Learning Energy-Efficient Air--Ground Actuation for Hybrid Robots on Stair-Like Terrain

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Jiaxing, Tian, Wen, Xu, Xinhang, Yuan, Junbin, Scherer, Sebastian, Cao, Muqing
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911548694331392
author Li, Jiaxing
Tian, Wen
Xu, Xinhang
Yuan, Junbin
Scherer, Sebastian
Cao, Muqing
author_facet Li, Jiaxing
Tian, Wen
Xu, Xinhang
Yuan, Junbin
Scherer, Sebastian
Cao, Muqing
contents Hybrid aerial--ground robots offer both traversability and endurance, but stair-like discontinuities create a trade-off: wheels alone often stall at edges, while flight is energy-hungry for small height gains. We propose an energy-aware reinforcement learning framework that trains a single continuous policy to coordinate propellers, wheels, and tilt servos without predefined aerial and ground modes. We train policies from proprioception and a local height scan in Isaac Lab with parallel environments, using hardware-calibrated thrust/power models so the reward penalizes true electrical energy. The learned policy discovers thrust-assisted driving that blends aerial thrust and ground traction. In simulation it achieves about 4 times lower energy than propeller-only control. We transfer the policy to a DoubleBee prototype on an 8cm gap-climbing task; it achieves 38% lower average power than a rule-based decoupled controller. These results show that efficient hybrid actuation can emerge from learning and deploy on hardware.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26687
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning Energy-Efficient Air--Ground Actuation for Hybrid Robots on Stair-Like Terrain
Li, Jiaxing
Tian, Wen
Xu, Xinhang
Yuan, Junbin
Scherer, Sebastian
Cao, Muqing
Robotics
Artificial Intelligence
Hybrid aerial--ground robots offer both traversability and endurance, but stair-like discontinuities create a trade-off: wheels alone often stall at edges, while flight is energy-hungry for small height gains. We propose an energy-aware reinforcement learning framework that trains a single continuous policy to coordinate propellers, wheels, and tilt servos without predefined aerial and ground modes. We train policies from proprioception and a local height scan in Isaac Lab with parallel environments, using hardware-calibrated thrust/power models so the reward penalizes true electrical energy. The learned policy discovers thrust-assisted driving that blends aerial thrust and ground traction. In simulation it achieves about 4 times lower energy than propeller-only control. We transfer the policy to a DoubleBee prototype on an 8cm gap-climbing task; it achieves 38% lower average power than a rule-based decoupled controller. These results show that efficient hybrid actuation can emerge from learning and deploy on hardware.
title Learning Energy-Efficient Air--Ground Actuation for Hybrid Robots on Stair-Like Terrain
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2603.26687