CoChat
Sign Up
Cited by 28Robotic Path Planning AlgorithmsRobotic Mechanisms and DynamicsHuman Motion and Animation

The DOI matches its Crossref record; the references it cites are not checked yet.

Motions in Microseconds via Vectorized Sampling-Based Planning

Open access
Thomason, Wil, Kingston, Zachary, Kavraki, Lydia E.·2024·2024 IEEE International Conference on Robotics and Automation (ICRA)
DOI 10.1109/icra57147.2024.10611190
Open this paper in CoChat — free accountOpen PDF

Abstract

Modern sampling-based motion planning algorithms typically take between hundreds of milliseconds to dozens of seconds to find collision-free motions for high degree-of-freedom problems. This paper presents performance improvements of more than 500x over the state-of-the-art, bringing planning times into the range of microseconds and solution rates into the range of kilohertz, without specialized hardware. Our key insight is how to exploit fine-grained parallelism within planning, providing generality-preserving algorithmic improvements to any such planner and significantly accelerating critical subroutines, such as forward kinematics and collision checking. We demonstrate our approach over a diverse set of challenging, realistic problems for complex robots ranging from 7 to 14 degrees-of-freedom. Moreover, we show our approach does not require high-power hardware by evaluating on a low-power single-board computer. The planning speeds demonstrated are fast enough to reside in the range of control frequencies and open up new avenues of motion planning research.

Overview

Integrity signals

Registry

Crossref · 10.1109/icra57147.2024.10611190

Cites

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Fundamental path planning research focuses primarily on indoor or outdoor terrestrial environments, with limited attention to planetary scenarios.

    “Fundamental path planning research, on the other hand, focuses primarily on indoor or outdoor terrestrial environments (Thomason et al., 2024; Le et al., 2025), with limited attention to planetary scenarios.”

    From Planetary Terrain Datasets and Benchmarks for Rover Path Planning (2025) · cites this paper as Thomason et al., 2024

