Efficient Perception, Planning, and Control Algorithm for Vision-Based Automated Vehicles

Abstract

Autonomous vehicles have limited computational resources and thus require efficient control systems. The cost and size of sensors have limited the development of self-driving cars. To overcome these restrictions, this study proposes an efficient framework for the operation of vision-based automatic vehicles; the framework requires only a monocular camera and a few inexpensive radars. The proposed algorithm comprises a multi-task UNet (MTUNet) network for extracting image features and constrained iterative linear quadratic regulator (CILQR) and vision predictive control (VPC) modules for rapid motion planning and control. MTUNet is designed to simultaneously solve lane line segmentation, the ego vehicle's heading angle regression, road type classification, and traffic object detection tasks at approximately 40 FPS for 228 x 228 pixel RGB input images. The CILQR controllers then use the MTUNet outputs and radar data as inputs to produce driving commands for lateral and longitudinal vehicle guidance within only 1 ms. In particular, the VPC algorithm is included to reduce steering command latency to below actuator latency, preventing performance degradation during tight turns. The VPC algorithm uses road curvature data from MTUNet to estimate the appropriate correction for the current steering angle at a look-ahead point to adjust the turning amount. The inclusion of the VPC algorithm in a VPC-CILQR controller leads to higher performance on curvy roads than the use of CILQR alone. Our experiments demonstrate that the proposed autonomous driving system, which does not require high-definition maps, can be applied in current autonomous vehicles.

arXiv comment14 figures, 14 pages

References in corpus (11)

• SSD: Single Shot MultiBox Detector
• MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation
• A Survey of Autonomous Driving: Common Practices and Emerging Technologies
• A Survey of Deep Learning Techniques for Autonomous Driving
• Benchmark Analysis of Representative Deep Neural Network Architectures
• Lidar for Autonomous Driving: The principles, challenges, and trends for automotive lidar and perception systems
• YOLOP: You Only Look Once for Panoptic Driving Perception
• Robust Lane Detection from Continuous Driving Scenes Using Deep Neural Networks
• A Survey of End-to-End Driving: Architectures and Training Methods
• TUM autonomous motorsport: An autonomous racing software for the Indy Autonomous Challenge
• Enhanced free space detection in multiple lanes based on single CNN with scene identification