scholarly journals FFRob: Leveraging symbolic planning for efficient task and motion planning

2017 ◽  
Vol 37 (1) ◽  
pp. 104-136 ◽  
Author(s):  
Caelan Reed Garrett ◽  
Tomás Lozano-Pérez ◽  
Leslie Pack Kaelbling
Keyword(s):  
Motion Planning ◽  
Heuristic Search ◽  
General Purpose ◽  
Configuration Spaces ◽  
Mobile Manipulation ◽  
Extended Action ◽  
Geometric Search ◽  
Problem Instances ◽  
Hybrid Configuration ◽  
Planning Problems

Mobile manipulation problems involving many objects are challenging to solve due to the high dimensionality and multi-modality of their hybrid configuration spaces. Planners that perform a purely geometric search are prohibitively slow for solving these problems because they are unable to factor the configuration space. Symbolic task planners can efficiently construct plans involving many variables but cannot represent the geometric and kinematic constraints required in manipulation. We present the FFRob algorithm for solving task and motion planning problems. First, we introduce extended action specification (EAS) as a general purpose planning representation that supports arbitrary predicates as conditions. We adapt existing heuristic search ideas for solving strips planning problems, particularly delete-relaxations, to solve EAS problem instances. We then apply the EAS representation and planners to manipulation problems resulting in FFRob. FFRob iteratively discretizes task and motion planning problems using batch sampling of manipulation primitives and a multi-query roadmap structure that can be conditionalized to evaluate reachability under different placements of movable objects. This structure enables the EAS planner to efficiently compute heuristics that incorporate geometric and kinematic planning constraints to give a tight estimate of the distance to the goal. Additionally, we show FFRob is probabilistically complete and has a finite expected runtime. Finally, we empirically demonstrate FFRob’s effectiveness on complex and diverse task and motion planning tasks including rearrangement planning and navigation among movable objects.

scholarly journals Sampling-based methods for factored task and motion planning

2018 ◽  
Vol 37 (13-14) ◽  
pp. 1796-1825 ◽  
Author(s):  
Caelan Reed Garrett ◽  
Tomás Lozano-Pérez ◽  
Leslie Pack Kaelbling
Keyword(s):  
Motion Planning ◽  
General Purpose ◽  
State Transitions ◽  
Transition Systems ◽  
Hybrid State ◽  
Time Planning ◽  
And Control ◽  
Planning Problems ◽  
Domain Independent

This paper presents a general-purpose formulation of a large class of discrete-time planning problems, with hybrid state and control-spaces, as factored transition systems. Factoring allows state transitions to be described as the intersection of several constraints each affecting a subset of the state and control variables. Robotic manipulation problems with many movable objects involve constraints that only affect several variables at a time and therefore exhibit large amounts of factoring. We develop a theoretical framework for solving factored transition systems with sampling-based algorithms. The framework characterizes conditions on the submanifold in which solutions lie, leading to a characterization of robust feasibility that incorporates dimensionality-reducing constraints. It then connects those conditions to corresponding conditional samplers that can be composed to produce values on this submanifold. We present two domain-independent, probabilistically complete planning algorithms that take, as input, a set of conditional samplers. We demonstrate the empirical efficiency of these algorithms on a set of challenging task and motion planning problems involving picking, placing, and pushing.

On Property Analysis of Optimal Solutions for Two Typical Motion Planning Problems

2021 ◽  
Author(s):  
Zixin Feng ◽  
Wenchao Xue ◽  
Hongsheng Qi ◽  
Zhe Jiang
Keyword(s):  
Motion Planning ◽  
Optimal Solutions ◽  
Property Analysis ◽  
Planning Problems

scholarly journals Maximizing the Coverage of Roadmap Graph for Optimal Motion Planning

Complexity ◽  
2018 ◽  
Vol 2018 ◽  
pp. 1-23 ◽  
Author(s):  
Jae-Han Park ◽  
Tae-Woong Yoon
Keyword(s):  
Motion Planning ◽  
Industry 4.0 ◽  
Industrial Robot ◽  
Efficient Solutions ◽  
Industrial Robots ◽  
Optimal Motion ◽  
Optimal Motion Planning ◽  
Planning Problems ◽  
Complex Planning ◽  
Satisfactory Quality

Automated motion-planning technologies for industrial robots are critical for their application to Industry 4.0. Various sampling-based methods have been studied to generate the collision-free motion of articulated industrial robots. Such sampling-based methods provide efficient solutions to complex planning problems, but their limitations hinder the attainment of optimal results. This paper considers a method to obtain the optimal results in the roadmap algorithm that is representative of the sampling-based method. We define the coverage of a graph as a performance index of its optimality as constructed by a sampling-based algorithm and propose an optimization algorithm that can maximize graph coverage in the configuration space. The proposed method was applied to the model of an industrial robot, and the results of the simulation confirm that the roadmap graph obtained by the proposed algorithm can generate results of satisfactory quality in path-finding tests under various conditions.

Tangent bundle RRT: A randomized algorithm for constrained motion planning

Robotica ◽  
2014 ◽  
Vol 34 (1) ◽  
pp. 202-225 ◽  
Author(s):  
Beobkyoon Kim ◽  
Terry Taewoong Um ◽  
Chansu Suh ◽  
F. C. Park
Keyword(s):  
Motion Planning ◽  
Configuration Space ◽  
Tangent Bundle ◽  
Numerical Experiments ◽  
Randomized Algorithm ◽  
Random Trees ◽  
Constrained Motion ◽  
Wide Range ◽  
Random Node ◽  
Planning Problems

SUMMARYThe Tangent Bundle Rapidly Exploring Random Tree (TB-RRT) is an algorithm for planning robot motions on curved configuration space manifolds, in which the key idea is to construct random trees not on the manifold itself, but on tangent bundle approximations to the manifold. Curvature-based methods are developed for constructing tangent bundle approximations, and procedures for random node generation and bidirectional tree extension are developed that significantly reduce the number of projections to the manifold. Extensive numerical experiments for a wide range of planning problems demonstrate the computational advantages of the TB-RRT algorithm over existing constrained path planning algorithms.

Sign in / Sign up

Export Citation Format

Share Document