Abstract
This work addresses the challenge of a robot using real-time feedback from contact sensors to reliably manipulate a movable object on a cluttered tabletop. We formulate this task as a partially observable Markov decision process (POMDP) in the joint space of robot configurations and object poses. This formulation enables the robot to explicitly reason about uncertainty and all major types of kinematic constraints: reachability, joint limits, and collision. We solve the POMDP using DESPOT, a state-of-the-art online POMDP solver, by leveraging two key ideas for computational efficiency. First, we lazily construct a discrete lattice in the robot’s configuration space. Second, we guide the search with heuristics derived from an unconstrained relaxation of the problem. We empirically show that our approach outperforms several baselines on a simulated seven degree-of-freedom manipulator.
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
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Dynamic Animation and Robotics Toolkit. http://dartsim.github.io (2013)
Bai, H., Hsu, D., Lee, W., Ngo, V.: Monte Carlo value iteration for continuousstate POMDPs. In: WAFR (2011)
Bohlin, R., Kavraki, L.: Path planning using lazy PRM. In: IEEE ICRA. pp. 521–528 (2000)
Boots, B., Byravan, A., Fox, D.: Learning predictive models of a depth camera & manipulator from raw execution traces. In: IEEE ICRA (2014)
Brokowski, M., Peshkin, M., Goldberg, K.: Curved fences for part alignment. In: IEEE ICRA (1993)
Calli, B., Singh, A., Walsman, A., Srinivasa, S., Abbeel, P., Dollar, A.: The YCB object and model set: Towards common benchmarks for manipulation research. In: ICAR (2015)
Catto, E.: Box2D. http://box2d.org (2010)
Cohen, B., Chitta, S., Likhachev, M.: Single-and dual-arm motion planning with heuristic search. IJRR (2013)
Dogar, M., Hsiao, K., Ciocarlie, M., Srinivasa, S.: Physics-based grasp planning through clutter. In: R:SS (2012)
Dogar, M., Srinivasa, S.: Push-grasping with dexterous hands: Mechanics and a method. In: IEEE/RSJ IROS (2010)
Dogar, M., Srinivasa, S.: A planning framework for non-prehensile manipulation under clutter and uncertainty. AuRo 33(3), 217–236 (2012)
Duff, D., Wyatt, J., Stolkin, R.: Motion estimation using physical simulation. In: IEEE ICRA (2010)
Emery-Montemerlo, R., Gordon, G., Schneider, J., Thrun, S.: Approximate solutions for partially observable stochastic games with common payoffs. In: AAMAS (2004)
Erdmann, M., Mason, M.: An exploration of sensorless manipulation. IEEE T-RA (1988)
Hauser, K.: Lazy collision checking in asymptotically-optimal motion planning. In: IEEE ICRA (2015)
Hebert, P., Howard, T., Hudson, N., Ma, J., Burdick, J.: The next best touch for model-based localization. In: IEEE ICRA (2013)
Horowitz, M., Burdick, J.: Interactive non-prehensile manipulation for grasping via POMDPs. In: IEEE ICRA (2013)
Hsiao, K.: Relatively robust grasping. Ph.D. thesis, MIT (2009)
Hsiao, K., Lozano-Pérez, T., Kaelbling, L.: Robust belief-based execution of manipulation programs. In: WAFR (2008)
Javdani, S., Bagnell, J., Srinivasa, S.: Shared autonomy via hindsight optimization. In: R:SS (2015)
Javdani, S., Klingensmith, M., Bagnell, J., Pollard, N., Srinivasa, S.: Efficient touch based localization through submodularity. In: IEEE ICRA (2013)
Klingensmith, M., Galluzzo, T., Dellin, C., Kazemi, M., Bagnell, J., Pollard, N.: Closed-loop servoing using real-time markerless arm tracking. In: IEEE ICRA Humanoids Workshop (2013)
Koval, M., King, J., Pollard, N., Srinivasa, S.: Robust trajectory selection for rearrangement planning as a multi-armed bandit problem. In: IEEE/RSJ IROS (2015)
