NeuralSVCD for Efficient Swept Volume Collision Detection
This addresses the efficiency-accuracy trade-off in SVCD for robot manipulation in unstructured environments, though it appears incremental as it builds on existing neural and geometric methods.
The paper tackles the problem of efficient and accurate swept volume collision detection (SVCD) for robot motion planning by introducing NeuralSVCD, a neural encoder-decoder architecture that leverages shape and temporal locality. The result shows it consistently outperforms state-of-the-art methods in both accuracy and computational efficiency across diverse robotic scenarios.
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/.