Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2509.00499 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915472268591104 |
|---|---|
| author | Son, Dongwon Jung, Hojin Kim, Beomjoon |
| author_facet | Son, Dongwon Jung, Hojin Kim, Beomjoon |
| contents | 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/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_00499 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NeuralSVCD for Efficient Swept Volume Collision Detection Son, Dongwon Jung, Hojin Kim, Beomjoon Robotics Artificial Intelligence Machine Learning 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/. |
| title | NeuralSVCD for Efficient Swept Volume Collision Detection |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2509.00499 |