A Voronoi-based hybrid motion planner

Foskey, Mark; Garber, Maxim; Lin, Ming C.; Manocha, Dinesh

doi:10.1109/iros.2001.973336

Cited by 78 publications

(68 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, these methods are mainly limited to volumetric objects and may not be able to handle self-collisions well. Voronoi regions of workspace can be used to generate samples in narrow passages [7], [19].…”

Section: B Handling Narrow Passages For Articulated Modelsmentioning

confidence: 99%

Retraction-based RRT planner for articulated models

Pan

Zhang

Manocha

2010

2010 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-We present a new retraction algorithm for high DOF articulated models and use our algorithm to improve the performance of RRT planners in narrow passages. The retraction step is formulated as a constrained optimization problem and performs iterative refinement on the boundary of CObstacle space. We also combine the retraction algorithm with decomposition planners to handle very high DOF articulated models. The performance of our approach is analyzed using Voronoi diagrams and we show that our retraction algorithm provides a good approximation to the ideal RRT-extension in constrained environments. We have implemented our algorithm and tested its performance on robots with more than 40 DOFs in complex environments. In practice, we observe significant performance (2-80X) improvement over prior RRT planners on challenging scenarios with narrow passages.

show abstract

Section: B Handling Narrow Passages For Articulated Modelsmentioning

confidence: 99%

Retraction-based RRT planner for articulated models

Pan

Zhang

Manocha

2010

2010 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

show abstract

“…They are frequently used for dynamic simulation [1,26] and robot motion planning [4,14,12]. But due to their high computation complexity, most prior interactive CCD algorithms are limited to rigid models [16] or articulated models [17,26].…”

Section: Continuous Collision Detection (Ccd)mentioning

confidence: 99%

Adjacency-based culling for continuous collision detection

2008

View full text Add to dashboard Cite

We present an efficient approach to reduce the number of elementary tests for continuous collision detection between rigid and deformable models. Our algorithm exploits the connectivity information and uses the adjacency relationships between the triangles to perform hierarchical culling. This can be combined with table-based lookups to eliminate duplicate elementary tests. In practice, our approach can reduce the number of elementary tests by two orders of magnitude. We demonstrate the performance of our algorithm on various challenging rigid body and deformable simulations.

show abstract

“…By retracting colliding samples, the probability of sampling narrow passages is increased. In [10], the medial axis of the workspace is used to bias sampling in the C-space. The workspace medial axis is quickly computed using graphics hardware.…”

Section: B Overcoming the Narrow Passage Problemmentioning

confidence: 99%

“…To overcome this, much work has been done to design new sampling techniques to increase the probability of sampling these narrow passages. Techniques include biasing sampling around obstacles [2], [6], [13], [19], biasing sampling toward the medial axis of the free space [23], [10], biasing sampling toward unknown/uncertain areas [8], [7], etc.…”

Section: Introductionmentioning

confidence: 99%

Biasing Samplers to Improve Motion Planning Performance

Thomas

Morales

Tang

et al. 2007

Proceedings 2007 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-With the success of randomized sampling-based motion planners such as Probabilistic Roadmap Methods, much work has been done to design new sampling techniques and distributions. To date, there is no sampling technique that outperforms all other techniques for all motion planning problems. Instead, each proposed technique has different strengths and weaknesses. However, little work has been done to combine these techniques to create new distributions. In this paper, we propose to bias one sampling distribution with another such that the resulting distribution out-performs either of its parent distributions. We present a general framework for biasing samplers that is easily extendable to new distributions and can handle an arbitrary number of parent distributions by chaining them together. Our experimental results show that by combining distributions, we can out-perform existing planners. Our results also indicate that not one single distribution combination performs the best in all problems, and we identify which perform better for the specific application domains studied.

show abstract

A Voronoi-based hybrid motion planner

Cited by 78 publications

References 13 publications

Retraction-based RRT planner for articulated models

Retraction-based RRT planner for articulated models

Adjacency-based culling for continuous collision detection

Biasing Samplers to Improve Motion Planning Performance

Contact Info

Product

Resources

About