NeuralSVCD for Efficient Swept Volume Collision Detection

Hojin Jung, Dongwon Son, Beomjoon Kim
Proceedings of The 9th Conference on Robot Learning, PMLR 305:5218-5233, 2025.

Abstract

Robot manipulation in unstructured environments requires efficient and reliable Swept Volume Collision Detection (SVCD) for safe motion planning. Traditional discrete methods potentially miss collisions between these points, whereas SVCD continuously checks for collisions along the entire trajectory. Existing SVCD methods typically face a trade-off between efficiency and accuracy, limiting practical use. In this paper, we introduce NeuralSVCD, a novel neural encoder-decoder architecture tailored to overcome this trade-off. Our approach leverages shape locality and temporal locality through distributed geometric representations and temporal optimization. This enhances computational efficiency without sacrificing accuracy. Comprehensive experiments show that NeuralSVCD consistently outperforms existing state-of-the-art SVCD methods in terms of both collision detection accuracy and computational efficiency, demonstrating its robust applicability across diverse robotic manipulation scenarios. Code and videos are available at https://neuralsvcd.github.io/.

Cite this Paper

BibTeX
@InProceedings{pmlr-v305-jung25e, title = {NeuralSVCD for Efficient Swept Volume Collision Detection}, author = {Jung, Hojin and Son, Dongwon and Kim, Beomjoon}, booktitle = {Proceedings of The 9th Conference on Robot Learning}, pages = {5218--5233}, year = {2025}, editor = {Lim, Joseph and Song, Shuran and Park, Hae-Won}, volume = {305}, series = {Proceedings of Machine Learning Research}, month = {27--30 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v305/main/assets/jung25e/jung25e.pdf}, url = {https://proceedings.mlr.press/v305/jung25e.html}, abstract = {Robot manipulation in unstructured environments requires efficient and reliable Swept Volume Collision Detection (SVCD) for safe motion planning. Traditional discrete methods potentially miss collisions between these points, whereas SVCD continuously checks for collisions along the entire trajectory. Existing SVCD methods typically face a trade-off between efficiency and accuracy, limiting practical use. In this paper, we introduce NeuralSVCD, a novel neural encoder-decoder architecture tailored to overcome this trade-off. Our approach leverages shape locality and temporal locality through distributed geometric representations and temporal optimization. This enhances computational efficiency without sacrificing accuracy. Comprehensive experiments show that NeuralSVCD consistently outperforms existing state-of-the-art SVCD methods in terms of both collision detection accuracy and computational efficiency, demonstrating its robust applicability across diverse robotic manipulation scenarios. Code and videos are available at https://neuralsvcd.github.io/.} }
Endnote
%0 Conference Paper %T NeuralSVCD for Efficient Swept Volume Collision Detection %A Hojin Jung %A Dongwon Son %A Beomjoon Kim %B Proceedings of The 9th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Joseph Lim %E Shuran Song %E Hae-Won Park %F pmlr-v305-jung25e %I PMLR %P 5218--5233 %U https://proceedings.mlr.press/v305/jung25e.html %V 305 %X Robot manipulation in unstructured environments requires efficient and reliable Swept Volume Collision Detection (SVCD) for safe motion planning. Traditional discrete methods potentially miss collisions between these points, whereas SVCD continuously checks for collisions along the entire trajectory. Existing SVCD methods typically face a trade-off between efficiency and accuracy, limiting practical use. In this paper, we introduce NeuralSVCD, a novel neural encoder-decoder architecture tailored to overcome this trade-off. Our approach leverages shape locality and temporal locality through distributed geometric representations and temporal optimization. This enhances computational efficiency without sacrificing accuracy. Comprehensive experiments show that NeuralSVCD consistently outperforms existing state-of-the-art SVCD methods in terms of both collision detection accuracy and computational efficiency, demonstrating its robust applicability across diverse robotic manipulation scenarios. Code and videos are available at https://neuralsvcd.github.io/.
APA
Jung, H., Son, D. & Kim, B.. (2025). NeuralSVCD for Efficient Swept Volume Collision Detection. Proceedings of The 9th Conference on Robot Learning, in Proceedings of Machine Learning Research 305:5218-5233 Available from https://proceedings.mlr.press/v305/jung25e.html.

Related Material