Machine Learning Based Obstacle Detection for Automatic Train Pairing
作者： Raja Sattiraju , Hans D. Schotten , Jacob Kochems
DOI:
关键词: Transmitter power output 、 Computer science 、 Ranging 、 Multipath propagation 、 Obstacle 、 Real-time computing 、 Supervised learning 、 Bistatic radar
摘要: Short Range wireless devices are becoming more and popular for ubiquitous sensor actuator connectivity in industrial communication scenarios. Apart from communication-only scenarios, there also mission-critical use cases where the distance between two communicating nodes needs to be determined precisely. Applications such as Automatic Guided Vehicles (AGV's), Train Pairing additionally require scan environment detect any potential humans/obstacles. Ultra-Wide Band (UWB) has emerged a promising candidate Real-Time Ranging Localization (RTRL) due advantages large channel capacity, better co-existence with legacy systems low transmit power, performance multipath environments etc. In this paper, we evaluate of UWB COTS device - TimeDomain P440 which can operate ranging radio monostatic radar simultaneously. To end, possibility using Supervised Learning based estimators predicting presence obstacles by constructing multiclass hypothesis. Simulation results show that Ensemble tree methods able calculate likelihood obstacle collision accuracies close 95%.
arxiv.org参考文章(11)
R. Bell, IEC 61508: functional safety of electrical/electronic/ programme electronic safety-related systems: overview Control of Major Accidents and Hazards Directive (COMAH) - Implications for Electrical and Control Engineers (Ref. No. 1999/173), IEE Colloquium. ,(1999)
Justin Metcalf, Shannon D. Blunt, Braham Himed, A machine learning approach to cognitive radar detection ieee radar conference. pp. 1405- 1411 ,(2015) , 10.1109/RADAR.2015.7131215
A. Petroff, A practical, high performance Ultra-Wideband radar platform ieee radar conference. pp. 0880- 0884 ,(2012) , 10.1109/RADAR.2012.6212261
Mohammad Abu Alsheikh, Shaowei Lin, Hwee-Pink Tan, Dusit Niyato, Machine Learning in Wireless Sensor Networks: Algorithms, Strategies, and Applications IEEE Communications Surveys and Tutorials. ,vol. 16, pp. 1996- 2018 ,(2014) , 10.1109/COMST.2014.2320099
Abdul Q. Javaid, Carlo M. Noble, Russell Rosenberg, Mary Ann Weitnauer, Towards Sleep Apnea Screening with an Under-the-Mattress IR-UWB Radar Using Machine Learning international conference on machine learning and applications. pp. 837- 842 ,(2015) , 10.1109/ICMLA.2015.79
Jingon Joung, Machine Learning-Based Antenna Selection in Wireless Communications IEEE Communications Letters. ,vol. 20, pp. 2241- 2244 ,(2016) , 10.1109/LCOMM.2016.2594776
Chunxiao Jiang, Haijun Zhang, Yong Ren, Zhu Han, Kwang-Cheng Chen, Lajos Hanzo, Machine Learning Paradigms for Next-Generation Wireless Networks IEEE Wireless Communications. ,vol. 24, pp. 98- 105 ,(2017) , 10.1109/MWC.2016.1500356WC
Junbum Park, Sung Ho Cho, IR-UWB Radar Sensor for Human Gesture Recognition by Using Machine Learning high performance computing and communications. pp. 1246- 1249 ,(2016) , 10.1109/HPCC-SMARTCITY-DSS.2016.0176
, , , Platform Architecture for Decentralized Positioning Systems. Sensors. ,vol. 17, pp. 957- ,(2017) , 10.3390/S17050957
Raja Sattiraju, Hans D. Schotten, Michael Karrenbauer, Andreas Weinand, Application of Machine Learning for Channel based Message Authentication in Mission Critical Machine Type Communication arXiv: Networking and Internet Architecture. ,(2017)