Skip to main content
SpringerLink
Log in
Book cover

Robotics Research pp 251–267Cite as

Accelerating Motion Planning for Learned Mobile Manipulation Tasks Using Task-Guided Gibbs Sampling

  • Conference paper
  • First Online:

Part of the book series: Springer Proceedings in Advanced Robotics ((SPAR,volume 10))

Abstract

We present Task-Guided Gibbs Sampling (TGGS), an approach to accelerating motion planning for mobile manipulation tasks learned from demonstrations. This method guides sampling toward configurations most likely to be useful for successful task execution while avoiding manual heuristics and preserving asymptotic optimality of the motion planner. We leverage a learned task model, which is used by the motion planner to evaluate plan cost, to also guide sampling, yielding plans with high rates of success faster than unbiased or goal-biased sampling. This is accomplished by tightly integrating sampling with a hybrid motion planner that builds separate base and arm roadmaps using Gibbs sampling. Such an approach allows the sampled arm configurations to depend on the reachable base configurations and vice-versa. We evaluate our method on two household tasks using the Fetch robot and greatly improve upon motion planners that rely on unbiased sampling or either of two goal-biased planners when using the same cost metric.

This is a preview of subscription content, log in via an institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   169.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD   219.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

References

  1. Akgun, B., Stilman, M.: Sampling heuristics for optimal motion planning in high dimensions. In: IEEE/RSJ International Conference Intelligent Robots and Systems (IROS), pp. 2640–2645 (2011)

    Google Scholar 

  2. Amato, N.M., Dill, K.A., Song, G.: Using motion planning to map protein folding landscapes and analyze folding kinetics of known native structures. J. Comput. Biol. 10(3–4), 239–255 (2003)

    Article  Google Scholar 

  3. Balkcom, D.J., Mason, M.T.: Time optimal trajectories for bounded velocity differential drive vehicles. Int. J. Robot. Res. 21(3), 199–217 (2002)

    Article  Google Scholar 

  4. Berenson, D., Simeon, T., Srinivasa, S.S.: Addressing cost-space chasms in manipulation planning. In: Proceedings of the IEEE International Conference Robotics and Automation (ICRA), pp. 4561–4568 (2011)

    Google Scholar 

  5. Bowen, C., Alterovitz, R.: Closed-loop global motion planning for reactive execution of learned tasks. In: Proceedings of the IEEE/RSJ International Conference Intelligent Robots and Systems (IROS), pp. 1754–1760 (2014)

    Google Scholar 

  6. Bowen, C., Ye, G., Alterovitz, R.: Asymptotically optimal motion planning for learned tasks using time-dependent cost maps. IEEE Trans. Autom. Sci. Eng. 12(1), 171–182 (2015)

    Article  Google Scholar 

  7. Burns, B., Brock, O.: Sampling-based motion planning using predictive models. In: IEEE International Conference Robotics and Automation (ICRA), pp. 3120–3125 (2005)

    Google Scholar 

  8. Calinon, S., Li, Z., Alizadeh, T., Tsagarakis, N.G., Caldwell, D.G.: Statistical dynamical systems for skills acquisition in humanoids. In: 12th IEEE-RAS International Conference Humanoid Robots (Humanoids), pp. 323–329 (2012)

    Google Scholar 

  9. Cambon, S., Alami, R., Gravot, F.: A hybrid approach to intricate motion, manipulation and task planning. Int. J. Robot. Res. (IJRR) 28(1), 104–126 (2009)

    Article  Google Scholar 

  10. Candido, S., Kim, Y.T., Hutchinson, S.: An improved hierarchical motion planner for humanoid robots. In: 8th IEEE-RAS International Conference Humanoid Robots (Humanoids), pp. 654–661 (2008)

    Google Scholar 

  11. Claassens, J., Demiris, Y.: Exploiting affordance symmetries for task reproduction planning. In: 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids), pp. 653–659 (2012)

    Google Scholar 

  12. Devaurs, D., Siméon, T., Cortés, J.: Enhancing the transition-based rrt to deal with complex cost spaces. In: IEEE International Conference Robotics and Automation (ICRA), pp. 4120–4125 (2013)

    Google Scholar 

  13. Dietrich, A., Wimbock, T., Albu-Schaffer, A., Hirzinger, G.: Reactive whole-body control: dynamic mobile manipulation using a large number of actuated degrees of freedom. IEEE Robot. Autom. Mag. 19(2), 20–33 (2012)

    Article  Google Scholar 

  14. Eppner, C., Sturm, J., Bennewitz, M., Stachniss, C., Burgard, W.: Imitation learning with generalized task descriptions. In: Proceedings of the IEEE International Conference Robotics and Automation (ICRA), pp. 3968–3974 (2009)

    Google Scholar 

  15. Gammell, J.D., Srinivasa, S.S., Barfoot, T.D.: Batch informed trees (BIT*): Sampling-based optimal planning via the heuristically guided search of implicit random geometric graphs. In: International Conference Robotics and Automation (ICRA), pp. 3067–3074 (2015)

    Google Scholar 

  16. Havoutis, I., Ramamoorthy, S.: Motion planning and reactive control on learnt skill manifolds. Int. J. Robot. Res. (IJRR) 32(9–10), 1120–1150 (2013)

