Metraipolis › archive › dc_e1375dade13e

Learning Event-based Obstacle Avoidance via Differentiable Simulation — arXiv:2610.38967

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.38967
License (as archived)
CC0-1.0
Archived
2026-11-01T02:44:18.315Z
SHA-256 of the archived text
23f063d3120041925d6fc4eb98d8870a46064d8e0fa58508eb794ea1472ca00b
Stable URL of this page
https://metraipolis.com/documento/dc_e1375dade13e

How to cite

Learning Event-based Obstacle Avoidance via Differentiable Simulation — arXiv:2610.38967 — arXiv (en), https://arxiv.org/abs/2610.38967 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e1375dade13e (Metraipolis archive dc_e1375dade13e, sha256 23f063d3120041925d6fc4eb98d8870a46064d8e0fa58508eb794ea1472ca00b)
BibTeX
@misc{dce1375dade13e,
  title = {Learning Event-based Obstacle Avoidance via Differentiable Simulation — arXiv:2610.38967},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38967},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e1375dade13e; sha256 23f063d3120041925d6fc4eb98d8870a46064d8e0fa58508eb794ea1472ca00b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38967. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reliable obstacle avoidance is essential for safe quadrotor flight in unknown environments, yet conventional frame-based cameras remain challenged by motion blur, limited dynamic range, and latency under fast motion. Event cameras, with sub-millisecond latency, high dynamic range, and negligible motion blur, offer a promising alternative, but leveraging them for closed-loop control remains difficult. Existing approaches either adopt cascaded architectures that first estimate depth and then map it to control commands, introducing error propagation, or achieve end-to-end control through costly offline pretraining before online fine-tuning can even begin. We address these challenges with a CUDA-based event simulator that exploits GPU parallelism to render events efficiently within the training loop, integrated into a differentiable simulation pipeline that enables direct gradient backpropagation through the differentiable physics model, improving sample efficiency. This allows us to train an end-to-end policy that maps event frames directly to control commands, without intermediate depth estimation. We validate our approach through zero-shot real-world deployment on a quadrotor, achieving robust obstacle avoidance in both odometry-assisted and odometry-free settings, including under low-light conditions where conventional cameras typically fail.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.38967 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-01T02:16:58.639Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).