Planning of graspless manipulation based on rapidly-exploring random trees

Miyazawa, Kanae; Maeda, Yusuke; Arai, Tamio

doi:10.1109/isatp.2005.1511442

Cited by 19 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the purpose of this comparison, primitives must be generated at the same input resolution, using (1) and (2). Equation (1) shows the number of traditional primitives (P trad ) in terms of m and the dimension n of the input vector that must be generated to attain the same input resolution as the optimized method.…”

Section: Comparing the Optimized And Traditional Rrt Extend Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Improving RRT's Efficiency through Motion Primitives Generation Optimization

Vieira

Grassi

2014

2014 Joint Conference on Robotics: SBR-LARS Robotics Symposium and Robocontrol

View full text Add to dashboard Cite

Rapidly-exploring Random Tree (RRT) algorithm has been used for motion planning in numerous and diverse robotic applications. For applications which demands higher motion resolution, the computational cost increases together with the number of motion primitives used to expand the RRT. In this paper we present a method based on optimization by elimination which is applied to the Rapidly-exploring Random Tree algorithm to reduce its computational cost. This method optimizes the efficiency of motion primitives generation. It identifies tree expansion in promising areas by initially generating and analyzing only few motion primitives. Then it increases the number of primitives for motion resolution enhancement in those promising areas. The results achieved by applying this method evidence a substantial decrease in the computational cost.

show abstract

Section: Comparing the Optimized And Traditional Rrt Extend Methodsmentioning

confidence: 99%

“…One of these methods is the Rapidlyexploring Random Tree (RRT) algorithm. Since first presented in [1], RRT and its variations have been used in numerous and diverse applications, e.g., humanoid robots [2], [3], [4] and autonomous vehicles [5], [6], [7].…”

Section: Introductionmentioning

confidence: 99%

Improving RRT's Efficiency through Motion Primitives Generation Optimization

Vieira

Grassi

2014

2014 Joint Conference on Robotics: SBR-LARS Robotics Symposium and Robocontrol

View full text Add to dashboard Cite

show abstract

“…Since checking for geometric constraints and manipulation feasibility is expensive, it resulted in large running times. More recently [18] they applied an RRT-variant to perform the search which resulted in some improvements in average running time but with high variance. Their work has also pursued a careful assessment of the stability of contacts, finding plans that are most stable under this measure, an important issue that we have not considered here.…”

Section: Related Workmentioning

confidence: 99%

Hierarchical planning for multi-contact non-prehensile manipulation

Lee

Lozano-Pérez

Kaelbling

2015

2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Abstract-Manipulation planning involves planning the combined motion of objects in the environment as well as the robot motions to achieve them. In this paper, we explore a hierarchical approach to planning sequences of non-prehensile and prehensile actions. We subdivide the planning problem into three stages (object contacts, object poses and robot contacts) and thereby reduce the size of search space that is explored. We show that this approach is more efficient than earlier strategies that search in the combined robot-object configuration space directly.

show abstract

“…The manipulated object is in contact with not only the robot but also with the environment. Moreover, graspless manipulation may be irreversible (Maeda et al, 2004;Maeda and Arai, 2005;Miyazawa et al, 2005). Nonprehensile manipulation methods are majorly divided into two different categories; quasi-static and dynamic manipulation methods.…”

Section: Introductionmentioning

confidence: 99%

An algorithm for dynamic object manipulation by a flexible link robot

Tarvirdizadeh

Alipour

Hadi

2016

Engineering Computations

View full text Add to dashboard Cite

Purpose -The purpose of this paper is to focus on an online closed-loop (CL) approach for performing dynamic object manipulation (DOM) by a flexible link manipulator. Design/methodology/approach -Toward above goal, a neural network and optimal control are integrated in a closed-loop structure, to achieve a robust control for online DOM applications. Additionally, an elegant novel numerical solution method will be developed which can handle the split boundary value problem resulted from DOM mission requirements for a wide range of boundary conditions. Findings -The obtained simulation results reveal the effectiveness of both proposed innovative numerical solution technique and control structure for online object manipulation purposes using flexible manipulators. Originality/value -The object manipulation problem has previously been studied, however, for the first time its accomplishment by flexible link manipulators was addressed just in offline form considering an open-loop control structure (Tarvirdizadeh and Yousefi-Koma, 2012). As an extension of Tarvirdizadeh and Yousefi-Koma (2012), the current research, consequently, focusses on a numerical solution and a CL approach for performing DOM by a flexible link manipulator.

show abstract

Planning of graspless manipulation based on rapidly-exploring random trees

Cited by 19 publications

References 13 publications

Improving RRT's Efficiency through Motion Primitives Generation Optimization

Improving RRT's Efficiency through Motion Primitives Generation Optimization

Hierarchical planning for multi-contact non-prehensile manipulation

An algorithm for dynamic object manipulation by a flexible link robot

Contact Info

Product

Resources

About