research-article

Learning-Based Proxy Collision Detection for Robot Motion Planning Applications

Authors:

Michael YipAuthors Info & Claims

IEEE Transactions on Robotics, Volume 36, Issue 4

Pages 1096 - 1114

https://doi.org/10.1109/TRO.2020.2974094

Published: 01 August 2020 Publication History

Abstract

This article demonstrates that collision detection-intensive applications such as robotic motion planning may be accelerated by performing collision checks with a machine learning model. We propose Fastron, a learning-based algorithm, to model a robot's configuration space to be used as a proxy collision detector in place of standard geometric collision checkers. We demonstrate that leveraging the proxy collision detector results in up to an <italic>order of magnitude</italic> faster performance in robot simulation and planning than state-of-the-art collision detection libraries. Our results show that Fastron learns a model more than 100 times faster than a competing C-space modeling approach, while also providing theoretical guarantees of learning convergence. Using the open motion planning libraries (OMPLs), we were able to generate initial motion plans across all experiments with varying robot and environment complexities and workspace obstacle locations. With Fastron, we can repeatedly generate new motion plans at a 56 Hz rate, showing its application toward autonomous surgical assistance task in shared environments with human-controlled manipulators. All performance gains were achieved despite using only CPU-based calculations, suggesting further computational gains with a GPU approach that can parallelize tensor algebra. Code is available online.<xref ref-type="fn" rid="fn1"><sup>1</sup></xref>

References

[1]

H. Choset et al., Principles of Robot Motion: Theory, Algorithms, and Implementation. Cambridge, MA, USA: MIT Press, 2005.

[2]

T. Lozano-Perez, “Spatial planning: A configuration space approach,” IEEE Trans. Comput., vol. 32, no. 2, pp. 108–120, Feb. 1983.

Digital Library

[3]

B. Burns and O. Brock, “Toward optimal configuration space sampling,” in Robotics: Science and Systems, Cambridge, MA, USA: MIT Press, 2005.

[4]

J. Pan and D. Manocha, “Efficient configuration space construction and optimization for motion planning,” Eng., vol. 1, no. 1, pp. 046–057, 2015.

[5]

M. Elbanhawi and M. Simic, “Sampling-based robot motion planning: A review,” IEEE Access, vol. 2, pp. 56–77, 2014.

[6]

M. Duguleana, F. Grigore, A. Teirelbar, and G. Mogan, “Obstacle avoidance of redundant manipulators using neural networks based reinforcement learning,” Robot. Comput. Integr. Manuf., vol. 28, no. 2, pp. 132–146, 2012.

Digital Library

[7]

J. Kuffner, K. Nishiwaki, S. Kagami, Y. Kuniyoshi, M. Inaba, and H. Inoue, “Self-collision detection and prevention for humanoid robots,” in Proc. IEEE Int. Conf. Robot. Autom., May 2002, pp. 2265–2270.

[8]

E. Rohmer, S. P. N. Singh, and M. Freese, “V-REP : A Versatile and Scalable Robot Simulation Framework,” in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., 2013, pp. 1321–1326.

[9]

N. Das, N. Gupta, and M. Yip, “Fastron: An online learning-based model and active learning strategy for proxy collision detection,” Proc. 1st Annu. Conf. Robot Learn., 2017, vol. 78, pp. 496–504. [Online]. Available: http://proceedings.mlr.press/v78/das17a.html

[10]

Y. Freund and R. E. Schapire, “Large margin classification using the perceptron algorithm,” Mach. Learn., vol. 37, no. 3, pp. 277–296, 1999.

Digital Library

[11]

J. Huh and D. D. Lee, “Learning high-dimensional mixture models for fast collision detection in rapidly-exploring random trees,” in Proc. IEEE Int. Conf. Robot. Autom., Jun. 2016, pp. 63–69.

[12]

S. M. LaValle, “Rapidly-exploring random trees: A new tool for path planning,” Animal Genetics, vol. 39, no. 5, pp. 561–563, 2008.

[13]

J. Pan and D. Manocha, “Fast probabilistic collision checking for sampling-based motion planning using locality-sensitive hashing,” Int. J. Robot. Res., vol. 35, no. 12, pp. 1477–1496, 2016.

Digital Library

[14]

I. Garcia, J. Martin-Guerrero, E. Soria-Olivas, R. Martinez, S. Rueda, and R. Magdalena, “A neural network approach for real-time collision detection,” in Proc. IEEE Int. Conf. Syst., Man Cybern., 2002, vol. 5, no. 1, pp. 1–5.

[15]

A. H. Qureshi, A. Simeonov, M. J. Bency, and M. C. Yip, “Motion Planning Networks,” in Proc. Int. Conf. Robot. Automat., Montreal, QC, Canada, 2019, pp. 2118–2124.

[16]

C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, 1995.

[17]

C. P. Diehl and G. Cauwenberghs, “SVM Incremental Learning, Adaptation and Optimization,” in Proc. Int. Joint Conf. Neural Netw., 2003, pp. 2685–2690.