Koval, M., Pollard, N., Srinivasa, S.: Pose estimation for planar contact manipulation with manifold particle filters. IJRR 34(7), 922–945 (2015)
Koval, M., Pollard, N., Srinivasa, S.: Pre- and post-contact policy decomposition for planar contact manipulation under uncertainty. IJRR (2015), in press
Kurniawati, H., Hsu, D., Lee, W.: SARSOP: Efficient point-based POMDP planning by approximating optimally reachable belief spaces. In: R:SS (2008)
LaValle, S., Hutchinson, S.: An objective-based framework for motion planning under sensing and control uncertainties. IJRR (1998)
Li, Q., Schürmann, C., Haschke, R., Ritter, H.: A control framework for tactile servoing. In: R:SS (2013)
Likhachev, M., Ferguson, D.: Planning long dynamically feasible maneuvers for autonomous vehicles. IJRR 28(8), 933–945 (2009)
Lim, Z., Hsu, D., Sun, L.: Monte Carlo value iteration with macro-actions. In: NIPS (2011)
Littman, M., Cassandra, A., Kaelbling, L.: Learning policies for partially observable environments: Scaling up. ICML (1995)
Lynch, K., Maekawa, H., Tanie, K.: Manipulation and active sensing by pushing using tactile feedback. In: IEEE/RSJ IROS (1992)
Ng, A., Jordan, M.: PEGASUS: A policy search method for large MDPs and POMDPs. In: UAI (2000)
Pastor, P., Righetti, L., Kalakrishnan, M., Schaal, S.: Online movement adaptation based on previous sensor experiences. In: IEEE/RSJ IROS (2011)
Petrovskaya, A., Khatib, O.: Global localization of objects via touch. IEEE T-RO 27(3), 569–585 (2011)
Pivtoraiko, M., Kelly, A.: Efficient constrained path planning via search in state lattices. In: i-SAIRAS (2005)
Platt, R., Fagg, A., Grupen, R.: Nullspace grasp control: theory and experiments. IEEE T-RO 26(2), 282–295 (2010)
Ross, S., Pineau, J., Paquet, S., Chaib-Draa, B.: Online planning algorithms for POMDPs. JAIR (2008)
Salisbury, K., Townsend, W., Eberman, B., DiPietro, D.: Preliminary design of a whole-arm manipulation system (WAMS). In: IEEE ICRA (1988)
Seiler, K., Kurniawati, H., Singh, S.: GPS-ABT: An online and approximate solver for POMDPs with continuous action space. In: IEEE ICRA (2015)
Silver, D., Veness, J.: Monte-Carlo planning in large POMDPs. In: NIPS (2010)
Smallwood, R., Sondik, E.: The optimal control of partially observable Markov processes over a finite horizon. Operations Research 21(5), 1071–1088 (1973)
Somani, A., Ye, N., Hsu, D., Lee, W.: DESPOT: Online POMDP planning with regularization. In: NIPS (2013)
Srinivasa, S., Berenson, D., Cakmak, M., Collet, A., Dogar, M., Dragan, A., Knepper, R., Niemueller, T., Strabala, K., VandeWeghe,M.: HERB 2.0: Lessons learned from developing a mobile manipulator for the home. Proc. IEEE 100(8), 1–19 (2012)
Stulp, F., Theodorou, E., Buchli, J., Schaal, S.: Learning to grasp under uncertainty. In: IEEE ICRA. pp. 5703–5708 (2011)
Townsend, W.: The BarrettHand grasper-programmably flexible part handling and assembly. Industrial Robot: An International Journal 27(3), 181–188 (2000)
Zhang, H., Chen, N.: Control of contact via tactile sensing. IEEE T-RA 16(5), 482–495 (2000)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Koval, M., Hsu, D., Pollard, N., Srinivasa, S.S. (2020). Configuration Lattices for Planar Contact Manipulation Under Uncertainty. In: Goldberg, K., Abbeel, P., Bekris, K., Miller, L. (eds) Algorithmic Foundations of Robotics XII. Springer Proceedings in Advanced Robotics, vol 13. Springer, Cham. https://doi.org/10.1007/978-3-030-43089-4_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-43089-4_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-43088-7
Online ISBN: 978-3-030-43089-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)