Abstract
Multiquery planning algorithms find paths between various different starts and goals in a single search space. They are designed to do so efficiently by reusing information across planning queries. This information may be computed before or during the search and often includes knowledge of valid paths.
Using known valid paths to solve an individual planning query takes less computational effort than finding a completely new solution. This allows multiquery algorithms, such as PRM*, to outperform single-query algorithms, such as RRT*, on many problems but their relative performance depends on how much information is reused. Despite this, few multiquery planners explicitly seek to maximize path reuse and, as a result, many do not consistently outperform single-query alternatives.
This paper presents Effort Informed Roadmaps (EIRM*), an almost-surely asymptotically optimal multiquery planning algorithm that explicitly prioritizes reusing computational effort. EIRM* uses an asymmetric bidirectional search to identify existing paths that may help solve an individual planning query and then uses this information to order its search and reduce computational effort. This allows it to find initial solutions up to an order-of-magnitude faster than state-of-the-art planning algorithms on the tested abstract and robotic multiquery planning problems.
M. P. Strub—Work performed while at the University of Oxford.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
All experiments were run using OMPL 1.5, on a laptop with an Intel i7-4720HQ CPU @ 2.60GHz processor with 16GB RAM.
References
Berenson, D., Abbeel, P., Goldberg, K.: A robot path planning framework that learns from experience. In: ICRA, pp. 3671–3678 (2012). https://ieeexplore.ieee.org/document/6224742
Bohlin, R., Kavraki, L.E.: Path planning using lazy PRM. In: ICRA, pp. 521–528 (2000). https://ieeexplore.ieee.org/abstract/document/844107
Bruce, J., Veloso, M.M.: Real-time randomized path planning for robot navigation. In: Kaminka, G.A., Lima, P.U., Rojas, R. (eds.) RoboCup 2002. LNCS (LNAI), vol. 2752, pp. 288–295. Springer, Heidelberg (2003). https://doi.org/10.1007/978-3-540-45135-8_23 https://ieeexplore.ieee.org/document/1041624
Chen, B., Dai, B., Lin, Q., Ye, G., Liu, H., Song, L.: Learning to plan in high dimensions via neural exploration-exploitation trees. In: ICLR (2020). https://openreview.net/forum?id=rJgJDAVKvB
Coleman, D., Şucan, I.A., Moll, M., Okada, K., Correll, N.: Experience-based planning with sparse roadmap spanners. In: ICRA, pp. 900–905 (2015). https://ieeexplore.ieee.org/document/7139284
Dobson, A., Bekris, K.E.: Sparse roadmap spanners for asymptotically near-optimal motion planning. IJRR 33, 18–47 (2014). https://doi.org/10.1177/0278364913498292
Dobson, A., Krontiris, A., Bekris, K.E.: Sparse roadmap spanners. In: Frazzoli, E., Lozano-Perez, T., Roy, N., Rus, D. (eds.) Algorithmic Foundations of Robotics X. STAR, vol. 86, pp. 279–296. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-36279-8_17
Elbanhawi, M., Simic, M.: Sampling-based robot motion planning: a review. IEEE Access (2014). https://ieeexplore.ieee.org/document/6722915
Faust, A., et al.: PRM-RL: long-range robotic navigation tasks by combining reinforcement learning and sampling-based planning. In: ICRA, pp. 5113–5120 (2018). https://arxiv.org/abs/1710.03937
Funk, N., Chalvatzaki, G., Belousov, B., Peters, J.: Learn2Assemble with Structured Representations and Search for Robotic Architectural Construction. In: CoRL (2021). https://openreview.net/forum?id=wBT0lZJAJ0V
Gammell, J.D., Strub, M.P.: Asymptotically optimal sampling-based motion planning methods. Ann. Rev. Control Robot. Autonom. Syst. 4, 295–318 (2021). https://arxiv.org/abs/2009.10484
Gammell, J.D., Barfoot, T.D., Srinivasa, S.S.: Informed sampling for asymptotically optimal path planning. T-RO 34, 966–984 (2018). https://ieeexplore.ieee.org/document/8392759
Gammell, J.D., Barfoot, T.D., Srinivasa, S.S.: Batch Informed Trees (BIT*): informed asymptotically optimal anytime search. IJRR 39, 543–567 (2020). https://doi.org/10.1177/0278364919890396
Hartmann, V.N., Oguz, O.S., Driess, D., Toussaint, M., Menges, A.: Robust task and motion planning for long-horizon architectural construction planning. In: IROS, pp. 6886–6893 (2020). https://ieeexplore.ieee.org/document/9341502
