RESAMPL: A Region-Sensitive Adaptive Motion Planner

Finding high quality paths within a limited time in configuration space is a challenging issue for path planning. Recently, an asymptotically optimal method called fast marching tree (FMT*) has been proposed. This method converges significantly faster than its state-of-the-art counterparts when addressing a wide range of problems. However, FMT* appears unable to solve the narrow passage problem in optimal path planning, since it is based on uniform sampling. Aiming at solving this problem, a novel region-based sampling method integrating global scenario information and local region information is proposed in this paper. First, global information related to configuration space is extracted from an initial sample set obtained via hybrid sampling. Then, local regions are constructed and local region information is captured to make intelligent decisions regarding regions that are difficult and need to be boosted. Finally, the initial sample set is sent to FMT* using a modified locally optimal onestep connection strategy in order to find an initial and feasible solution. If no solution is found and time permits, the guided hybrid sampling will be adopted in order to add more useful samples to the sample set until a solution is found or the time for doing so runs out. Simulation results for six benchmark scenarios validate that our method can achieve significantly better results than other state-of-theart methods when applied in challenging scenarios with narrow passages.

show abstract

“…Our region construction method is related to [30] but differs in two aspects. First, we only consider free samples.…”

Section: Region Constructionmentioning

confidence: 99%

A Region-Specific Hybrid Sampling Method for Optimal Path Planning

Zhong

Liu

2016

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

show abstract

“…There is a class of motion planning techniques called Feature Sensitive Motion Planning [18,20,24,27] that apply a divide-and-conquer approach by breaking up the environment into regions, solving each region, and combining the solutions. Although these techniques do not map C obst these approaches often use information from samples, both valid and invalid to find appropriate regions.…”

Section: Preliminaries and Related Workmentioning

confidence: 99%

Toggle PRM: A Coordinated Mapping of C-Free and C-Obstacle in Arbitrary Dimension

Denny

Amatoo

2013

Springer Tracts in Advanced Robotics

View full text Add to dashboard Cite

Motion planning has received much attention over the past 40 years. More than 15 years have passed since the introduction of the successful sampling-based approach known as the Probabilistic RoadMap Method (PRM). PRM and its many variants have demonstrated great success for some high-dimensional problems, but they all have some level of difficulty in the presence of narrow passages. Recently, an approach called Toggle PRM has been introduced whose performance does not degrade for 2-dimensional problems with narrow passages. In Toggle PRM, a simultaneous, coordinated mapping of both C f ree and C obst is performed and every connection attempt augments one of the maps -either validating an edge in the current space or adding a configuration 'witnessing' the connection failure to the other space. In this paper, we generalize Toggle PRM to d-dimensions and show that the benefits of mapping both C f ree and C obst continue to hold in higher dimensions. In particular, we introduce a new narrow passage characterization, α-ε-separable narrow passages, which describes the types of passages that can be successfully mapped by Toggle PRM. Intuitively, α-ε-separable narrow passages are arbitrarily narrow regions of C f ree that separate regions of C obst , at least locally, such as hallways in an office building. We experimentally compare Toggle PRM with other methods in a variety of scenarios with different types of narrow passages and robots with up to 16 DOF.

show abstract

“…Recently, several hybrid motion planners have been proposed [17], [18], [19], [20]. All these meta-planners focus on combining different PRMs using machine learning or statistics collected during sampling to discover when and where to apply certain sampling strategies.…”

Section: B Hybrid Motion Plannersmentioning

confidence: 99%

Hybrid Motion Planning Using Minkowski Sums

Lien

2008

Robotics: Science and Systems IV

View full text Add to dashboard Cite

Abstract-Probabilistic and deterministic planners are two major approximate-based frameworks for solving motion planning problems. Both approaches have their own advantages and disadvantages. In this work, we provide an investigation to the following question: Is there a planner that can take the advantages from both probabilistic and deterministic planners? Our strategy to achieve this goal is to use the point-based Minkowski sum of the robot and the obstacles in workspace. Our experimental results show that our new method, called M-sum planner, which uses the geometric properties of Minkowski sum to solve motion planning problems, provides advantages over the existing probabilistic or deterministic planners. In particular, Msum planner is significantly more efficient than the Probabilistic Roadmap Methods (PRMs) and its variants for problems that can be solved by reusing configurations.

show abstract

RESAMPL: A Region-Sensitive Adaptive Motion Planner

Cited by 56 publications

References 16 publications

A Region-Specific Hybrid Sampling Method for Optimal Path Planning

A Region-Specific Hybrid Sampling Method for Optimal Path Planning

Toggle PRM: A Coordinated Mapping of C-Free and C-Obstacle in Arbitrary Dimension

Hybrid Motion Planning Using Minkowski Sums

Contact Info

Product

Resources

About