reduction in cost of transport (COT) compared to purely legged locomotion.
📝 Abstract
Wheeled-legged robots possess both agile mobility for traversing complex terrains and high efficiency, making them suitable for long-distance transportation applications. Conventional actuated wheeled robots require specialized hardware and electrical design due to the incorporation of wheel components. We propose a novel and low-cost passive wheeled legged robot equipped with standard casters on each leg to obtain omnidirectional mobility. The control method employs an asymmetric actor-critic structure, enabling the utilization of the privileged information of the passive caster's angles and velocities. We develop a caster base posture adjustment strategy based on velocity commands, utilizing actuated joints to modify the caster base joint axis posture and thereby adjust the propulsion direction of the casters. Moreover, we implemented multiple propulsion modes to achieve varying degrees of caster twisting oscillation, converting these into propulsive force. We conducted a slalom test and mode switch experience, which shows the passive wheeled quadruped could achieve omnidirectional movement versatility, and reduce the cost of transport (COT) by up to 89.1% with respect to legged motion.