Generalizing Informed Sampling for Asymptotically Optimal Sampling-based Kinodynamic Planning via Markov Chain Monte Carlo

Yi, Daqing; Thakker, Rohan; Gulino, Cole; Salzman, Oren; Srinivasa, Siddhartha S.

doi:10.48550/arxiv.1710.06092

Cited by 3 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Samples may be rejected if they are guaranteed to not improve the current trajectory (Akgun & Stilman 2011), but this leads to a large fraction of samples being rejected in high dimensional problems (Kunz et al 2016). Kunz et al (2016) and Yi et al (2017) improve the efficiency of this approach using hierarchical rejection sampling and Markov Chain Monte Carlo methods. Generally, informed sampling approaches aim to leverage the current best path to improve sampling quality.…”

Section: Related Workmentioning

confidence: 99%

Learning Sampling Distributions for Robot Motion Planning

Ichter

Harrison

Pavone

2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

287

206

View full text Add to dashboard Cite

A defining feature of sampling-based motion planning is the reliance on an implicit representation of the state space, which is enabled by a set of probing samples. Traditionally, these samples are drawn either probabilistically or deterministically to uniformly cover the state space. Yet, the motion of many robotic systems is often restricted to "small" regions of the state space, due to, for example, differential constraints or collision-avoidance constraints. To accelerate the planning process, it is thus desirable to devise non-uniform sampling strategies that favor sampling in those regions where an optimal solution might lie. This paper proposes a methodology for non-uniform sampling, whereby a sampling distribution is learned from demonstrations, and then used to bias sampling. The sampling distribution is computed through a conditional variational autoencoder, allowing sample generation from the latent space conditioned on the specific planning problem. This methodology is general, can be used in combination with any samplingbased planner, and can effectively exploit the underlying structure of a planning problem while maintaining the theoretical guarantees of sampling-based approaches. Specifically, on several planning problems, the proposed methodology is shown to effectively learn representations for the relevant regions of the state space, resulting in an order of magnitude improvement in terms of success rate and convergence to the optimal cost. * These authors contributed equally to this work.This work was originally presented at the 2018 IEEE International Conference on Robotics and Automation (ICRA). This extended version includes new numerical experiments demonstrating generalization, iterative retraining of the generative model, and multirobot planning experiments.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning Sampling Distributions for Robot Motion Planning

Ichter

Harrison

Pavone

2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

287

206

View full text Add to dashboard Cite

show abstract

“…Gammell et al [18] introduced Informed RRT* which improves RRT* performance by restricting samples to an ellipsoid that contains all samples that could possible improve the path length after an initial path is found. Kunz et al [19] and Yi et al [20] improve the informed sampling technique. This technique does not improve the speed at which the first path is found.…”

Section: Related Workmentioning

confidence: 99%

Learning Implicit Sampling Distributions for Motion Planning

Zhang

Huh

Lee

2018

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Sampling-based motion planners have experienced much success due to their ability to efficiently and evenly explore the state space. However, for many tasks, it may be more efficient to not uniformly explore the state space, especially when there is prior information about its structure. Previous methods have attempted to modify the sampling distribution using hand selected heuristics that can work well for specific environments but not universally. In this paper, a policysearch based method is presented as an adaptive way to learn implicit sampling distributions for different environments. It utilizes information from past searches in similar environments to generate better distributions in novel environments, thus reducing overall computational cost. Our method can be incorporated with a variety of sampling-based planners to improve performance. Our approach is validated on a number of tasks, including a 7DOF robot arm, showing marked improvement in number of collision checks as well as number of nodes expanded compared with baseline methods.

show abstract