Dynamic-Domain RRTs: Efficient Exploration by Controlling the Sampling Domain

@article{Yershova2005DynamicDomainRE,
  title={Dynamic-Domain RRTs: Efficient Exploration by Controlling the Sampling Domain},
  author={Anna Yershova and L{\'e}onard Jaillet and Thierry Sim{\'e}on and Steven M. LaValle},
  journal={Proceedings of the 2005 IEEE International Conference on Robotics and Automation},
  year={2005},
  pages={3856-3861}
}
  • A. Yershova, L. Jaillet, S. LaValle
  • Published 18 April 2005
  • Computer Science
  • Proceedings of the 2005 IEEE International Conference on Robotics and Automation
Sampling-based planners have solved difficult problems in many applications of motion planning in recent years. In particular, techniques based on the Rapidly-exploring Random Trees (RRTs) have generated highly successful single-query planners. Even though RRTs work well on many problems, they have weaknesses which cause them to explore slowly when the sampling domain is not well adapted to the problem. In this paper we characterize these issues and propose a general framework for minimizing… 
Adaptive tuning of the sampling domain for dynamic-domain RRTs
TLDR
A new variant of the dynamic-domain RRT, which iteratively adapts the sampling domain for the Voronoi region of each node during the search process, which allows automatic tuning of the parameter and significantly increases the robustness of the algorithm.
Learning Implicit Sampling Distributions for Motion Planning
TLDR
A policy-search based method is presented as an adaptive way to learn implicit sampling distributions for different environments that utilizes information from past searches in similar environments to generate better distributions in novel environments, thus reducing overall computational cost.
Sampling heuristics for optimal motion planning in high dimensions
TLDR
A sampling-based motion planner that improves the performance of the probabilistically optimal RRT* planning algorithm and incorporates an existing bi-directional approach to search which decreases the time to find an initial path.
Single-Query Motion Planning with Utility-Guided Random Trees
  • B. Burns, O. Brock
  • Computer Science
    Proceedings 2007 IEEE International Conference on Robotics and Automation
  • 2007
TLDR
A utility-guided algorithm is presented for the online adaptation of the random tree expansion strategy that guides expansion towards regions of maximum utility based on local characteristics of state space.
Costmap planning in high dimensional configuration spaces
  • R. Iehl, J. Cortes, T. Siméon
  • Computer Science
    2012 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)
  • 2012
TLDR
This paper proposes to introduce ideas from the ML-RRT algorithm, which can efficiently solve high-dimensional path planning problems by relying on a hierarchical partitioning of the configuration space parameters.
Learned Sampling Distributions for Efficient Planning in Hybrid Geometric and Object-Level Representations
TLDR
This work shows that learning a sampling distribution that incorporates both geometric information and explicit, object-level semantics for sampling-based planners enables efficient planning at longer horizons in partially-known environments.
Metrics for Efficient Environment Exploration in Robot Motion Planning
Although current state-of-the-art planners utilize properties of the environment such as the workspace topology to guide exploration, more efficient methods and metrics that bias exploration based on
Toward Optimal Configuration Space Sampling
TLDR
A new approach to multi-query samplingbased motion planning is proposed, which exploits information obtained from earlier exploration and its current state to guide exploration and significantly decreases the runtime required for motion planning.
Sampling-based algorithms for optimal path planning problems
TLDR
This dissertation proposes an incremental sampling-based algorithm that is provably correct and probabilistically complete and an incremental local model-checking algorithm for the deterministic μ-calculus, both of which guarantee asymptotic optimality without sacrificing computational efficiency.
Balancing Exploration and Exploitation in Sampling-Based Motion Planning
TLDR
The exploring/exploiting tree (EET) algorithm for motion planning deliberately trades probabilistic completeness for computational efficiency and enables the EET planner to outperform state-of-the-art sampling-based planners by up to three orders of magnitude.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 74 REFERENCES
A Single-Query Bi-Directional Probabilistic Roadmap Planner with Lazy Collision Checking
TLDR
Experimental results show that this combination of techniques drastically reduces planning times, making it possible to handle difficult problems, including multi-robot problems in geometrically complex environments.
RRT-connect: An efficient approach to single-query path planning
  • J. Kuffner, S. LaValle
  • Computer Science
    Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065)
  • 2000
A simple and efficient randomized algorithm is presented for solving single-query path planning problems in high-dimensional configuration spaces. The method works by incrementally building two
A framework for using the workspace medial axis in PRM planners
  • Christopher Holleman, L. Kavraki
  • Materials Science
    Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065)
  • 2000
TLDR
This work examines the medial axis as a skeleton, including a method to compute an approximation to it, and forms a heuristic for finding difficult configurations using the medialaxis, and demonstrates its effectiveness in a planner for rigid objects in a 3D workspace.
The Gaussian sampling strategy for probabilistic roadmap planners
TLDR
This paper presents a new, simple sampling strategy, which it is called the Gaussian sampler, that gives a much better coverage of the difficult parts of the free configuration space.
MAPRM: a probabilistic roadmap planner with sampling on the medial axis of the free space
TLDR
A new method of sampling the configuration space in which randomly generated configurations are retracted onto the medial axis of the free space is proposed, and it is shown that sampling and retracting in this manner increases the number of nodes found in small volume corridors in a way that is independent of the volume of the corridor and depends only on the characteristics of the obstacles bounding it.
Motion planning a aerial robot using rapidly-exploring random trees with dynamic constraints
  • Jongwoo Kim, J. Ostrowski
  • Engineering
    2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422)
  • 2003
TLDR
A rapidly-exploring random tree (RRT) is used for the motion planning of a blimp system, and some techniques for improving the performance of the planner are proposed.
Incrementally reducing dispersion by increasing Voronoi bias in RRTs
  • S. R. Lindemann, S. LaValle
  • Computer Science
    IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004
  • 2004
TLDR
Initial results show that the new RRT-like planners based on exact Voronoi diagram computation are advantageous compared to existing RRTs, especially with respect to the number of collision checks and nodes in the search tree.
Kinodynamic motion planning: connecting exploration trees using trajectory optimization Methods
TLDR
This paper proposes a solution to cope with the complexity issue of motion planning for complex dynamic systems for which no steering method is known by running a tree exploration method with a big neighborhood and locally modifying the trajectory to make it reach exactly the goal.
Manipulation Planning with Probabilistic Roadmaps
TLDR
A general manipulation planning approach capable of addressing continuous sets for modeling both the possible grasps and the stable placements of the movable object, rather than discrete sets generally assumed by the previous approaches.
Path planning using lazy PRM
  • Robert Bohlin, L. Kavraki
  • Computer Science
    Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065)
  • 2000
TLDR
The overall theme of the algorithm, called Lazy PRM, is to minimize the number of collision checks performed during planning and hence minimize the running time of the planner.
...
1
2
3
4
5
...