Unsupervised Hump Detection for Mobile Robots Based On Kinematic Measurements and Deep-Learning Based Autoencoder
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.
KeywordsNeural networks Anomaly detection Path planning Kinematic measurement Mobile robotics Deep learning
The kinematic measurements were executed in the Gait- and Motionlab Heidelberg, University Clinics and were supported by the local laboratory team. The project is funded by the Federal Ministry for Economic Affairs and Energy of Germany.
- 3.Edgeworth, F.Y.: On observations relating to several quantities. Hermathena 13(6), 279–285 (1887)Google Scholar
- 5.Gamboa, J.C.B.: Deep Learning for Time-Series Analysis. arXiv preprint arXiv:1701.01887. (2017)
- 6.Tai, L., Liu, M.: Deep-learning in mobile robotics-from perception to control systems: A survey on why and why not. arXiv:1612.07139. (2016)
- 9.Malhotra, P., Ramakrishnan, A., Anand, G., Vig, L., Agarwal, P., Shroff, G.: LSTM-based encoder-decoder for multi-sensor anomaly detection. arXiv preprint arXiv:1607.00148. (2016)
- 10.Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114. (2013)
- 11.Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. arXiv preprint arXiv:1401.4082. (2014)
- 12.Sölch, M., Bayer, J., Ludersdorfer, M., van der Smagt, P.: Variational inference for on-line anomaly detection in high-dimensional timeseries. arXiv preprint arXiv:1602.07109. (2016)
- 13.An, J., Cho, S.: Variational autoencoder based anomaly detection using reconstruction probability. Technical report, SNU Data Mining Center (2015)Google Scholar
- 14.Fabius, O., van Amersfoort, J.R.: Variational recurrent auto-encoders. arXiv preprint arXiv:1412.6581 (2014)
- 17.Bengio, Y.: Practical recommendations for gradient-based training of deep architectures. In: Neural Networks: Tricks of the Trade, pp. 437-478. Springer, Berlin, Heidelberg (2012)Google Scholar