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

TL;DR

This paper presents an efficient vision-based autonomous vehicle control system using a monocular camera and inexpensive sensors, combining a multi-task neural network with rapid motion planning algorithms for real-time driving.

Contribution

The study introduces a novel framework integrating MTUNet with CILQR and VPC for efficient, map-free autonomous driving using only low-cost sensors and achieving high-speed processing.

Findings

MTUNet achieves 40 FPS for multiple tasks on 228x228 images.

The VPC algorithm reduces steering latency below actuator latency.

The system outperforms traditional methods on curvy roads.

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.