Anytime solution optimization for sampling-based motion planning

Luna, Ryan; Sucan, Ioan A.; Moll, Mark; Kavraki, Lydia E.

doi:10.1109/icra.2013.6631301

Cited by 67 publications

(42 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, they tend to produce jerky paths that are far from optimal. Some hybrid approaches have combined samplingbased planning with local optimization to produce better paths [19,25].…”

Section: Background and Related Workmentioning

confidence: 99%

Asymptotically Optimal Planning by Feasible Kinodynamic Planning in a State–Cost Space

Hauser

Zhou

2016

IEEE Trans. Robot.

View full text Add to dashboard Cite

Abstract-This paper presents an equivalence between feasible kinodynamic planning and optimal kinodynamic planning, in that any optimal planning problem can be transformed into a series of feasible planning problems in a state-cost space whose solutions approach the optimum. This transformation gives rise to a meta-algorithm that produces an asymptotically optimal planner, given any feasible kinodynamic planner as a subroutine. The meta-algorithm is proven to be asymptotically optimal, and a formula is derived relating expected running time and solution suboptimality. It is directly applicable to a wide range of optimal planning problems because it does not resort to the use of steering functions or numerical boundary-value problem solvers. On a set of benchmark problems, it is demonstrated to perform, using the EST and RRT algorithms as subroutines, at a superior or comparable level to related planners.

show abstract

“…However, they tend to produce jerky paths that are far from optimal. Some hybrid approaches have combined samplingbased planning with local optimization to produce better paths [19,25].…”

Section: Background and Related Workmentioning

confidence: 99%

Asymptotically Optimal Planning by Feasible Kinodynamic Planning in a State–Cost Space

Hauser

Zhou

2016

IEEE Trans. Robot.

View full text Add to dashboard Cite

show abstract

“…Asymptotically optimal sampling-based planners avoid the local minima inherent in potential field methods [25], and can avoid the suboptimal plans resulting from sampling-based planners which are merely probabilistically complete (e.g., RRT [22]). Because we rapidly replan [26], [27] when landmarks move, it is also useful to be able to access the best known plan at any given time [28]. For these reasons, we use a variation on a probabilistic roadmap (PRM), but do not allow it to grow arbitrarily large.…”

Section: Related Workmentioning

confidence: 99%

Asymptotically Optimal Motion Planning for Tasks Using Learned Virtual Landmarks

Bowen

Alterovitz

2016

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Utilizing appropriate landmarks in the environment is often critical to planning a robot's motion for a given task. We propose a method to automatically learn task-relevant landmarks, and incorporate the method into an asymptotically optimal motion planner that is informed by a set of human-guided demonstrations. Our method learns from kinesthetic demonstrations a task model that is parameterized by the poses of virtual landmarks. The approach models a task using multivariate Gaussian distributions in a feature space that includes the robot's configurations and the relative positions of landmarks in the environment. The method automatically learns virtual landmarks that are based on linear combinations or projections of sensed landmarks whose pose is identified using the robot's kinematic model and vision sensors. To compute motion plans for the task in new environments, we parameterize the learned task model using the virtual landmark poses and compute paths that maximally adhere to the learned task model while avoiding obstacles. We experimentally evaluate our approach on two manipulation tasks using the Baxter robot in an environment with obstacles.Index Terms-Motion and path planning, probability and statistical methods.

show abstract

“…Basic techniques combine the results of completed searches [37], [38]. This allows for a wide variety of methods as inputs, including both global and local techniques, but keeps each search independent.…”

Section: Hybridizationmentioning

confidence: 99%

Regionally accelerated batch informed trees (RABIT*): A framework to integrate local information into optimal path planning

Choudhury

Gammell

Barfoot

et al. 2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Sampling-based optimal planners, such as RRT*, almost-surely converge asymptotically to the optimal solution, but have provably slow convergence rates in high dimensions. This is because their commitment to finding the global optimum compels them to prioritize exploration of the entire problem domain even as its size grows exponentially. Optimization techniques, such as CHOMP, have fast convergence on these problems but only to local optima. This is because they are exploitative, prioritizing the immediate improvement of a path even though this may not find the global optimum of nonconvex cost functions.In this paper, we present a hybrid technique that integrates the benefits of both methods into a single search. A key insight is that applying local optimization to a subset of edges likely to improve the solution avoids the prohibitive cost of optimizing every edge in a global search. This is made possible by Batch Informed Trees (BIT*), an informed global technique that orders its search by potential solution quality. In our algorithm, Regionally Accelerated BIT* (RABIT*), we extend BIT* by using optimization to exploit local domain information and find alternative connections for edges in collision and accelerate the search. This improves search performance in problems with difficult-to-sample homotopy classes (e.g., narrow passages) while maintaining almost-sure asymptotic convergence to the global optimum.Our experiments on simulated random worlds and real data from an autonomous helicopter show that on certain difficult problems, RABIT* converges 1.8 times faster than BIT*. Qualitatively, in problems with difficult-to-sample homotopy classes, we show that RABIT* is able to efficiently transform paths to avoid obstacles.

show abstract

Anytime solution optimization for sampling-based motion planning

Cited by 67 publications

References 31 publications

Asymptotically Optimal Planning by Feasible Kinodynamic Planning in a State–Cost Space

Asymptotically Optimal Planning by Feasible Kinodynamic Planning in a State–Cost Space

Asymptotically Optimal Motion Planning for Tasks Using Learned Virtual Landmarks

Regionally accelerated batch informed trees (RABIT*): A framework to integrate local information into optimal path planning

Contact Info

Product

Resources

About