LVD-NMPC: A learning-based vision dynamics approach to nonlinear model predictive control for autonomous vehicles

International Journal of Advanced Robotic Systems

article

Sorin Grigorescu¹  Cosmin Ginerica²  Mihai Zaha²  Gigel Macesanu¹  Bogdan Trasnea¹ 

[1] Transilvania University of Brasov;Elektrobit Automotive GmbH

关键词: Autonomous vehicles;    autonomous driving;    vision dynamics;    learning control;    artificial intelligence;    deep learning;    perception and control;    robot vision;   

DOI  :  10.1177/17298814211019544

学科分类：社会科学、人文和艺术（综合）

来源: InTech

【 摘 要 】

In this article, we introduce a learning-based vision dynamics approach to nonlinear model predictive control (NMPC) for autonomous vehicles, coined learning-based vision dynamics (LVD) NMPC. LVD-NMPC uses an a-priori process model and a learned vision dynamics model used to calculate the dynamics of the driving scene, the controlled system’s desired state trajectory, and the weighting gains of the quadratic cost function optimized by a constrained predictive controller. The vision system is defined as a deep neural network designed to estimate the dynamics of the image scene. The input is based on historic sequences of sensory observations and vehicle states, integrated by an augmented memory component. Deep Q-learning is used to train the deep network, which once trained can also be used to calculate the desired trajectory of the vehicle. We evaluate LVD-NMPC against a baseline dynamic window approach (DWA) path planning executed using standard NMPC and against the PilotNet neural network. Performance is measured in our simulation environment GridSim, on a real-world 1:8 scaled model car as well as on a real size autonomous test vehicle and the nuScenes computer vision dataset.

【 授权许可】

CC BY