# Mastering Diverse, Unknown, and Cluttered Tracks for Robust Vision-Based Drone Racing

arXiv: https://arxiv.org/abs/2512.09571 · HTML: https://mlsanity.com/paper/2512.09571/

## Key facts

- Cited by 3 papers in the map (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 31 of its 39 references that are in the map.
- First posted on arXiv 10 Dec 2025.

## 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, 30 of 31)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments](https://mlsanity.com/paper/2301.04195/) (2023)
- [Asymmetric Actor Critic for Image-Based Robot Learning](https://mlsanity.com/paper/1710.06542/) (2017)
- [ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots](https://mlsanity.com/paper/2306.14874/) (2023)
- [Robot Parkour Learning](https://mlsanity.com/paper/2309.05665/) (2023)
- [Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning](https://mlsanity.com/paper/2310.10943/) (2023)
- [Autonomous Drone Racing with Deep Reinforcement Learning](https://mlsanity.com/paper/2103.08624/) (2021)
- [A Benchmark Comparison of Learned Control Policies for Agile Quadrotor Flight](https://mlsanity.com/paper/2202.10796/) (2022)
- [BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds](https://mlsanity.com/paper/2502.10363/) (2025)
- [Back to Newton's Laws: Learning Vision-based Agile Flight via Differentiable Physics](https://mlsanity.com/paper/2407.10648/) (2024)
- [Autonomous Drone Racing: A Survey](https://mlsanity.com/paper/2301.01755/) (2023)
- [Differential Flatness of Quadrotor Dynamics Subject to Rotor Drag for Accurate Tracking of High-Speed Trajectories](https://mlsanity.com/paper/1712.02402/) (2017)
- [Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight](https://mlsanity.com/paper/2403.12203/) (2024)
- [AlphaPilot: Autonomous Drone Racing](https://mlsanity.com/paper/2005.12813/) (2020)
- [L2C2: Locally Lipschitz Continuous Constraint towards Stable and Smooth Reinforcement Learning](https://mlsanity.com/paper/2202.07152/) (2022)
- [NavRL: Learning Safe Flight in Dynamic Environments](https://mlsanity.com/paper/2409.15634/) (2024)
- [Time-Optimal Planning for Quadrotor Waypoint Flight](https://mlsanity.com/paper/2108.04537/) (2021)
- [Model Predictive Contouring Control for Time-Optimal Quadrotor Flight](https://mlsanity.com/paper/2108.13205/) (2021)
- [Learning Agile Locomotion on Risky Terrains](https://mlsanity.com/paper/2311.10484/) (2023)
- [AirSim Drone Racing Lab](https://mlsanity.com/paper/2003.05654/) (2020)
- [End-to-end Reinforcement Learning for Time-Optimal Quadcopter Flight](https://mlsanity.com/paper/2311.16948/) (2023)
- [Learning Minimum-Time Flight in Cluttered Environments](https://mlsanity.com/paper/2203.15052/) (2022)
- [Learning Deep Sensorimotor Policies for Vision-based Autonomous Drone Racing](https://mlsanity.com/paper/2210.14985/) (2022)
- [Time-Optimal Online Replanning for Agile Quadrotor Flight](https://mlsanity.com/paper/2203.09839/) (2022)
- [Environment as Policy: Learning to Race in Unseen Tracks](https://mlsanity.com/paper/2410.22308/) (2024)
- [Minimum-Time Quadrotor Waypoint Flight in Cluttered Environments](https://mlsanity.com/paper/2202.03947/) (2022)
- [TACO: General Acrobatic Flight Control via Target-and-Command-Oriented Reinforcement Learning](https://mlsanity.com/paper/2503.01125/) (2025)
- [Time-optimal Flight in Cluttered Environments via Safe Reinforcement Learning](https://mlsanity.com/paper/2406.19646/) (2024)
- [Learning Generalizable Policy for Obstacle-Aware Autonomous Drone Racing](https://mlsanity.com/paper/2411.04246/) (2024)

## Built on by (most cited first, 3 of 3)

- [Fuzzy Logic Theory-based Adaptive Reward Shaping for Robust Reinforcement Learning (FARS)](https://mlsanity.com/paper/2604.15772/) (2026)
- [Redesigning Regularization for Effective Policy Smoothing](https://mlsanity.com/paper/2606.13169/) (2026)
- [Bridging Performance and Generalization in Reinforcement Learning for Agile Flight](https://mlsanity.com/paper/2606.27348/) (2026)

## Abstract (arXiv)

Most reinforcement learning(RL)-based methods for drone racing target fixed, obstacle-free tracks, leaving the generalization to unknown, cluttered environments largely unaddressed. This challenge stems from the need to balance racing speed and collision avoidance, limited feasible space causing policy exploration trapped in local optima during training, and perceptual ambiguity between gates and obstacles in depth maps-especially when gate positions are only coarsely specified. To overcome these issues, we propose a two-phase learning framework: an initial soft-collision training phase that preserves policy exploration for high-speed flight, followed by a hard-collision refinement phase that enforces robust obstacle avoidance. An adaptive, noise-augmented curriculum with an asymmetric actor-critic architecture gradually shifts the policy's reliance from privileged gate-state information to depth-based visual input. We further impose Lipschitz constraints and integrate a track-primitive generator to enhance motion stability and cross-environment generalization. We evaluate our framework through extensive simulation and ablation studies, and validate it in real-world experiments on a computationally constrained quadrotor. The system achieves agile flight while remaining robust to gate-position errors, developing a generalizable drone racing framework with the capability to operate in diverse, partially unknown and cluttered environments. https://yufengsjtu.github.io/MasterRacing.github.io/