# Aggressive Quadrotor Flight Using Curiosity-Driven Reinforcement Learning

arXiv: https://arxiv.org/abs/2203.14033 · HTML: https://mlsanity.com/paper/2203.14033/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Mar 2022.

## Built on by (most cited first, 8 of 8)

- [What Matters in Learning A Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Study](https://mlsanity.com/paper/2412.11764/) (2024)
- [The Power of Input: Benchmarking Zero-Shot Sim-To-Real Transfer of Reinforcement Learning Control Policies for Quadrotor Control](https://mlsanity.com/paper/2410.07686/) (2024)
- [VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play](https://mlsanity.com/paper/2502.01932/) (2025)
- [FM-Planner: Foundation Model Guided Path Planning for Autonomous Drone Navigation](https://mlsanity.com/paper/2505.20783/) (2025)
- [Towards Task-Oriented Flying: Framework, Infrastructure, and Principles](https://mlsanity.com/paper/2504.15129/) (2025)
- [JuggleRL: Mastering Ball Juggling with a Quadrotor via Deep Reinforcement Learning](https://mlsanity.com/paper/2509.24892/) (2025)
- [Curiosity-Driven Reinforcement Learning based Low-Level Flight Control](https://mlsanity.com/paper/2307.15724/) (2023)
- [Sim-to-Real Transfer in Reinforcement Learning for Maneuver Control of a Variable-Pitch MAV](https://mlsanity.com/paper/2504.07694/) (2025)

## Abstract (arXiv)

The ability to perform aggressive movements, which are called aggressive flights, is important for quadrotors during navigation. However, aggressive quadrotor flights are still a great challenge to practical applications. The existing solutions to aggressive flights heavily rely on a predefined trajectory, which is a time-consuming preprocessing step. To avoid such path planning, we propose a curiosity-driven reinforcement learning method for aggressive flight missions and a similarity-based curiosity module is introduced to speed up the training procedure. A branch structure exploration (BSE) strategy is also applied to guarantee the robustness of the policy and to ensure the policy trained in simulations can be performed in real-world experiments directly. The experimental results in simulations demonstrate that our reinforcement learning algorithm performs well in aggressive flight tasks, speeds up the convergence process and improves the robustness of the policy. Besides, our algorithm shows a satisfactory simulated to real transferability and performs well in real-world experiments.