A Fast Integrated Planning and Control Framework for Autonomous Driving via Imitation Learning

For safe and efficient planning and control in autonomous driving, we need a driving policy which can achieve desirable driving quality in long-term horizon with guaranteed safety and feasibility. Optimization-based approaches, such as Model Predictive Control (MPC), can provide such optimal policies, but their computational complexity is generally unacceptable for real-time implementation. To address this problem, we propose a fast integrated planning and control framework that combines learning- and optimization-based approaches in a two-layer hierarchical structure. The first layer, defined as the "policy layer", is established by a neural network which learns the long-term optimal driving policy generated by MPC. The second layer, called the "execution layer", is a short-term optimization-based controller that tracks the reference trajecotries given by the "policy layer" with guaranteed short-term safety and feasibility. Moreover, with efficient and highly-representative features, a small-size neural network is sufficient in the "policy layer" to handle many complicated driving scenarios. This renders online imitation learning with Dataset Aggregation (DAgger) so that the performance of the "policy layer" can be improved rapidly and continuously online. Several exampled driving scenarios are demonstrated to verify the effectiveness and efficiency of the proposed framework.

[1]  Sanjiv Singh,et al.  The 2005 DARPA Grand Challenge: The Great Robot Race , 2007 .

[2]  Håkan Jonsson,et al.  Planning Smooth and Obstacle-Avoiding B-Spline Paths for Autonomous Mining Vehicles , 2010, IEEE Transactions on Automation Science and Engineering.

[3]  Geoffrey J. Gordon,et al.  A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning , 2010, AISTATS.

[4]  Rajesh Rajamani,et al.  Vehicle dynamics and control , 2005 .

[5]  David González,et al.  A Review of Motion Planning Techniques for Automated Vehicles , 2016, IEEE Transactions on Intelligent Transportation Systems.

[6]  Jishun Li,et al.  Automatic parking path optimization based on Bezier curve fitting , 2012, 2012 IEEE International Conference on Automation and Logistics.

[7]  Dean Pomerleau,et al.  ALVINN, an autonomous land vehicle in a neural network , 2015 .

[8]  Jonathan P. How,et al.  Real-Time Motion Planning With Applications to Autonomous Urban Driving , 2009, IEEE Transactions on Control Systems Technology.

[9]  Emilio Frazzoli,et al.  Optimal kinodynamic motion planning using incremental sampling-based methods , 2010, 49th IEEE Conference on Decision and Control (CDC).

[10]  Kyunghyun Cho,et al.  Query-Efficient Imitation Learning for End-to-End Autonomous Driving , 2016, ArXiv.

[11]  Maxim Likhachev,et al.  Motion planning in urban environments , 2008 .

[12]  Jianxiong Xiao,et al.  DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[13]  Xin Zhang,et al.  End to End Learning for Self-Driving Cars , 2016, ArXiv.

[14]  Julius Ziegler,et al.  Trajectory planning for Bertha — A local, continuous method , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[15]  Andreas Eidehall,et al.  On path planning methods for automotive collision avoidance , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[16]  Xiaohui Li,et al.  A unified approach to local trajectory planning and control for autonomous driving along a reference path , 2014, 2014 IEEE International Conference on Mechatronics and Automation.