Learning to Retrieve Relevant Experiences for Motion Planning

Chamzas, Constantinos; Cullen, Aedan; Shrivastava, Anshumali; Kavraki, Lydia E.

doi:10.1109/icra46639.2022.9812076

Cited by 7 publications

(4 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ichter et al [15] train a conditional variational autoencoder (CVAE) to generate not only domain-conditioned but also problemconditioned samples. Chamzas et al [16], [17] demonstrate that learning primitive distributions associated with obstacle pairs is effective.…”

Section: Other Motion Planning Methods With Learningmentioning

confidence: 99%

“…The trajectory optimization problem is constructed by direct transcription [33] with N = 200 discretization points with time step ∆t. The cost function is the sum of squared control input: 2 and the constraints are given by ( 12)- (17).…”

Section: B Task 1: Kinodynamic Planning For Double Integratormentioning

confidence: 99%

“…Therefore, the dimension of P-space is n p = 10. The motion planning problem is defined as finding For NNLib, the library size is varied as 2 i for i ∈ (4,6,8,10,12,14,16,17,18,19,20), where 2 20 = 1, 048, 576. The corresponding library construction time to achieve each specific library size is calculated from the logging results.…”

Section: B Task 1: Kinodynamic Planning For Double Integratormentioning

confidence: 99%

See 2 more Smart Citations

Classifier-Aided Maximization of Feasible- Error-Region for Robust Manipulation Learning

Ishida

Okada

Inaba

2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Library-based methods are known to be very effective for fast motion planning by adapting an experience retrieved from a precomputed library. This article presents CoverLib, a principled approach for constructing and utilizing such a library. CoverLib iteratively adds an experience-classifier-pair to the library, where each classifier corresponds to an adaptable region of the experience within the problem space. This iterative process is an active procedure, as it selects the next experience based on its ability to effectively cover the uncovered region. During the query phase, these classifiers are utilized to select an experience that is expected to be adaptable for a given problem. Experimental results demonstrate that CoverLib effectively mitigates the trade-off between plannability and speed observed in global (e.g. sampling-based) and local (e.g. optimization-based) methods. As a result, it achieves both fast planning and high success rates over the problem domain. Moreover, due to its adaptationalgorithm-agnostic nature, CoverLib seamlessly integrates with various adaptation methods, including nonlinear programmingbased and sampling-based algorithms.

show abstract

Section: Other Motion Planning Methods With Learningmentioning

confidence: 99%

Section: B Task 1: Kinodynamic Planning For Double Integratormentioning

confidence: 99%

Section: B Task 1: Kinodynamic Planning For Double Integratormentioning

confidence: 99%

See 1 more Smart Citation

Classifier-Aided Maximization of Feasible- Error-Region for Robust Manipulation Learning

Ishida

Okada

Inaba

2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…This method solves motion queries by retrieving similar primitives from the database and combining their local samplers. A follow-up work, FIRE (Chamzas et al, 2022) extracts local representations of various planning problems to learn the similarity function over them.…”

Section: Paths and Parameter Selectionmentioning

confidence: 99%

A Survey on the Integration of Machine Learning with Sampling-based Motion Planning

et al. 2022

View full text Add to dashboard Cite

Sampling-based methods are widely adopted solutions for robot motion planning. The methods are straightforward to implement, effective in practice for many robotic systems. It is often possible to prove that they have desirable properties, such as probabilistic completeness and asymptotic optimality. Nevertheless, they still face challenges as the complexity of the underlying planning problem increases, especially under tight computation time constraints, which impact the quality of returned solutions or given inaccurate models. This has motivated machine learning to improve the computational efficiency and applicability of Sampling-Based Motion Planners (SBMPs). This survey reviews such integrative efforts and aims to provide a classification of the alternative directions that have been explored in the literature. It first discusses how learning has been used to enhance key components of SBMPs, such as node sampling, collision detection, distance or nearest neighbor computation, local

show abstract

Efficient Task Planning Using Abstract Skills and Dynamic Road Map Matching

Elimelech

Kavraki

Vardi

2023

Springer Proceedings in Advanced Robotics

View full text Add to dashboard Cite

Multi-Robot Task Planning (MR-TP) is the search for a discrete-action plan a team of robots should take to complete a task. The complexity of such problems scales exponentially with the number of robots and task complexity, making them challenging for online solution. To accelerate MR-TP over a system's lifetime, this work looks at combining two recent advances: (i) Decomposable State Space Hypergraph (DaSH), a novel hypergraph-based framework to efficiently model and solve MR-TP problems; and (ii) learning-by-abstraction, a technique that enables automatic extraction of generalizable planning strategies from individual planning experiences for later reuse. Specifically, we wish to extend this strategy-learning technique, originally designed for single-robot planning, to benefit multi-robot planning using hypergraph-based MR-TP.

show abstract

Learning to Retrieve Relevant Experiences for Motion Planning

Cited by 7 publications

References 47 publications

Classifier-Aided Maximization of Feasible- Error-Region for Robust Manipulation Learning

Classifier-Aided Maximization of Feasible- Error-Region for Robust Manipulation Learning

A Survey on the Integration of Machine Learning with Sampling-based Motion Planning

Efficient Task Planning Using Abstract Skills and Dynamic Road Map Matching

Contact Info

Product

Resources

About