Unsupervised Hump Detection for Mobile Robots Based On Kinematic Measurements and Deep-Learning Based Autoencoder

被引：0

作者：

Rettig, Oliver ^{[1
]}

Mueller, Silvan ^{[1
]}

Strand, Marcus ^{[1
]}

Katic, Darko ^{[2
]}

机构：

[1] Baden Wuerttemberg Cooperat State Univ, Dept Comp Sci, D-76133 Karlsruhe, Germany

[2] ArtiMinds Robot GmbH, D-76139 Karlsruhe, Germany

来源：

INTELLIGENT AUTONOMOUS SYSTEMS 15, IAS-15 | 2019年 / 867卷

关键词：

Neural networks; Anomaly detection; Path planning; Kinematic measurement; Mobile robotics; Deep learning;

D O I：

10.1007/978-3-030-01370-7_9

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Small humps on the floor go beyond the detectable scope of laser scanners and are therefore not integrated into SLAM based maps of mobile robots. However, even such small irregularities can have a tremendous effect on the robot's stability and the path quality. As a basis to develop anomaly detection algorithms, example kinematics data is collected for an overrun of a cable channel and a bulb plate. A recurrent neuronal network (RNN), based on the autoencoder principle, could be trained successfully with this data. The described RNN architecture looks promising to be used for realtime anomaly detection and also to quantify path quality.

引用

页码：99 / 110

页数：12

共 16 条

[1] An J., 2015, Special Lecture on IE, V1, P1
[2] Bengio Yoshua, 2012, Neural Networks: Tricks of the Trade. Second Edition: LNCS 7700, P437, DOI 10.1007/978-3-642-35289-8_26
[3] Edgeworth F.Y., 1887, Hermathena, V6, P279
[4] Fabius O, 2015, Arxiv, DOI arXiv:1412.6581
[5] Gamboa J, 2017, ARXIV
[6] Graves A, 2012, STUD COMPUT INTELL, V385, P1, DOI [10.1162/neco.1997.9.1.1, 10.1007/978-3-642-24797-2]
[7] A survey of outlier detection methodologies
Hodge V.J.
Austin J.
[J]. Artificial Intelligence Review, 2004, 22 (2) : 85 - 126
[8] Rezende DJ, 2014, Arxiv, DOI [arXiv:1401.4082, 10.48550/arXiv.1401.4082]
[9] Malhotra P, 2016, Arxiv, DOI arXiv:1607.00148
[10] Meyer J.-A., 2003, Cognitive Systems Research, V4, P283, DOI 10.1016/S1389-0417(03)00007-X

← 1 2 →