    Article  Google Scholar 

  17. Iehl, R., Cortés, J., Siméon, T.: Costmap planning in high dimensional configuration spaces. In: IEEE/ASME International Conference Advanced Intelligent Mechatronics (AIM), pp. 166–172 (2012)

    Google Scholar 

  18. Jaillet, L., Porta, J.M.: Asymptotically-optimal path planning on manifolds. Robot.: Sci. Syst. VIII, 145 (2013)

    Google Scholar 

  19. Kaelbling, L.P., Lozano-Pérez, T.: Hierarchical task and motion planning in the now. In: IEEE International Conference Robotics and Automation (ICRA), pp. 1470–1477 (2011)

    Google Scholar 

  20. Kalakrishnan, M., Chitta, S., Theodorou, E., Pastor, P., Schaal, S.: STOMP: Stochastic trajectory optimization for motion planning. In: Proceedings of the IEEE International Conference Robotics and Automation (ICRA), pp. 4569–4574 (2011)

    Google Scholar 

  21. Karaman, S., Frazzoli, E.: Optimal kinodynamic motion planning using incremental sampling-based methods. In: Proceedings of the IEEE Conference Decision and Control, pp. 7681–7687 (2010)

    Google Scholar 

  22. Karaman, S., Frazzoli, E.: Sampling-based algorithms for optimal motion planning. Int. J. Robot. Res. 30(7), 846–894 (2011)

    Article  Google Scholar 

  23. Kunz, T., Stilman, M.: Manipulation planning with soft task constraints. In: IEEE/RSJ International Conference Intelligent Robots and Systems (IROS), pp. 1937–1942 (2012)

    Google Scholar 

  24. Kurniawati, H., Hsu, D.: Workspace importance sampling for probabilistic roadmap planning. In: IEEE/RSJ International Conference Intelligent Robots and Systems (IROS), vol. 2, pp. 1618–1623 (2004)

    Google Scholar 

  25. Lindemann, S.R., LaValle, S.M.: Current issues in sampling-based motion planning. In: Proceedings of the International Symposium on Robotics Research, pp. 36–54 (2005)

    Google Scholar 

  26. Pilania, V., Gupta, K.: A hierarchical and adaptive mobile manipulator planner with base pose uncertainty. Auton. Robot. 39(1), 65–85 (2015)

    Article  Google Scholar 

  27. Plaku, E., Kavraki, L.E., Vardi, M.Y.: Hybrid systems: from verification to falsification by combining motion planning and discrete search. Form. Methods Syst. Des. 34(2), 157–182 (2009)

    Article  Google Scholar 

  28. Şucan, I.A., Chitta, S.: Motion planning with constraints using configuration space approximations. In: IEEE/RSJ International Conference Intelligent Robots and Systems (IROS), pp. 1904–1910 (2012)

    Google Scholar 

  29. Sun, Z., Hsu, D., Jiang, T., Kurniawati, H., Reif, J.H.: Narrow passage sampling for probabilistic roadmap planning. IEEE Trans. Robot. (TRO) 21(6), 1105–1115 (2005)

    Article  Google Scholar 

  30. Tanner, H.G., Loizou, S.G., Kyriakopoulos, K.J.: Nonholonomic navigation and control of cooperating mobile manipulators. IEEE Trans. Robot. Autom. 19(1), 53–64 (2003)

    Article  Google Scholar 

  31. Tanwani, A.K., Calinon, S.: Learning robot manipulation tasks with task-parameterized semitied hidden semi-Markov model. IEEE Robot. Autom. Lett. 1(1), 235–242 (2016)

    Article  Google Scholar 

  32. Wise, M., Ferguson, M., King, D., Diehr, E., Dymesich, D.: Fetch and freight: Standard platforms for service robot applications. In: Workshop on Autonomous Mobile Service Robots (2016)

    Google Scholar 

  33. Wolfe, J., Marthi, B., Russell, S.J.: Combined task and motion planning for mobile manipulation. In: International Conference Automated Planning and Scheduling, pp. 254–258 (2010)

    Google Scholar 

  34. Yang, Y., Brock, O.: Elastic roadmaps–motion generation for autonomous mobile manipulation. Auton. Robot. 28(1), 113–130 (2010)

    Article  Google Scholar 

Download references

Acknowledgements

We thank Armaan Sethi for his assistance with the demonstrations and experimental evaluation. We used the Rviz visualization tool to generate various figures. This research was supported in part by the U.S. National Science Foundation (NSF) under awards CCF-1533844 and IIS-1149965.

Author information

Authors and Affiliations

  1. University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599-3175, USA

    Chris Bowen & Ron Alterovitz

Authors
  1. Chris Bowen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ron Alterovitz
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Chris Bowen .

Editor information

Editors and Affiliations

  1. Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA

    Nancy M. Amato

  2. Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA

    Greg Hager

  3. Department of Computer Science and Engineering, Texas A&M University, College Station, TX, USA

    Shawna Thomas

  4. Department of Electrical Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile

    Miguel Torres-Torriti

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Bowen, C., Alterovitz, R. (2020). Accelerating Motion Planning for Learned Mobile Manipulation Tasks Using Task-Guided Gibbs Sampling. In: Amato, N., Hager, G., Thomas, S., Torres-Torriti, M. (eds) Robotics Research. Springer Proceedings in Advanced Robotics, vol 10. Springer, Cham. https://doi.org/10.1007/978-3-030-28619-4_23

Download citation

Publish with us

Policies and ethics

Search

Navigation