# Multi-Task Reinforcement Learning of Drone Aerobatics by Exploiting Geometric Symmetries

arXiv: https://arxiv.org/abs/2602.10997 · HTML: https://mlsanity.com/paper/2602.10997/

## 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 21 of its 27 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

## Builds on (most cited first, 21 of 21)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation](https://mlsanity.com/paper/2112.05124/) (2021)
- [Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning](https://mlsanity.com/paper/2310.10943/) (2023)
- [SO(2)-Equivariant Reinforcement Learning](https://mlsanity.com/paper/2203.04439/) (2022)
- [Deep Drone Acrobatics](https://mlsanity.com/paper/2006.05768/) (2020)
- [EDGI: Equivariant Diffusion for Planning with Embodied Agents](https://mlsanity.com/paper/2303.12410/) (2023)
- [Leveraging Symmetry in RL-based Legged Locomotion Control](https://mlsanity.com/paper/2403.17320/) (2024)
- [A Comparative Study of Nonlinear MPC and Differential-Flatness-Based Control for Quadrotor Agile Flight](https://mlsanity.com/paper/2109.01365/) (2021)
- [Improving Equivariant Model Training via Constraint Relaxation](https://mlsanity.com/paper/2408.13242/) (2024)
- [Multi-Task Reinforcement Learning for Quadrotors](https://mlsanity.com/paper/2412.12442/) (2024)
- [Leveraging Symmetries in Pick and Place](https://mlsanity.com/paper/2308.07948/) (2023)
- [Morphological Symmetries in Robotics](https://mlsanity.com/paper/2402.15552/) (2024)
- [EquAct: An SE(3)-Equivariant Multi-Task Transformer for Open-Loop Robotic Manipulation](https://mlsanity.com/paper/2505.21351/) (2025)
- [SO(2)-Equivariant Downwash Models for Close Proximity Flight](https://mlsanity.com/paper/2305.18983/) (2023)
- [Equivariant Reinforcement Learning for Quadrotor UAV](https://mlsanity.com/paper/2206.01233/) (2022)
- [A Practical Guide for Incorporating Symmetry in Diffusion Policy](https://mlsanity.com/paper/2505.13431/) (2025)
- [Reactive Aerobatic Flight via Reinforcement Learning](https://mlsanity.com/paper/2505.24396/) (2025)
- [User-Conditioned Neural Control Policies for Mobile Robotics](https://mlsanity.com/paper/2211.12181/) (2022)
- [TACO: General Acrobatic Flight Control via Target-and-Command-Oriented Reinforcement Learning](https://mlsanity.com/paper/2503.01125/) (2025)
- [Equivariant Reinforcement Learning Frameworks for Quadrotor Low-Level Control](https://mlsanity.com/paper/2502.20500/) (2025)

## Abstract (arXiv)

Flight control for autonomous micro aerial vehicles (MAVs) is evolving from steady flight near equilibrium points toward more aggressive aerobatic maneuvers, such as flips, rolls, and Power Loop. Although reinforcement learning (RL) has shown great potential in these tasks, conventional RL methods often suffer from low data efficiency and limited generalization. This challenge becomes more pronounced in multi-task scenarios where a single policy is required to master multiple maneuvers. In this paper, we propose a novel end-to-end multi-task reinforcement learning framework, called GEAR (Geometric Equivariant Aerobatics Reinforcement), which fully exploits the inherent SO(2) rotational symmetry in MAV dynamics and explicitly incorporates this property into the policy network architecture. By integrating an equivariant actor network, FiLM-based task modulation, and a multi-head critic, GEAR achieves both efficiency and flexibility in learning diverse aerobatic maneuvers, enabling a data-efficient, robust, and unified framework for aerobatic control. GEAR attains a 98.85% success rate across various aerobatic tasks, significantly outperforming baseline methods. In real-world experiments, GEAR demonstrates stable execution of multiple maneuvers and the capability to combine basic motion primitives to complete complex aerobatics.