Citations

The citation lists haven’t been fetched yet

References 77 · Cited by 28

Research works printed but not linked: 79

  1. 10.1109/ROBOT.2000.844730 · DOI · Paper page
  2. Choset, 2005, Principles of robot motion: theory, algorithms, and implementations
  3. 10.1017/CBO9780511546877 · DOI
  4. 10.1007/978-3-319-32552-1_7 · DOI
  5. 10.1109/70.508439 · DOI · Paper page
  6. 10.1177/0278364913488805 · DOI
  7. 10.1177/0278364914528132 · DOI
  8. 10.1109/HUMANOIDS.2018.8625041 · DOI
  9. 10.1109/ROBOT.1999.770055 · DOI
  10. 10.1109/IROS.2011.6095053 · DOI
  11. 10.1109/ICRA.2012.6225334 · DOI
  12. 10.1109/ICRA.2013.6631154 · DOI
  13. Bhardwaj, 2021, STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulation, Conference on Robot Learning.
  14. 10.1109/ICRA48891.2023.10160765 · DOI
  15. Fishman, Motion Policy Networks, 205, 967
  16. 10.1109/LRA.2021.3133603 · DOI · Paper page
  17. 10.1109/MRA.2012.2205651 · DOI · Paper page
  18. 10.1109/SFCS.1979.10 · DOI
  19. Canny, 1988, The complexity of robot motion planning
  20. 10.1007/978-3-030-43089-4_40 · DOI
  21. 10.1201/b14581 · DOI
  22. 10.1111/j.1467-8659.2009.01377.x · DOI
  23. 10.1109/IROS40897.2019.8968492 · DOI
  24. 10.1109/ICRA.2012.6225337 · DOI
  25. Coumans, PyBullet, a Python module for physics simulation for games, robotics and machine learning
  26. 10.1007/3-540-36460-9_27 · DOI
  27. 10.1109/ROBOT.2000.844107 · DOI
  28. 10.1609/icaps.v28i1.13879 · DOI
  29. 10.1109/IROS.2000.895219 · DOI
  30. 10.24963/ijcai.2018/679 · DOI
  31. 10.1109/TRO.2020.2974094 · DOI
  32. 10.1109/ICRA48506.2021.9561516 · DOI
  33. 10.1109/ICRA48891.2023.10161528 · DOI
  34. 10.15607/rss.2018.xiv.043 · DOI
  35. 10.1109/LRA.2022.3227860 · DOI
  36. 10.1109/ROBOT.1990.126256 · DOI
  37. 10.1023/A:1007948727999 · DOI
  38. Wedge, On heavy-tailed runtimes and restarts in rapidly-exploring random trees, 127
  39. 10.1109/TRO.2010.2098622 · DOI
  40. 10.1109/TRO.2005.847599 · DOI
  41. 10.23919/FPL.2017.8056773 · DOI
  42. 10.1109/IROS.2012.6386194 · DOI
  43. 10.1609/socs.v15i1.21761 · DOI
  44. 10.1109/LRA.2022.3157544 · DOI
  45. 10.1609/aaai.v29i1.9367 · DOI
  46. Fukunaga, 2017, A Survey of Parallel A*
  47. 10.1007/978-3-319-63516-3_11 · DOI
  48. 10.1177/0278364911429335 · DOI
  49. 2023, Intel® 64 and IA-32 architectures software developer’s manual, Tech. rep. Intel®
  50. 10.1109/4.126537 · DOI
  51. 10.1109/ICRA.2019.8794099 · DOI
  52. 10.1109/SII.2019.8700380 · DOI
  53. 10.1109/IRC.2017.72 · DOI
  54. 10.1109/IROS45743.2020.9341411 · DOI
  55. 10.1109/MCAS.2021.3071609 · DOI
  56. 10.15607/RSS.2016.XII.004 · DOI
  57. 10.1109/MICRO.2016.7783748 · DOI
  58. Murray, 2019, Accelerated Motion Planning Through Hardware/Software Co-Design
  59. 10.1145/3579371.3589092 · DOI
  60. 10.1145/3445814.3446746 · DOI
  61. 10.1109/CCGrid.2014.16 · DOI
  62. 10.1109/ROBOT.2001.933002 · DOI
  63. 10.1109/ROBOT.1987.1087825 · DOI
  64. 10.1145/966131.966132 · DOI
  65. O’Sullivan, Real-Time Collision Detection and Response Using Sphere-Trees, 1
  66. 10.1609/icaps.v29i1.3543 · DOI
  67. 10.1177/02783649211069572 · DOI
  68. 10.1007/978-3-030-44051-0_5 · DOI
  69. 10.1177/0278364907079280 · DOI
  70. 10.1109/ROBOT.2010.5509683 · DOI
  71. 10.1177/0278364912453186 · DOI
  72. 10.1109/MRA.2011.2181749 · DOI
  73. 10.1109/IROS47612.2022.9981698 · DOI
  74. Quigley, 2009, ROS: an open-source Robot Operating System, 3, 5
  75. 10.1007/BF01386213 · DOI
  76. 10.1177/0278364904045481 · DOI
  77. 10.1007/978-3-540-48113-3_8 · DOI
  78. Jakob, 2022, nanobind: tiny and efficient C++/Python bindings
  79. Huang, 2018, Robust watertight manifold surface generation method for shapenet models

Metadata

Authors
Thomason, W., Kingston, Z., & Kavraki, L. E.
Affiliations
Rice University (US)
ORCID
Venue
2024 IEEE International Conference on Robotics and Automation (ICRA)
Publisher
IEEE
Published
2024-05-13
Pages
8749-8756
ISSN
1050-4729 (ISSN-L)
DOI
10.1109/icra57147.2024.10611190
OpenAlex
W4401416897
Cited by
28
References
77
Citations by year
2026: 10 · 2025: 16 · 2024: 2
FWCI
5.78
Type
conference paper
Language
en
Open access
Licence
Locations
  • Proceedings - IEEE International Conference on Robotics and Automation/Proceedings (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • Computing Research Association
  • Rice University
Topics
  • Physical Sciences › Engineering › Control and Systems Engineering › Robotic Path Planning Algorithms
  • Physical Sciences › Engineering › Control and Systems Engineering › Robotic Mechanisms and Dynamics
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Human Motion and Animation
Keywords
sampling-based motion planning, parallel planning, high-degree-of-freedom robots, collision detection, forward kinematics, real-time planning, robot motion planning

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review