mlsanityData to 14 Oct 2026

Battery-Aware Reinforcement Learning for Aggressive Quadrotor Flight

arXiv 2609.37316 ↗First posted 29 Sep 2026cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

Abstract (arXiv)

Agile flight tasks such as drone racing and pursuit-evasion require strong acceleration and precise turns, but the available thrust changes as the battery discharges and voltage drops under load. Conservative command limits make this variation easier to tolerate, at the cost of unused performance. We investigate how learned controllers can use that additional thrust while retaining the flight controller's voltage compensation and rate control. Our training simulator couples an identified load-transient battery model to rotor dynamics and firmware saturation. The feedforward policy receives filtered voltage during both training and deployment. Controlled ablations distinguish the benefit of a larger thrust-command range from that of voltage information. On a 38 g Crazyflie Brushless, the resulting policy reduces circle tracking error by 49% relative to stock-authority RL at 3.84 m/s, while preserving easy-task precision. Mean 20-lap race time decreases from 106.22 s to 95.24 s. Compared with a voltage-blind policy with the same increased authority, hardware error and race time are lower by 15.3% and 4.5%, respectively. In simulation, replacing the policy's voltage input with a recording from a different battery condition worsens hard-circle tracking, with a smaller, voltage-dependent effect in racing. Together, these results show where a simple voltage input complements existing actuator compensation in aggressive learned flight.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 14 of its 24 references that are in the map. First posted on arXiv 29 Sep 2026.

Builds on

14 of 24 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025SkyDreamer: Interpretable End-to-End Vision-Based Drone Racing with Model-Based Reinforcement Learning16 Oct
  2. 2025Learned Controllers for Agile Quadrotors in Pursuit-Evasion Games3 Jun

Other references · 12

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 672
  3. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 508
  4. 2017Asymmetric Actor Critic for Image-Based Robot Learningcited by 238
  5. 2023Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learningcited by 111
  6. 2022skrl: Modular and Flexible Library for Reinforcement Learningcited by 49
  7. 2023DATT: Deep Adaptive Trajectory Tracking for Quadrotor Controlcited by 16
  8. 2021Range, Endurance, and Optimal Speed Estimates for Multicopterscited by 6
  9. 2025Agile Flight Emerges from Multi-Agent Competitive Racingcited by 4
  10. 2026How to Model Your Crazyflie Brushlesscited by 2
  11. 2025Accurate Control under Voltage Drop for Rotor Dronescited by 1
  12. 2026BC-NMPC: Battery-Constrained NMPC with Propulsion Prediction and Replanning for High-Speed Flightcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Reactive Aerobatic Flight via Reinforcement Learning
  2. 2025Leveling the Playing Field: Carefully Comparing Classical and Learned Controllers for Quadrotor Trajectory Tracking
  3. 2025RAPTOR: A Foundation Policy for Quadrotor Control
  4. 2025Dynamics-Invariant Quadrotor Control using Scale-Aware Deep Reinforcement Learning
  5. 2024Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight
  6. 2026Precise Aggressive Aerial Maneuvers with Sensorimotor Policies
  7. 2024Demonstrating Agile Flight from Pixels without State Estimation
  8. 2024A Learning-based Quadcopter Controller with Extreme Adaptation