Minimum distances for robot task simulation

Red, W. Edward

doi:10.1017/s0263574700002162

Cited by 25 publications

(9 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Efficient algorithms were also reported by Barr [l]. Barr and Gilbert [2], Wolfe [24], Red [21], Buckley and Leifer [4], Cameron [5], and Gilbert er al. [lo].…”

Section: Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Collision identification between convex polyhedra using neural networks

Yuan

1995

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

Collision identification between convex polyhedra is a major research focus in computer-aided manufacturing and path planning for robots. This paper presents a collision-identification neural network (CINN) to identify possible collisions between two convex polyhedra. It consists of a modified Hamming net and a constraint subnet. The modified Hamming net is designed for point-to-polyhedron collision identification, and the constraint subnet is designed to move a point within a polyhedron and detect possible collisions with another polyhedron. A CINN has a simple canonical structure. It is very easy to program and can be implemented by a modest number of nonlinear amplifiers and three analog integrators. The working principle of the CINN is very similar to the well-known Hopfield net model. Its simple collective computing power accomplishes the relatively complicated task of collision identification between convex polyhedra, rendering a suitable device for online path planning of robots. An example is presented to demonstrate the application of CINN's to collision-free motion planning.

show abstract

“…Efficient algorithms were also reported by Barr [l]. Barr and Gilbert [2], Wolfe [24], Red [21], Buckley and Leifer [4], Cameron [5], and Gilbert er al. [lo].…”

Section: Neural Networkmentioning

confidence: 99%

“…Three forces act on it: ~, 2 3 and v,34 denote the velocity caused by the spring forces while v,3 represents the velocity caused by the collision force. The constraint velocities can be computed by vs23 = -k,(a3 -b2), vs34 = -ks(b3a) (21) where 3 p i . , is the pseudodistance between polygon A3 and B and 3zi?)…”

Section: Amentioning

confidence: 99%

Collision identification between convex polyhedra using neural networks

Yuan

1995

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

show abstract

“…The basic disadvantage of the early vertex-based and surface-to surface method (9) is the computation time. The more the number of "element"-vertices and surfaces, the more computation time we need to spend.…”

Section: Introductionmentioning

confidence: 99%

Collision Distance Detection Based on Swept Volume Strategy for Optimal Motion Plan

Huang

2009

JAMDSM

View full text Add to dashboard Cite

A swept volume strategy to detect the collision distances between obstacles is presented in this paper for robot motion planning based on optimization technique. The strategy utilizes the recursive quadratic programming optimization method to perform the motion planning problem. This paper is based on segmental swept volume for convenient distance-to-contact calculation. Hermite interpolation is presented to approach the envelope bounding the swept volume. The new method is capable of handling a modestly non-convex swept volume and it has yielded accurate answers in distance calculations. Also, examples would be presented to illustrate and demonstrate this approach in the paper.

show abstract

“…These approaches can be classified either by the method of distance calculation or by their underlying principles. In terms of the method of distance calculation, existing distance calculation approaches can be characterised as vertexbased approaches [3,4], surface-based approaches [5], and convex object-based approaches [2,[6][7][8]. In terms of the underlying principles, the research can be classified into three major categories: forbidden region identification methods [3], swept volume methods [9][10][11][12], and constrained distance minimization methods [1, 2, 13}. In this work, a new formulation for collision identification and distance calculation in motion planning, using neural networks, is introduced.…”

Section: Introductionmentioning

confidence: 99%