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

arXiv: https://arxiv.org/abs/2603.26687 · HTML: https://mlsanity.com/paper/2603.26687/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 13 Mar 2026.

## Builds on (most cited first, 17 of 17)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics](https://mlsanity.com/paper/2005.04269/) (2020)
- [Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning](https://mlsanity.com/paper/2105.08328/) (2021)
- [Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robots](https://mlsanity.com/paper/2111.01674/) (2021)
- [Fast and Efficient Locomotion via Learned Gait Transitions](https://mlsanity.com/paper/2104.04644/) (2021)
- [Ascento: A Two-Wheeled Jumping Robot](https://mlsanity.com/paper/2005.11435/) (2020)
- [Reinforcement Learning for Blind Stair Climbing with Legged and Wheeled-Legged Robots](https://mlsanity.com/paper/2402.06143/) (2024)
- [Learning to Walk and Fly with Adversarial Motion Priors](https://mlsanity.com/paper/2309.12784/) (2023)
- [Autonomous Hybrid Ground/Aerial Mobility in Unknown Environments](https://mlsanity.com/paper/2009.05631/) (2020)
- [DoubleBee: A Hybrid Aerial-Ground Robot with Two Active Wheels](https://mlsanity.com/paper/2303.05075/) (2023)
- [Hybrid aerial ground locomotion with a single passive wheel](https://mlsanity.com/paper/2003.09242/) (2020)
- [BogieCopter: A Multi-Modal Aerial-Ground Vehicle for Long-Endurance Inspection Applications](https://mlsanity.com/paper/2303.01933/) (2023)
- [Quadrotor Morpho-Transition: Learning vs Model-Based Control Strategies](https://mlsanity.com/paper/2506.14039/) (2025)

## Abstract (arXiv)

Hybrid aerial--ground robots can use thrust to cross obstacles that impede wheel-driven motion, but deciding how much thrust to apply during contact remains challenging. We present an energy-aware reinforcement learning framework that jointly commands wheels, tilt servos and propellers through a single continuous policy, without prescribing locomotion modes. Hardware-calibrated power models penalise estimated electrical energy, while a terrain curriculum and a terminal reward for upright, settled arrivals support learning of thrust-assisted climbing. In simulation, continuous thrust allocation improves single-step clearance over fixed-thrust and mode-switching baselines as steps become taller. At the wheel-radius step height, it draws approximately 27 percent less mean power than the best fixed allocation. An energy-weight ablation shows the accompanying trade-off between efficiency and reliability. On a physical DoubleBee prototype, the unchanged network with a deployment interface clears two 6 centimetre steps in 8 of 10 trials. Additional hardware tests show both the potential for transfer to different terrain geometries and the remaining limitations in heading control, contact robustness and recovery.