Deep Neural Network Based Subspace Learning of Robotic Manipulator Workspace Mapping

TL;DR

This paper presents a deep neural network approach for efficient robotic manipulator workspace mapping, significantly reducing computation time while maintaining high accuracy compared to traditional methods.

Contribution

Introduces a subspace learning method using DNNs for fast workspace mapping, overcoming the high computational cost of classical kinematic algorithms.

Findings

Run-time reduced from 5223 seconds to 0.224 seconds

High accuracy with an average F-measure of 0.9665

Effective on large datasets of around 60,000 samples

Abstract

The manipulator workspace mapping is an important problem in robotics and has attracted significant attention in the community. However, most of the pre-existing algorithms have expensive time complexity due to the reliance on sophisticated kinematic equations. To solve this problem, this paper introduces subspace learning (SL), a variant of subspace embedding, where a set of robot and scope parameters is mapped to the corresponding workspace by a deep neural network (DNN). Trained on a large dataset of around $\mathbf{6\times 10^4}$ samples obtained from a MATLAB$^\circledR$ implementation of a classical method and sampling of designed uniform distributions, the experiments demonstrate that the embedding significantly reduces run-time from $\mathbf{5.23 \times 10^3}$ s of traditional discretization method to $\mathbf{0.224}$ s, with high accuracies (average F-measure is $\mathbf{0.9665}$ with batch gradient descent and resilient backpropagation).