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

• URL: http://arxiv.org/abs/2603.26687v1
• Date: Fri, 13 Mar 2026 14:55:01 GMT
• Title: Learning Energy-Efficient Air--Ground Actuation for Hybrid Robots on Stair-Like Terrain
• Abstract summary: Hybrid aerial-ground robots offer both traversability and endurance, but stair-like discontinuities create a trade-off.<n>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.
• Score: 14.868564001069986
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Dynamics-Informed Reinforcement Learning for Agile and Energy-Efficient Locomotion of a Monopedal Hopping Quadcopter [6.592942321170304]
  Reinforcement Learning is promising but prone to energy-inefficient "reward hacking"<n>We propose a Dynamics-Informed RL framework for a monopedal hopping quadcopter.
  arXiv  Detail & Related papers  (2026-09-14T11:32:27Z)
• Reinforcement Learning-Based Control for an Inline Skating Humanoid Robot [10.006591553493807]
  We train and deploy a reinforcement learning control policy that enables novel locomotion strategies for a humanoid robot modified to equip consumer inline skates instead of conventional feet.<n>Our skating strategies emerge entirely from our reward structure, without reliance on human motion data, imitation learning, or kinematic priors.<n>Our policy demonstrates up to a 50% reduction in Cost of Transport compared to standard walking gaits.
  arXiv  Detail & Related papers  (2026-06-30T15:25:06Z)
• Underactuated multimodal jumping robot for extraterrestrial exploration [0.3867363075280543]
  We present a rolling and jumping underactuated monopedal robot designed to explore multimodal locomotion on low-gravity bodies.<n>It uses only two reaction wheels to control its spatial orientation with two controllers: a balancing controller which can aim the robot's jump direction on the ground, and an aerial reorientation controller which can aim the robot's leg for landing after flight.
  arXiv  Detail & Related papers  (2026-03-06T18:08:32Z)
• How to Model Your Crazyflie Brushless [50.54424040768484]
  In early 2025, the Crazyflie Brushless was introduced, featuring brushless motors that provide around 50% more thrust.<n>This work presents a dynamics model of the Crazyflie Brushless and identifies its key parameters.<n>We demonstrate its suitability for reinforcement learning applications by training an end-to-end neural network position controller and learning a backflip controller.
  arXiv  Detail & Related papers  (2026-03-06T06:21:39Z)
• Tilt-Ropter: A Novel Hybrid Aerial and Terrestrial Vehicle with Tilt Rotors and Passive Wheels [13.687917750845303]
  We present Tilt-Ropter, a novel hybrid aerial-terrestrial vehicle (HATV)<n>The fully actuated design of Tilt-Ropter enables decoupled force and torque control.<n>Results show a 92.8% reduction in power consumption during ground locomotion.
  arXiv  Detail & Related papers  (2026-02-02T06:15:33Z)
• Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction [86.53248703859718]
  We introduce a perceptive locomotion framework that merges terrain sensing, gait regulation, and whole-body control into a single reinforcement learning policy.<n>Experiments conducted on a 31-DoF, 1.65 m humanoid robot demonstrate robust locomotion in both simulation and real-world settings.
  arXiv  Detail & Related papers  (2025-12-08T11:42:41Z)
• Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control [106.32794844077534]
  This paper presents a study on using deep reinforcement learning to create dynamic locomotion controllers for bipedal robots. We develop a general control solution that can be used for a range of dynamic bipedal skills, from periodic walking and running to aperiodic jumping and standing. This work pushes the limits of agility for bipedal robots through extensive real-world experiments.
  arXiv  Detail & Related papers  (2024-01-30T10:48:43Z)
• Barkour: Benchmarking Animal-level Agility with Quadruped Robots [70.97471756305463]
  We introduce the Barkour benchmark, an obstacle course to quantify agility for legged robots. Inspired by dog agility competitions, it consists of diverse obstacles and a time based scoring mechanism. We present two methods for tackling the benchmark.
  arXiv  Detail & Related papers  (2023-05-24T02:49:43Z)
• Continuous Versatile Jumping Using Learned Action Residuals [35.996425893483796]
  We propose a hierarchical framework that combines optimal control and reinforcement learning to learn continuous jumping motions for quadrupedal robots. The core of our framework is a stance controller, which combines a manually designed acceleration controller with a learned residual policy. After training in simulation, our framework can be deployed directly to the real robot, and perform versatile, continuous jumping motions.
  arXiv  Detail & Related papers  (2023-04-17T23:28:32Z)
• Robust and Versatile Bipedal Jumping Control through Reinforcement Learning [141.56016556936865]
  This work aims to push the limits of agility for bipedal robots by enabling a torque-controlled bipedal robot to perform robust and versatile dynamic jumps in the real world. We present a reinforcement learning framework for training a robot to accomplish a large variety of jumping tasks, such as jumping to different locations and directions. We develop a new policy structure that encodes the robot's long-term input/output (I/O) history while also providing direct access to a short-term I/O history.
  arXiv  Detail & Related papers  (2023-02-19T01:06:09Z)
• Learning a Single Near-hover Position Controller for Vastly Different Quadcopters [56.37274861303324]
  This paper proposes an adaptive near-hover position controller for quadcopters. It can be deployed to quadcopters of very different mass, size and motor constants. It also shows rapid adaptation to unknown disturbances during runtime.
  arXiv  Detail & Related papers  (2022-09-19T17:55:05Z)
• Fast and Efficient Locomotion via Learned Gait Transitions [35.86279693549959]
  We focus on the problem of developing efficient controllers for quadrupedal robots. We devise a hierarchical learning framework, in which distinctive locomotion gaits and natural gait transitions emerge automatically. We show that the learned hierarchical controller consumes much less energy across a wide range of locomotion speed than baseline controllers.
  arXiv  Detail & Related papers  (2021-04-09T23:53:28Z)
• Robust Quadruped Jumping via Deep Reinforcement Learning [10.095966161524043]
  In this paper, we consider jumping varying distances and heights for a quadrupedal robot in noisy environments. We propose a framework using deep reinforcement learning that leverages and augments the complex solution of nonlinear trajectory optimization for quadrupedal jumping. We demonstrate robustness of foot disturbances of up to 6 cm in height, or 33% of the robot's nominal standing height, while jumping 2x the body length in distance.
  arXiv  Detail & Related papers  (2020-11-13T19:04:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.