Biasing Samplers to Improve Motion Planning Performance

Thomas, Shawna; Morales, Marco; Tang, Xinyu; Amato, Nancy M.

doi:10.1109/robot.2007.363556

Cited by 19 publications

(11 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, Thomas et al (2007) observe that many of the above biased sampling schemes can be compounded. They show that through a combination of biases, PRM planners can realize performance superior to any individual biased sampling method.…”

Section: Sampling Strategies With Fixed Biasmentioning

confidence: 99%

Real-time informed path sampling for motion planning search

Knepper

Mason

2012

The International Journal of Robotics Research

View full text Add to dashboard Cite

Mobile robot motions often originate from an uninformed path sampling process such as random or low-dispersion sampling. We demonstrate an alternative approach to path sampling that closes the loop on the expensive collision-testing process. Although all necessary information for collision-testing a path is known to the planner, that information is typically stored in a relatively unavailable form in a costmap or obstacle map. By summarizing the most salient data in a more accessible form, our process delivers a denser sampling of the free path space per unit time than open-loop sampling techniques. We obtain this result by probabilistically modeling-in real time and with minimal information-the locations of obstacles and free space, based on collision-test results. We present CALM, the combined adaptive locality model, along with an algorithm to bias path sampling based on the model's predictions. We provide experimental results in simulation for motion planning on mobile robots, demonstrating up to a 330% increase in paths surviving collision test.

show abstract

Section: Sampling Strategies With Fixed Biasmentioning

confidence: 99%

Real-time informed path sampling for motion planning search

Knepper

Mason

2012

The International Journal of Robotics Research

View full text Add to dashboard Cite

show abstract

“…an underlying distribution, their strengths can be combined by setting up chains of dependent samplers [9].…”

Section: Introductionmentioning

confidence: 99%

Adaptive workspace biasing for sampling-based planners

Zucker

Kuffner

Bagnell

2008

2008 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-The widespread success of sampling-based planning algorithms stems from their ability to rapidly discover the connectivity of a configuration space. Past research has found that non-uniform sampling in the configuration space can significantly outperform uniform sampling; one important strategy is to bias the sampling distribution based on features present in the underlying workspace. In this paper, we unite several previous approaches to workspace biasing into a general framework for automatically discovering useful sampling distributions. We present a novel algorithm, based on the REINFORCE family of stochastic policy gradient algorithms, which automatically discovers a locally-optimal weighting of workspace features to produce a distribution which performs well for a given class of sampling-based motion planning queries. We present as well a novel set of workspace features that our adaptive algorithm can leverage for improved configuration space sampling. Experimental results show our algorithm to be effective across a variety of robotic platforms and highdimensional configuration spaces.

show abstract

“…The key issue is that sampling a high dimensional space densely enough is computationally infeasible. Other studies in this direction include obstacle based sampling (Thomas et al, 2007;Rodriguez et al, 2006), Gaussian sampling (Boor et al, 1999) and other approaches.…”

Section: Sampling Based Motion Planningmentioning

confidence: 99%

Motion planning and reactive control on learnt skill manifolds

Havoutis

Ramamoorthy

2013

The International Journal of Robotics Research

View full text Add to dashboard Cite

We address the problem of encoding and executing skills, i.e. motion tasks involving a combination of specifications regarding constraints and variability. We take an approach that is model-free in the sense that we do not assume an explicit and complete analytical specification of the task – which can be hard to obtain for many realistic robot systems. Instead, we learn an encoding of the skill from observations of an initial set of sample trajectories. This is achieved by encoding trajectories in a skill manifold which is learnt from data and generalizes in the sense that all trajectories on the manifold satisfy the constraints and allowable variability in the demonstrated samples. In new instances of the trajectory-generation problem, we restrict attention to geodesic trajectories on the learnt skill manifold, making computation more tractable. This procedure is also extended to accommodate dynamic obstacles and constraints, and to dynamically react against unexpected perturbations, enabling a form of model-free feedback control with respect to an incompletely modelled skill. We present experiments to validate this framework using various robotic systems – ranging from a three-link arm to a small humanoid robot – demonstrating significant computational improvements without loss of accuracy. Finally, we present a comparative evaluation of our framework against a state-of-the-art imitation-learning method.

show abstract

Biasing Samplers to Improve Motion Planning Performance

Cited by 19 publications

References 20 publications

Real-time informed path sampling for motion planning search

Real-time informed path sampling for motion planning search

Adaptive workspace biasing for sampling-based planners

Motion planning and reactive control on learnt skill manifolds

Contact Info

Product

Resources

About