ClearNav: Perception-Aligned Quadrotor Flight Using Differential-Physics
ClearNav: Perception-Aligned Quadrotor Flight Using Differential-Physics
This paper introduces ClearNav, a navigation policy for autonomous quadrotors that reduces collisions in cluttered environments by aligning motion with the visual field of the onboard camera. The policy uses reward terms to constrain movement to observed directions and penalizes lateral velocity and proximity to obstacles. It achieves a 6.8 point improvement in success rate and a 65% reduction in collisions in simulation, with similar performance in real-world tests.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S4
- Control
- Reported autonomousOpen source S2
Reported numbers
success
6.8
maximum speed
5
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
d 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%
Open source S4
arXiv:2610.17419v1 Announce Type: new Abstract: 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 on
Open source S2
Source：arXiv Robotics — research abstracts · arxiv.org