[18]

A. J. Smola, B. Scholkopf, and K. R. Muller, “The connection between regularization operators and support vector kernels,” Neural Netw., vol. 11, no. 4, pp. 637–649, 1998.

Digital Library

[19]

C. E. Rasmussen and C. K. I. Williams, Gaussian Processes for Machine Learning. Cambridge, MA, USA: The MIT Press, 2006.

Digital Library

[20]

T. Hofmann, B. Schölkopf, and A. J. Smola, “Kernel methods in machine learning,” Ann. Statist., vol. 36, no. 3, pp. 1171–1220, 2008.

[21]

H. Q. Minh, P. Niyogi, and Y. Yao, “Mercer's theorem, feature maps, and smoothing,” in Proc. Int. Conf. Comput. Learn. Theory, 2006, pp. 154–168.

[22]

S. J. Wright, “Coordinate descent algorithms,” Math. Program., vol. 151, no. 1, pp. 3–34, 2015.

Digital Library

[23]

E. G. Gilbert, D. W. Johnson, and S. S. Keerthi, “A fast procedure for computing the distance between complex objects in three-dimensional space,” IEEE J. Robot. Autom., vol. 4, no. 2, pp. 193–203, Apr. 1988.

[24]

G. Schohn and D. Cohn, “Less is more: Active learning with support vector machines,” in Proc. 17th Int. Conf. Mach. Learn., 2000, pp. 839–846.

[25]

K. Huang, D. Zheng, J. Sun, Y. Hotta, K. Fujimoto, and S. Naoi, “Sparse learning for support vector classification,” Pattern Recognit. Lett., vol. 31, no. 13, pp. 1944–1951, 2010.

Digital Library

[26]

J. Pan, X. Zhang, and D. Manocha, “Efficient penetration depth approximation using active learning,” ACM Trans. Graph., vol. 32, no. 6, 2013, Art. no.

[27]

P. I. Corke, Robotics, Vision & Control. Berlin, Germany: Springer, 2017.

[28]

J. Pan, S. Chitta, and D. Manocha, “FCL: A general purpose library for collision and proximity queries,” in Proc. IEEE Int. Conf. Robot. Autom., 2012, pp. 3859–3866.

[29]

S. Chitta, I. Sucan, and S. Cousins, “MoveIt!” IEEE Robot. Autom. Mag., 19, no. 1, pp. 18–19, Mar. 2012.

[30]

D. Hershberger, D. Gossow, and J. Faust, “3D visualization tool for ROS,” 2018. [Online]. Available: http://wiki.ros.org/rviz

[31]

M. Quigley et al., “ROS: An open-source Robot Operating System,” in Proc. ICRA Workshop Open Source Softw., 2009, pp. 1–6.

[32]

I. A. Sucan, M. Moll, and L. E. Kavraki, “The open motion planning library,” IEEE Robot. Autom. Mag., vol. 19, no. 4, pp. 72–82, Dec. 2012.

[33]

J. J. Kuffner and S. M. Lavalle, “RRT-Connect: An efficient approach to single-query path planning,” in Proc. Int. Conf. Robot. Autom., Apr. 2000, pp. 995–1001.

[34]

S. Karaman and E. Frazzoli, “Sampling-based algorithms for optimal motion planning,” Int. J. Robot. Res., vol. 30, no. 7, pp. 1–76, 2011.

[35]

J. D. Gammell, S. S. Srinivasa, and T. D. Barfoot, “Batch informed trees (BIT^*): Sampling-based optimal planning via the heuristically guided search of implicit random geometric graphs,” in Proc. IEEE Int. Conf. Robot. Autom., 2015, pp. 3067–3074.

[36]

B. Yuh, “The bedside assistant in robotic surgery-keys to success,” Urologic Nursing, vol. 33, no. 1, pp. 29–32, 2013.

[37]

R. M. Kuntz, S. Ahyai, K. Lehrich, and A. M. R. Fayad, “Transurethral holmium laser enucleation of the prostate versus transurethral electrocautery resection of the prostate: A randomized prospective trial in 200 patients,” J. Urology, vol. 172, pp. 1012–1016, Sep. 2004.

[38]

O. Mohareri and S. E. Salcudean, “Da vinci auxiliary arm as a robotic surgical assistant for semiautonomous ultrasound guidance during robot-assisted laparoscopic surgery,” in Proc. Hamlyn Symp. Med. Robot., Jul. 2014, pp. 45–46.

[39]

Z. Chen, A. Deguet, R. Taylor, S. Dimaio, G. Fischer, and P. Kazanzides, “An open-source hardware and software platform for telesurgical robotics research,” in Proc. Workshop Syst. Arch. Comput. Assist. Interventions, 2013, pp. 1–10.

