robotics
The Drone Learns the Moving Gap Without a Teacher
A differentiable pathwise objective reached 99.3 percent in simulation and 80 percent across ten real flights through a dynamic narrow opening.
Summary
A differentiable pathwise objective reached 99.3 percent in simulation and 80 percent across ten real flights through a dynamic narrow opening.
A moving narrow gap turns agile flight into a timing problem as much as a geometry problem. The proposed objective gates centering, alignment and collision terms by signed distance to the moving gap plane, providing dense pathwise gradients rather than a sparse success signal. A visual-and-inertial policy trained from scratch in one stage reached 99.3 percent success in simulation after minutes on one GPU, then crossed the physical moving gap in eight of ten trials from varied starts. The real-world sample is small, so the result demonstrates transfer rather than a production reliability rate.
Why it matters
A differentiable pathwise objective reached 99.3 percent in simulation and 80 percent across ten real flights through a dynamic narrow opening.
Limits and context
No additional limitation was separately recorded.
Key claims
A differentiable pathwise objective reached 99.3 percent in simulation and 80 percent across ten real flights through a dynamic narrow opening.
Evidence: source-2026-10-29-011
Sources
- arXiv preprint 2610.37557, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.