2000 character limit reached
Neural Implicit Swept Volume Models for Fast Collision Detection (2402.15281v3)
Published 23 Feb 2024 in cs.RO and cs.LG
Abstract: Collision detection is one of the most time-consuming operations during motion planning. Thus, there is an increasing interest in exploring machine learning techniques to speed up collision detection and sampling-based motion planning. A recent line of research focuses on utilizing neural signed distance functions of either the robot geometry or the swept volume of the robot motion. Building on this, we present a novel neural implicit swept volume model to continuously represent arbitrary motions parameterized by their start and goal configurations. This allows to quickly compute signed distances for any point in the task space to the robot motion. Further, we present an algorithm combining the speed of the deep learning-based signed distance computations with the strong accuracy guarantees of geometric collision checkers. We validate our approach in simulated and real-world robotic experiments, and demonstrate that it is able to speed up a commercial bin picking application.
- K. Kleeberger, R. Bormann, W. Kraus, and M. F. Huber, “A Survey on Learning-Based Robotic Grasping,” Current Robotics Reports, vol. 1, pp. 239–249, 12 2020.
- A. ten Pas, M. Gualtieri, K. Saenko, and R. Platt Jr., “Grasp Pose Detection in Point Clouds,” Int. Journal of Robotics Research (IJRR), vol. 36, no. 13–14, pp. 1455–1473, 2017.
- J. Pan and D. Manocha, “Efficient Configuration Space Construction and Optimization for Motion Planning,” Engineering, vol. 1, no. 1, pp. 46–57, Mar. 2015.
- D. Coleman, I. A. Șucan, S. Chitta, and N. Correll, “Reducing the Barrier to Entry of Complex Robotic Software: a MoveIt! Case Study,” Journal of Software Engineering for Robotics (JOSER), vol. 5, no. 1, pp. 3–16, Mar. 2014.
- S. Sellán, N. Aigerman, and A. Jacobson, “Swept Volumes via Spacetime Numerical Continuation,” ACM Trans. on Graphics, vol. 40, no. 4, pp. 1–11, 2021.
- K. Cao, C. Wei, A. Gaidon, N. Arechiga, and T. Ma, “Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss,” in Advances in Neural Information Processing Systems (NeurIPS), 2019.
- J. Tan, C. Wang, B. Li, Q. Li, W. Ouyang, C. Yin, and J. Yan, “Equalization Loss for Long-Tailed Object Recognition,” in Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2020.
- X. Wang, L. Lian, Z. Miao, Z. Liu, and S. Yu, “Long-tailed Recognition by Routing Diverse Distribution-Aware Experts,” in Proc. of the Int. Conf. on Learning Representations (ICLR), 2021.
- H.-T. L. Chiang, A. Faust, S. Sugaya, and L. Tapia, “Fast Swept Volume Estimation with Deep Learning,” in Algorithmic Foundations of Robotics XIII: Proc. of the 13th Workshop on the Algorithmic Foundations of Robotics (WAFR), 2020, DOI: 10.1007/978-3-030-44051-0_4.
- J. Baxter, M. R. Yousefi, S. Sugaya, M. Morales, and L. Tapia, “Deep Prediction of Swept Volume Geometries: Robots and Resolutions,” in Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), 2020, DOI: 10.1109/IROS45743.2020.9341396.
- M.-H. Lee and J.-S. Liu, “Single Swept Volume Reconstruction by Signed Distance Function Learning: A feasibility study based on implicit geometric regularization,” IFAC-PapersOnLine, vol. 55, no. 15, pp. 142–147, 2022, Conf. on Intelligent Control and Automation Sciences (ICONS).
- A. Gropp, L. Yariv, N. Haim, M. Atzmon, and Y. Lipman, “Implicit Geometric Regularization for Learning Shapes,” in Proc. of the Int. Conf. on Machine Learning (ICML), 2020, DOI: 10.5555/3524938.3525293.
- J. B. Michaux, Y. Kwon, Q. Chen, and R. Vasudevan, “Reachability-based Trajectory Design with Neural Implicit Safety Constraints,” in Proc. of Robotics: Science and Systems (RSS), 2023, DOI: 10.15607/RSS.2023.XIX.062.
- P. Liu, K. Zhang, D. Tateo, S. Jauhri, J. Peters, and G. Chalvatzaki, “Regularized Deep Signed Distance Fields for Reactive Motion Generation,” in Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), 2022, DOI: 10.1109/IROS47612.2022.9981456.
- M. Koptev, N. Figueroa, and A. Billard, “Neural Joint Space Implicit Signed Distance Functions for Reactive Robot Manipulator Control,” IEEE Robotics and Automation Letters, vol. 8, no. 2, pp. 480–487, 2023.
- Y. Li, Y. Zhang, A. Razmjoo, and S. Calinon, “Learning Robot Geometry as Distance Fields: Applications to Whole-body Manipulation,” 2023, arXiv preprint, DOI: 10.48550/arXiv.2307.00533.
- K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778, DOI: 10.1109/CVPR.2016.90.
- J. J. Park, P. Florence, J. Straub, R. Newcombe, and S. Lovegrove, “DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation,” in Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2019, DOI: 10.1109/CVPR.2019.00025.
- S. Sellán, O. Stein, et al., “Gpytoolbox: A python geometry processing toolbox,” 2023, https://gpytoolbox.org.
- A. Jacobson, D. Panozzo, et al., “libigl: A simple C++ geometry processing library,” 2023, https://libigl.github.io.
- J. Pan, S. Chitta, and D. Manocha, “FCL: A General Purpose Library for Collision and Proximity Queries,” in Proc. of the IEEE Int. Conf. on Robotics and Automation (ICRA), 2012, pp. 3859–3866, DOI: 10.1109/ICRA.2012.6225337.
- D. Joho, J. Schwinn, and K. Safronov, “Data, Models, and Code for: Neural Implicit Swept Volume Models for Fast Collision Detection,” Dataset on zenodo.org, 2024, DOI: 10.5281/zenodo.10638607.