Learning lane change trajectories from on-road driving data

Lane change is one of the most principle driving behaviors on structure roads. It frequently happens in daily driving. A key issue in lane change technique is trajectory planning, where a set of trajectories describing possible vehicle motions are generated by applying a parametric function, and by uniformly sampling the end states in configuration space; the trajectories are then examined to find an optimal one for execution. However, such a trajectory set has poor efficiency due to the large sample number. Many trajectories in this set seldom happen in real human driving behaviors. In this research, lane change trajectories are collected from real driving data of different drivers. Their statistics are analyzed, through which, a simplified trajectory set is generated. Experiment results show that the trajectory set has much less number of samples but can still guarantee to cover usual lane change behaviors of human being.

[1]  Yoshitaka Marumo,et al.  Analysis of Braking Behavior of Train Drivers to Detect Unusual Driving , 2010 .

[2]  D. French,et al.  Decision-making style, driving style, and self-reported involvement in road traffic accidents. , 1993, Ergonomics.

[3]  Julius Ziegler,et al.  Spatiotemporal state lattices for fast trajectory planning in dynamic on-road driving scenarios , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  Dinesh Manocha,et al.  Virtualized Traffic: Reconstructing Traffic Flows from Discrete Spatio-Temporal Data , 2009, 2009 IEEE Virtual Reality Conference.

[5]  Roland Siegwart,et al.  Bayesian on-line learning of driving behaviors , 2011, 2011 IEEE International Conference on Robotics and Automation.

[6]  Alex Pentland,et al.  Driver behavior recognition and prediction in a SmartCar , 2000, Defense, Security, and Sensing.

[7]  Sharon Newnam,et al.  A comparison of the driving behavior between remunerated and volunteer drivers , 2011 .

[8]  Julius Ziegler,et al.  Optimal trajectory generation for dynamic street scenarios in a Frenét Frame , 2010, 2010 IEEE International Conference on Robotics and Automation.

[9]  Erwin R. Boer,et al.  Toward an Integrated Model of Driver Behavior in Cognitive Architecture , 2001 .

[10]  A. Modjtahedzadeh,et al.  A control theoretic model of driver steering behavior , 1990, IEEE Control Systems Magazine.

[11]  Jiuhong Ruan,et al.  Study on Intelligent Vehicle Lane Change Path Planning and Control Simulation , 2006, 2006 IEEE International Conference on Information Acquisition.

[12]  Dinesh Manocha,et al.  Virtualized Traffic: Reconstructing Traffic Flows from Discrete Spatio-Temporal Data , 2009, VR.

[13]  John M. Dolan,et al.  A point-based MDP for robust single-lane autonomous driving behavior under uncertainties , 2011, 2011 IEEE International Conference on Robotics and Automation.

[14]  Benjamin Coifman,et al.  Lane Change Maneuver Detection from Probe Vehicle DGPS Data , 2006, 2006 IEEE Intelligent Transportation Systems Conference.

[15]  Z Bareket,et al.  USING NEURAL NETWORKS TO IDENTIFY DRIVING STYLE AND HEADWAY CONTROL BEHAVIOR OF DRIVERS , 1998 .