Cited By

Ren YZhou ZXu ZYang YZhai GLeibold MNi FZhang ZBuss MZheng Y(2024)Enabling Versatility and Dexterity of the Dual-Arm Manipulators: A General Framework Toward Universal Cooperative ManipulationIEEE Transactions on Robotics10.1109/TRO.2024.337004840(2024-2045)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TRO.2024.3370048
Sun DLiao Q(2024)A Fuzzy Cluster-Based Framework for Robot–Environment Collision ReactionIEEE Transactions on Fuzzy Systems10.1109/TFUZZ.2023.329012432:1(75-89)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TFUZZ.2023.3290124
Lee MLiu J(2024)Reliable and Accurate Implicit Neural Representation of Multiple Swept Volumes with Application to Safe Human–Robot InteractionSN Computer Science10.1007/s42979-024-02640-85:3Online publication date: 12-Mar-2024
https://dl.acm.org/doi/10.1007/s42979-024-02640-8
Show More Cited By

Index Terms

Learning-Based Proxy Collision Detection for Robot Motion Planning Applications

Index terms have been assigned to the content through auto-classification.

Recommendations

Dynamic Motion Planning Algorithm in Human-Robot Collision Avoidance
Intelligent Robotics and Applications
Abstract
The collision-free robotic motion planning algorithm in a dynamic environment is an effective method for the prevention of collision in a human-robot interaction scenario. In this paper, an improvement of the Rapidly-exploring Random Tree (RRT) ...
A collision-free path-planning method for an articulated mobile robot

In previous works, we treated the collision-free path-planning problem for a nonholonomic mobile robot in a cluttered environment. We used a method based on a representation of the obstacles on the robot's velocity space. This representation is called ...
Kinematic and dynamic motion space analysis and robot motion planning

Comments

Information & Contributors

Information

Published In

cover image IEEE Transactions on Robotics

IEEE Transactions on Robotics Volume 36, Issue 4

Aug. 2020

349 pages

ISSN:1552-3098

Issue’s Table of Contents

1552-3098 © 2020 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.

Publisher

IEEE Press

Publication History

Published: 01 August 2020

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

13
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 20 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Ren YZhou ZXu ZYang YZhai GLeibold MNi FZhang ZBuss MZheng Y(2024)Enabling Versatility and Dexterity of the Dual-Arm Manipulators: A General Framework Toward Universal Cooperative ManipulationIEEE Transactions on Robotics10.1109/TRO.2024.337004840(2024-2045)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TRO.2024.3370048
Sun DLiao Q(2024)A Fuzzy Cluster-Based Framework for Robot–Environment Collision ReactionIEEE Transactions on Fuzzy Systems10.1109/TFUZZ.2023.329012432:1(75-89)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TFUZZ.2023.3290124
Lee MLiu J(2024)Reliable and Accurate Implicit Neural Representation of Multiple Swept Volumes with Application to Safe Human–Robot InteractionSN Computer Science10.1007/s42979-024-02640-85:3Online publication date: 12-Mar-2024
https://dl.acm.org/doi/10.1007/s42979-024-02640-8
Zang XYin MXiao JZonouz SYuan BOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)GraphMPProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3666260(3131-3142)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3666260
Liu HWu GZhou LPedrycz WSuganthan P(2023)Tangent-Based Path Planning for UAV in a 3-D Low Altitude Urban EnvironmentIEEE Transactions on Intelligent Transportation Systems10.1109/TITS.2023.328556824:11(12062-12077)Online publication date: 1-Nov-2023
https://dl.acm.org/doi/10.1109/TITS.2023.3285568
Wu SLiu GZhang YXue A(2023)A fast and accurate compound collision detector for RRT motion planningRobotics and Autonomous Systems10.1016/j.robot.2023.104484167:COnline publication date: 1-Sep-2023
https://dl.acm.org/doi/10.1016/j.robot.2023.104484
Ma GDuan YLi MXie ZZhu J(2023)A probability smoothing Bi-RRT path planning algorithm for indoor robotFuture Generation Computer Systems10.1016/j.future.2023.02.004143:C(349-360)Online publication date: 1-Jun-2023
https://dl.acm.org/doi/10.1016/j.future.2023.02.004
Mirzendehdel ABehandish M(2023)Co-design Optimization of Moving Parts for Compliance and Collision AvoidanceComputer-Aided Design10.1016/j.cad.2023.103547163:COnline publication date: 1-Oct-2023
https://dl.acm.org/doi/10.1016/j.cad.2023.103547
Zhang RYu CChen JFan CGao SKoyejo SMohamed SAgarwal ABelgrave DCho KOh A(2022)Learning-based motion planning in dynamic environments using GNNs and temporal encodingProceedings of the 36th International Conference on Neural Information Processing Systems10.5555/3600270.3602445(30003-30015)Online publication date: 28-Nov-2022
https://dl.acm.org/doi/10.5555/3600270.3602445
Strub MGammell J(2022)Adaptively Informed Trees (AIT*) and Effort Informed Trees (EIT*)International Journal of Robotics Research10.1177/0278364921106957241:4(390-417)Online publication date: 1-Apr-2022
https://dl.acm.org/doi/10.1177/02783649211069572
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents