mlsanityData to 14 Oct 2026

ClearNav: Perception-Aligned Quadrotor Flight Using Differential-Physics

arXiv 2610.17419 ↗First posted 12 Oct 2026cs.RO cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Autonomous quadrotor flight in cluttered environment is an key capability for tasks like inspection and search. Navigation policies trained in simulation and transferred to hardware can fly at high speed in open space, but they can still collide as obstacle clearance shrinks. We attribute most of these collisions to a single mechanism, namely motion in directions the onboard camera does not observe. Heading that is not aligned with the direction of travel and lateral excursion during obstacle avoidance both carry the vehicle toward obstacles outside its field of view. We introduce ClearNav, a navigation policy trained with two reward terms that constrain motion to the observed direction, a forward-looking heading target and a penalty on lateral velocity. A third term penalizes speed near obstacles so that an obstacle entering the field of view remains avoidable. In simulation, across 18 held-out scenarios with 2304 paired flights per policy unseen in training, ClearNav improves success by 6.8 points, cuts the collision rate by 65% relative to the state of the arts, and flies at maximum 5m/s. For the proximity term alone under matched commanded speeds, the collision reduction still holds at 70%. The effect is significant on static scenes and consistent in direction on moving obstacles, though not significant there at the suite level, showing that safer flight in clutter is possible even on the limited sensors and compute of small drones. We also validate our navigation policy in a real-world cluttered environment, showing that it enables the quadrotor to navigate through the cluttered environment successfully and safely.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 12 Oct 2026.

Builds on

29 of 39 references.

References · 29

  1. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  2. 2021Learning High-Speed Flight in the Wildcited by 128
  3. 2024Back to Newton's Laws: Learning Vision-based Agile Flight via Differentiable Physicscited by 45
  4. 2019Robust and Efficient Quadrotor Trajectory Generation for Fast Autonomous Flightcited by 41
  5. 2024Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flightcited by 31
  6. 2024Demonstrating Agile Flight from Pixels without State Estimationcited by 31
  7. 2024A Review of Differentiable Simulatorscited by 28
  8. 2020Fast Frontier-based Information-driven Autonomous Exploration with an MAVcited by 24
  9. 2020RAPTOR: Robust and Perception-aware Trajectory Replanning for Quadrotor Fast Flightcited by 23
  10. 2024Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulationcited by 20
  11. 2024Learning Quadrotor Control From Visual Features Using Differentiable Simulationcited by 19
  12. 2024SOUS VIDE: Cooking Visual Drone Navigation Policies in a Gaussian Splatting Vacuumcited by 16
17 more
  1. 2017Search-based Motion Planning for Aggressive Flight in SE(3)cited by 15
  2. 2025Dream to Fly: Model-Based Reinforcement Learning for Vision-Based Drone Flightcited by 15
  3. 2024Residual Policy Learning for Perceptive Quadruped Control Using Differentiable Simulationcited by 13
  4. 2017Search-based Motion Planning for Quadrotors using Linear Quadratic Minimum Time Controlcited by 11
  5. 2023Deep Learning for Optimization of Trajectories for Quadrotorscited by 9
  6. 2025SkyDreamer: Interpretable End-to-End Vision-Based Drone Racing with Model-Based Reinforcement Learningcited by 8
  7. 2025GRaD-Nav: Efficiently Learning Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamicscited by 7
  8. 2025Quadrotor Navigation using Reinforcement Learning with Privileged Informationcited by 6
  9. 2025Reactive Aerobatic Flight via Reinforcement Learningcited by 5
  10. 2026Reinforcement Learning for Active Perception in Autonomous Navigationcited by 4
  11. 2025DiffAero: A GPU-Accelerated Differentiable Simulation Framework for Efficient Quadrotor Policy Learningcited by 3
  12. 2026Vector Field Augmented Differentiable Policy Learning for Vision-Based Drone Racingcited by 2
  13. 2026Simple but Stable, Fast and Safe: Achieve End-to-end Control by High-Fidelity Differentiable Simulationcited by 2
  14. 2025A Self-Supervised Learning Approach with Differentiable Optimization for UAV Trajectory Planningcited by 1
  15. 2025Dreaming Falcon: Physics-Informed Model-Based Reinforcement Learning for Quadcopterscited by 1
  16. 2026High-Speed Vision-Based Flight in Clutter with Safety-Shielded Reinforcement Learningcited by 1
  17. 2026Learn for Variation: Efficient AAV Trajectory Learning through a Differentiable Wireless World Modelcited by 1

Built on by

Not cited yet.