analiza aiqbench
This paper applies reinforcement learning to make a passive-wheel quadruped navigate more efficiently. Its main contributions are a time-budgeted goal-reaching objective and an adaptive push-glide cycle that the policy learns jointly with steering. Simulation results show higher success rates and lower cost of transport than the evaluated planner-controller baselines, and the paper reports zero-shot sim-to-real transfer on a physical robot. Readers should weigh the simulation gains against the hardware evidence, which covers a limited set of indoor, slope, and outdoor terrains.
SkateNav: Learning Energy-Efficient Navigation through Adaptive Skating on Passive-Wheel Quadrupedal Robots
arXiv:2610.25962v1 Announce Type: new Abstract: Passive-wheel quadrupedal robots offer energy-efficient locomotion through leg-driven propulsion and momentum-driven gliding. However, navigation requires coordinating steering with intermittent propulsion and adapting push-glide timing to task demands. Velocity-tracking objectives may suppress the speed variations inherent in skating, discouraging efficient gliding. To address these challenges, we propose SkateNav, a unified skating-navigation framework based on reinforcement learning. A time-budgeted goal-reaching objective allows the policy to jointly learn steering, propulsion, and their temporal allocation. An adaptive skating cycle structures gliding, pushing, and recovery, while frequency modulation at every control step adjusts phase durations to navigation demands. Simulation experiments demonstrate higher average success rates and lower cost of transport than the evaluated planner-controller baselines, with ablations confirming the contributions of cycle structure and frequency adaptation. Real-world experiments demonstrate zero-shot transfer from simulation to a passive-wheel Mini Cheetah across cluttered indoor spaces, slopes, and paved outdoor surfaces. Supplementary videos are available on the project page: https://ktw1404.github.io/SkateNav/
Abstract:Passive-wheel quadrupedal robots offer energy-efficient locomotion through leg-driven propulsion and momentum-driven gliding. However, navigation requires coordinating steering with intermittent propulsion and adapting push-glide timing to task demands. Velocity-tracking objectives may suppress the speed variations inherent in skating, discouraging efficient gliding. To address these challenges, we propose SkateNav, a unified skating-navigation framework based on reinforcement learning. A time-budgeted goal-reaching objective allows the policy to jointly learn steering, propulsion, and their temporal allocation. An adaptive skating cycle structures gliding, pushing, and recovery, while frequency modulation at every control step adjusts phase durations to navigation demands. Simulation experiments demonstrate higher average success rates and lower cost of transport than the evaluated planner-controller baselines, with ablations confirming the contributions of cycle structure and frequency adaptation. Real-world experiments demonstrate zero-shot transfer from simulation to a passive-wheel Mini Cheetah across cluttered indoor spaces, slopes, and paved outdoor surfaces. Supplementary videos are available on the project page: this https URL
8 pages, 12 figures, 3 tables. Project page: this https URL
Robotics (cs.RO)
arXiv:2610.25962 [cs.RO]
(or arXiv:2610.25962v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.25962 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 255 cuvinte