Multi-Model Recurrent Neural Network Control for Lane Change Systems under Speed Variation

A new multi-model recurrent neural network(RNN) control scheme is developed for autonomous vehicle lane-change maneuvering with longitudinal speed variation. Lateral motion control for lane-change maneuvering under longitudinal speed variation becomes challenging because the lateral vehicle dynamics is very involved. The literature has studied lane-change control using a bicycle dynamic model with fixed longitudinal speed. However, It rarely reported how a lane-change controller under variation of speed performs. In the paper, we develop an innovative scheme in which multiple RNNs are trained. And a probabilistic data association of their outputs is given as the command to the steering angle. Each RNN is trained by optimizing the corresponding model predictive control (MPC) with fixed vehicle speed. Further, the discrete probability distribution is used to avoid impractical RNN training for lane-change maneuvering with various vehicle speed variation scenarios. The proposed multi-model RNN control scheme is demonstrated through an application. The proposed system shows that it satisfies the constraints given in the design of MPCs and exhibit better control performance.

[1]  Junfei Qiao,et al.  Nonlinear Model Predictive Control Based on a Self-Organizing Recurrent Neural Network , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Sergey Levine,et al.  Learning deep control policies for autonomous aerial vehicles with MPC-guided policy search , 2015, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[3]  Chung Choo Chung,et al.  Multilevel approximate model predictive control and its application to autonomous vehicle active steering , 2013, 52nd IEEE Conference on Decision and Control.

[4]  Miroslav Fikar,et al.  Clipping-Based Complexity Reduction in Explicit MPC , 2012, IEEE Transactions on Automatic Control.

[5]  H. E. Tseng,et al.  Linear model predictive control for lane keeping and obstacle avoidance on low curvature roads , 2013, 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013).

[6]  Alberto Bemporad,et al.  Model predictive control based on linear programming - the explicit solution , 2002, IEEE Transactions on Automatic Control.

[7]  Frank Allgöwer,et al.  Learning an Approximate Model Predictive Controller With Guarantees , 2018, IEEE Control Systems Letters.

[8]  Chung Choo Chung,et al.  Autonomous Vehicle Lateral Maneuvering by Approximate Explicit Predictive Control , 2018, 2018 Annual American Control Conference (ACC).

[9]  Wonhee Kim,et al.  Lateral Control System for Autonomous Lane Change System on Highways , 2016 .

[10]  Maciej Lawrynczuk,et al.  Accuracy and computational efficiency of suboptimal nonlinear predictive control based on neural models , 2011, Appl. Soft Comput..

[11]  Kimon P. Valavanis,et al.  Nonlinear Model Predictive Control With Neural Network Optimization for Autonomous Autorotation of Small Unmanned Helicopters , 2011, IEEE Transactions on Control Systems Technology.

[12]  Chung Choo Chung,et al.  Approximate Model Predictive Control with Recurrent Neural Network for Autonomous Driving Vehicles , 2019, 2019 58th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE).

[13]  Manfred Morari,et al.  Autonomous vehicle steering using explicit LPV-MPC , 2009, 2009 European Control Conference (ECC).

[14]  Jing Peng,et al.  An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories , 1990, Neural Computation.

[15]  Thomas Besselmann,et al.  Explicit Model Predictive Control for Systems with Linear Parameter-Varying State Transition Matrix , 2008 .

[16]  Zhen Huang,et al.  Model Predictive Control for Intelligent Vehicle Lane Change , 2013 .

[17]  Chung Choo Chung,et al.  Proximate model predictive control strategy for autonomous vehicle lateral control , 2011, 2012 American Control Conference (ACC).