# Whole-Body Control Through Narrow Gaps From Pixels To Action

arXiv: https://arxiv.org/abs/2409.00895 · HTML: https://mlsanity.com/paper/2409.00895/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Sep 2024.

## Built on by (most cited first, 14 of 14)

- [VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments](https://mlsanity.com/paper/2512.15258/) (2025)
- [NavDreamer: Video Models as Zero-Shot 3D Navigators](https://mlsanity.com/paper/2602.09765/) (2026)
- [Flying on Point Clouds with Reinforcement Learning](https://mlsanity.com/paper/2503.00496/) (2025)
- [GRaD-Nav: Efficiently Learning Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamics](https://mlsanity.com/paper/2503.03984/) (2025)
- [Reactive Aerobatic Flight via Reinforcement Learning](https://mlsanity.com/paper/2505.24396/) (2025)
- [Learning Human-Like Badminton Skills for Humanoid Robots](https://mlsanity.com/paper/2602.08370/) (2026)
- [FLOAT Drone: A Fully-actuated Coaxial Aerial Robot for Close-Proximity Operations](https://mlsanity.com/paper/2503.00785/) (2025)
- [Towards Task-Oriented Flying: Framework, Infrastructure, and Principles](https://mlsanity.com/paper/2504.15129/) (2025)
- [Learning Agile Gate Traversal via Analytical Optimal Policy Gradient](https://mlsanity.com/paper/2508.21592/) (2025)
- [High-Speed Vision-Based Flight in Clutter with Safety-Shielded Reinforcement Learning](https://mlsanity.com/paper/2602.08653/) (2026)
- [ASTER: Attitude-aware Suspended-payload Quadrotor Traversal via Efficient Reinforcement Learning](https://mlsanity.com/paper/2603.10715/) (2026)
- [PerchRL: Vision-Based Agile Perching on Inclined Platforms under Rapid and Irregular Motion](https://mlsanity.com/paper/2606.03441/) (2026)
- [Agile Fall Recovery for Quadrotors with Bidirectional Thrust via Reinforcement Learning](https://mlsanity.com/paper/2606.16513/) (2026)
- [Learning Vision-Based Agile Gap Traversal: Differentiable Simulation with a Warm-Started Critic](https://mlsanity.com/paper/2609.30696/) (2026)

## Abstract (arXiv)

Flying through body-size narrow gaps in the environment is one of the most challenging moments for an underactuated multirotor. We explore a purely data-driven method to master this flight skill in simulation, where a neural network directly maps pixels and proprioception to continuous low-level control commands. This learned policy enables whole-body control through gaps with different geometries demanding sharp attitude changes (e.g., near-vertical roll angle). The policy is achieved by successive model-free reinforcement learning (RL) and online observation space distillation. The RL policy receives (virtual) point clouds of the gaps' edges for scalable simulation and is then distilled into the high-dimensional pixel space. However, this flight skill is fundamentally expensive to learn by exploring due to restricted feasible solution space. We propose to reset the agent as states on the trajectories by a model-based trajectory optimizer to alleviate this problem. The presented training pipeline is compared with baseline methods, and ablation studies are conducted to identify the key ingredients of our method. The immediate next step is to scale up the variation of gap sizes and geometries in anticipation of emergent policies and demonstrate the sim-to-real transformation.