Abstract
An important requirement for a robot to operate reliably in the real world is a robust motion planning module. Current planning systems do not have consistent performance across all situations a robot encounters. We are interested in planning algorithms that adapt during a planning cycle by actively inferring the structure of the valid configuration space, and focusing on potentially good solutions. Consider the problem of evaluating edges on a graph to discover a good path. Edges are not alike in value—some are important, others are informative. Important edges have a lot of good paths flowing through them. Informative edges, on being evaluated, affect the likelihood of other neighboring edges being valid. Evaluating edges is expensive, both for robots with complex geometries like robot arms, and for robots with limited onboard computation like UAVs. Until now, we have addressed this challenge via laziness, deferring edge evaluation until absolutely necessary, with the hope that edges turn out to be valid. Our key insight is that we can do more than passive laziness—we can actively probe for information. We draw a novel connection between motion planning and Bayesian active learning. By leveraging existing active learning algorithms, we derive efficient edge evaluation policies which we apply on a spectrum of real world problems. We discuss insights from these preliminary results and potential research questions whose study may prove fruitful for both disciplines.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bohlin, R., Kavraki, L.E.: Path planning using lazy PRM. In: ICRA (2000)
Burns, B., Brock, O.: Sampling-based motion planning using predictive models. In: ICRA (2005)
Canny, J.: The Complexity of Robot Motion Planning. MIT Press, Cambridge (1988)
Chen, Y., Javdani, S., Karbasi, A., Bagnell, D., Srinivasa, S., Krause, A.: Submodular surrogates for value of information. In: AAAI (2015)
Choudhury, S., Javdani, S., Srinivasa, S., Scherer, S.: Near-optimal edge evaluation in explicit generalized binomial graphs, Arxiv (2017)
Choudhury, S., Dellin, C.M., Srinivasa, S.S.: Pareto-optimal search over configuration space beliefs for anytime motion planning. In: IROS (2016)
Choudhury, S., Salzman, O., Choudhury, S., Srinivasa, S.S.: Densification strategies for anytime motion planning over large dense roadmaps. In: ICRA (2017)
Dasgupta, S.: Analysis of a greedy active learning strategy. In: NIPS (2004)
Dellin, C.M., Srinivasa, S.S.: A unifying formalism for shortest path problems with expensive edge evaluations via lazy best-first search over paths with edge selectors. In: ICAPS (2016)
Gammell, J.D., Srinivasa, S.S., Barfoot, T.D.: Batch informed trees: sampling-based optimal planning via heuristically guided search of random geometric graphs. In: ICRA (2015)
Golovin, D., Krause, A.: Adaptive submodularity: theory and applications in active learning and stochastic optimization. J. Artif. Intell. Res. (2011)
Golovin, D., Krause, A., Ray, D.: Near-optimal bayesian active learning with noisy observations. In: NIPS (2010)
Guillory, A., Bilmes, J.A.: Interactive submodular set cover. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10) (2010)
Huh, J., Lee, D.D.: Learning high-dimensional mixture models for fast collision detection in rapidly-exploring random trees. In: ICRA (2016)
Javdani, S., Chen, Y., Karbasi, A., Krause, A., Bagnell, D., Srinivasa, S.: Near optimal bayesian active learning for decision making. In: AISTATS (2014)
Karaman, Sertac, Frazzoli, Emilio: Sampling-based algorithms for optimal motion planning. Int. J. Robot. Res. 30(7), 846–894 (2011)
LaValle, S.M.: Planning Algorithms. Cambridge University Press, Cambridge (2006)
LaValle, S.M., Kuffner Jr, J.J.: Randomized kinodynamic planning. IJRR (2001)
Narayanan, V., Likhachev, M.: Heuristic search on graphs with existence priors for expensive-to-evaluate edges. In: ICAPS (2017)
Nielsen, C.L., Kavraki, L.E.: A 2 level fuzzy prm for manipulation planning. In: IROS (2000)
Osband, I., Russo, D., Van Roy, B.: (More) efficient reinforcement learning via posterior sampling. In: NIPS (2013)
Pan, J., Chitta, S., Manocha, D.: Faster sample-based motion planning using instance-based learning. In: WAFR. Springer (2012)
Ramos, F., Ott, L.: Hilbert maps: scalable continuous occupancy mapping with stochastic gradient descent. IJRR (2016)
Tallavajhula, A., Choudhury, S., Scherer, S., Kelly, A.: List prediction applied to motion planning. In: ICRA (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Choudhury, S., Srinivasa, S.S. (2020). A Bayesian Active Learning Approach to Adaptive Motion Planning. 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_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-28619-4_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-28618-7
Online ISBN: 978-3-030-28619-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)