Hartmann, V.N., Orthey, A., Driess, D., Oguz, O.S., Toussaint, M.: Long-horizon multi-robot rearrangement planning for construction assembly. To Appear in T-RO (2021)
Hauser, K.: Lazy collision checking in asymptotically-optimal motion planning. In: ICRA, pp. 2951–2957 (2015) https://ieeexplore.ieee.org/document/7139603
Ichter, B., Harrison, J., Pavone, M.: Learning sampling distributions for robot motion planning. In: ICRA, pp. 7087–7094 (2018). https://ieeexplore.ieee.org/document/8460730
Ichter, B., Schmerling, E., Lee, T.W.E., Faust, A.: Learned critical probabilistic roadmaps for robotic motion planning. In: ICRA, pp. 9535–9541 (2020). https://ieeexplore.ieee.org/document/9197106
Karaman, S., Frazzoli, E.: Sampling-based algorithms for optimal motion planning. IJRR 30, 846–894 (2011). https://doi.org/10.1177/0278364911406761
Kavraki, L.E., Svestka, P., Latombe, J.C., Overmars, M.H.: Probabilistic roadmaps for path planning in high-dimensional configuration spaces. T-RO 12, 566–580 (1996). https://ieeexplore.ieee.org/document/508439
Kiesel, S., Gu, T., Ruml, W.: An effort bias for sampling-based motion planning. In: IROS, pp. 2864–2871 (2017). https://ieeexplore.ieee.org/document/8206118
Lagriffoul, F., Dantam, N.T., Garrett, C., Akbari, A., Srivastava, S., Kavraki, L.E.: Platform-independent benchmarks for task and motion planning. RA-L 3, 3765–3772 (2018). https://ieeexplore.ieee.org/document/8411475
Lavalle, S.M.: Rapidly-exploring random trees: a new tool for path planning. Technical Report (1998)
Li, T.Y., Shie, Y.C .: An incremental learning approach to motion planning with roadmap management. In: ICRA, pp. 3411–3416 (2002). https://ieeexplore.ieee.org/document/1014238
Pan, J., Chitta, S., Manocha, D.: FCL: a general purpose library for collision and proximity queries. In: ICRA, pp. 3859–3866 (2012). https://ieeexplore.ieee.org/document/6225337
Penrose, M.: Random Geometric Graphs. OUP Oxford, Oxford (2003)
Phillips, M., Cohen, B.J., Chitta, S., Likhachev, M.: E-graphs: bootstrapping planning with experience graphs. In: R:SS, p. 110 (2012). http://www.roboticsproceedings.org/rss08/p43.pdf
Phillips, M., Dornbush, A., Chitta, S., Likhachev, M.: Anytime incremental planning with e-graphs. In: ICRA, pp. 2444–2451 (2013). https://www.cs.cmu.edu/~maxim/files/anytimeincrementalegraphsicra13.pdf
Solovey, K., Kleinbort, M.: The critical radius in sampling-based motion planning. IJRR 39, 266–285 (2020). https://doi.org/10.1177/0278364919859627
Stewart, B.S., White, C.C.: Multiobjective A*. J. ACM 38, 775–814 (1991). https://doi.org/10.1145/115234.115368
Strub, M.P.: Leveraging multiple sources of information to search continuous spaces. PhD thesis, University of Oxford (2021). https://robotic-esp.com/papers/strubdphil21
Strub, M.P., Gammell, J.D.: AIT* and EIT*: asymmetric bidirectional sampling-based path planning. To appear in IJRR (2022). https://robotic-esp.com/papers/strubijrr22
Şucan, I.A., Moll, M., Kavraki, L.E.: The open motion planning library. RAM, 72–82 (2012). https://ompl.kavrakilab.org
Sánchez, G., Latombe, J.C.: A single-query bi-directional probabilistic roadmap planner with lazy collision checking. In: ISRR (2001). https://doi.org/10.1007/3-540-36460-927
Thayer, J., Benton, J., Helmert, M.: Better parameter-free anytime search by minimizing time between solutions. In: SOcS (2012)
Acknowledgement
This research has been supported by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy - EXC 2120/1 - 390831618 and UK Research and Innovation and EPSRC through ACE-OPS: From Autonomy to Cognitive assistance in Emergency OPerationS [EP/S030832/1].
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Supplementary material 1 (mp4 2244 KB)
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hartmann, V.N., Strub, M.P., Toussaint, M., Gammell, J.D. (2023). Effort Informed Roadmaps (EIRM*): Efficient Asymptotically Optimal Multiquery Planning by Actively Reusing Validation Effort. In: Billard, A., Asfour, T., Khatib, O. (eds) Robotics Research. ISRR 2022. Springer Proceedings in Advanced Robotics, vol 27. Springer, Cham. https://doi.org/10.1007/978-3-031-25555-7_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-25555-7_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25554-0
Online ISBN: 978-3-031-25555-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)