Full Workspace Generation of Serial-link Manipulators by Deep Learning based Jacobian Estimation

August 31, 2018 · Entered Twilight · 🏛 arXiv.org

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, 2018-08-2606:43:47101423--0.0.hdf5, JacobianNet.py, README.md, SVM_Linear_L2.sav, SVM_RBF.sav, SVM_Sigmoid.sav, Untitled.ipynb, __pycache__, baseline, conf_hist, conf_history_pretrained, confidence_comparison.py, confidence_matlab.py, confidence_only.py, create_matlab_dataset.py, data.zip, data, est_matlab.hdf5, estimation_comparison.py, estimation_matlab.py, estimation_only.py, evaluate_model.ipynb, graph, graph_histories, histories, matlab_eval.m, models, paper_models, pretrained.model, pretrained, pretrained_hist, shared_estimaiton.model, visualization.py, visualization

Authors Peiyuan Liao, Jiajun Mao arXiv ID 1809.05020 Category cs.RO: Robotics Citations 2 Venue arXiv.org Repository https://github.com/liaopeiyuan/Jacobian-Estimation Last Checked 2 months ago

Abstract

Apart from solving complicated problems that require a certain level of intelligence, fine-tuned deep neural networks can also create fast algorithms for slow, numerical tasks. In this paper, we introduce an improved version of [1]'s work, a fast, deep-learning framework capable of generating the full workspace of serial-link manipulators. The architecture consists of two neural networks: an estimation net that approximates the manipulator Jacobian, and a confidence net that measures the confidence of the approximation. We also introduce M3 (Manipulability Maps of Manipulators), a MATLAB robotics library based on [2](RTB), the datasets generated by which are used by this work. Results have shown that not only are the neural networks significantly faster than numerical inverse kinematics, it also offers superior accuracy when compared to other machine learning alternatives. Implementations of the algorithm (based on Keras[3]), including benchmark evaluation script, are available at https://github.com/liaopeiyuan/Jacobian-Estimation . The M3 Library APIs and datasets are also available at https://github.com/liaopeiyuan/M3 .