On Multi-Sensor Radar Configurations for Vehicle Tracking in Autonomous Driving Environments

Multi-sensor radar tracking systems can provide better system performance, visibility and complementary information than single sensor tracking systems. One way to utilize multiple sensors for target tracking is to generate individual sensor detections and fuse these detections to produce optimized system tracks. All or a subset of detections from the sensors are fed into a tracker algorithm, allowing the filter to choose the best possible measurement association. This paper discusses the implementation of a multi-sensor target tracking system using three different sensor configurations for providing vehicle detections. The three sensor configurations compare the accuracy of one vs two radar sensors, operating in either a stepped frequency waveform or a hybrid stepped frequency and continuous waveform. The purpose of this paper is to provide insight into the possibilities of multi-sensor radar tracking for the advancement of autonomous driving.

[1]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[2]  Henry Leung,et al.  Statistical performance analysis of track initiation techniques , 1997, IEEE Trans. Signal Process..

[3]  Anna Freud,et al.  Design And Analysis Of Modern Tracking Systems , 2016 .

[4]  Holger Blume,et al.  An experimental high performance radar system for highly automated driving , 2017, 2017 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM).

[5]  Thia Kirubarajan,et al.  Probabilistic data association techniques for target tracking in clutter , 2004, Proceedings of the IEEE.

[6]  Matthias Scheutz,et al.  Belief theoretic methods for soft and hard data fusion , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[7]  Thanuka Wickramarathne.  Evidence updating for stream-processing in big-data: Robust conditioning in soft and hard data fusion environments , 2017, 2017 20th International Conference on Information Fusion (Fusion).

[8]  Fredrik Gustafsson,et al.  Particle filters for positioning, navigation, and tracking , 2002, IEEE Trans. Signal Process..

[9]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[10]  H. Rohling,et al.  Radar waveform for automotive radar systems and applications , 2008, 2008 IEEE Radar Conference.

[11]  Amir Averbuch,et al.  Interacting Multiple Model Methods in Target Tracking: A Survey , 1988 .

[12]  F. Pektas,et al.  A score-based track initiation procedure to eliminate false tracks in the presence of sea clutter , 2012, 2012 IEEE Radar Conference.

[13]  Bassem Mahafza,et al.  Radar Systems Analysis and Design Using MATLAB , 2000 .

[14]  Xiaofeng Ma,et al.  An improved MFSK waveform for low-cost automotive radar , 2016, 2016 CIE International Conference on Radar (RADAR).

[15]  Thia Kirubarajan,et al.  Performance measures for multiple target tracking problems , 2011, 14th International Conference on Information Fusion.

[16]  Mark R. Bell,et al.  An adaptive greedy pursuit algorithm for pulse-Doppler radar , 2015, 2015 49th Asilomar Conference on Signals, Systems and Computers.

[17]  Garrick J. Forkenbrock,et al.  Blind Spot Monitoring in Light Vehicles – System Performance , 2014 .

[18]  Thanuka Wickramarathne,et al.  Low-Cost Radar for Object Tracking in Autonomous Driving: A Data-Fusion Approach , 2018, 2018 IEEE 87th Vehicular Technology Conference (VTC Spring).

[19]  Klaus C. J. Dietmayer,et al.  Multi-sensor multi-object tracking of vehicles using high-resolution radars , 2016, 2016 IEEE Intelligent Vehicles Symposium (IV).

[20]  Nitesh V. Chawla,et al.  Convergence Analysis of Iterated Belief Revision in Complex Fusion Environments , 2014, IEEE Journal of Selected Topics in Signal Processing.

[21]  Kiril Alexiev.  Implementation of Hough Transform as track detector , 2000, Proceedings of the Third International Conference on Information Fusion.

[22]  Marc-Michael Meinecke,et al.  COMBINATION OF LFMCW AND FSK MODULATION PRINCIPLES FOR AUTOMOTIVE RADAR SYSTEMS Symposium Topic: Automotive Radar , 2000 .

[23]  Sameer Singh,et al.  Approaches to Multisensor Data Fusion in Target Tracking: A Survey , 2006, IEEE Transactions on Knowledge and Data Engineering.

[24]  Peter Bauer,et al.  On the Use of 3-D Accelerometers for Road Quality Assessment , 2018, 2018 IEEE 87th Vehicular Technology Conference (VTC Spring).

[25]  Kamal Premaratne,et al.  Toward Efficient Computation of the Dempster–Shafer Belief Theoretic Conditionals , 2013, IEEE Transactions on Cybernetics.