Evaluating Low-Resource Lane Following Algorithms for Compute-Constrained Automated Vehicles

2024-09-04

AI Summary

To address the deployment challenges of lane-following algorithms on compute-constrained autonomous vehicles, this paper evaluates and optimizes five lightweight real-time approaches, proposing an unsupervised-learning-based lane detection method achieving ultra-low latency (<10 ms/frame). The method integrates unsupervised image segmentation with classical vision-based feature extraction and incorporates embedded-system deployment optimizations to enable end-to-end real-time inference. It is rigorously validated in both simulation and on a steer-by-wire electric vehicle platform. Compared to high-compute deep learning alternatives, the proposed approach demonstrates significantly improved generalization robustness under varying illumination, complex road textures, and curved-road scenarios. It achieves higher lane-tracking accuracy and smoother vehicle control, while enabling cost-effective, large-scale deployment of L1/L2-level advanced driver assistance systems (ADAS) on resource-limited hardware.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Reliable lane-following is essential for automated and assisted driving, yet existing solutions often rely on models that require extensive computational resources, limiting their deployment in compute-constrained vehicles. We evaluate five low-resource lane-following algorithms designed for real-time operation on vehicles with limited computing resources. Performance was assessed through simulation and deployment on real drive-by-wire electric vehicles, with evaluation metrics including reliability, comfort, speed, and adaptability. The top-performing methods used unsupervised learning to detect and separate lane lines with processing time under 10 ms per frame, outperforming compute-intensive and poor generalizing deep learning approaches. These approaches demonstrated robustness across lighting conditions, road textures, and lane geometries. The findings highlight the potential for efficient lane detection approaches to enhance the accessibility and reliability of autonomous vehicle technologies. Reducing computing requirements enables lane keeping to be widely deployed in vehicles as part of lower-level automation, including active safety systems.

Problem

• Evaluate low-resource lane-following algorithms for compute-constrained vehicles.
• Assess performance of algorithms in real-time operation on limited-resource vehicles.
• Highlight efficient lane detection to enhance autonomous vehicle accessibility and reliability.

Innovation

• Unsupervised learning for lane detection
• Real-time processing under 10 ms per frame
• Robust across lighting, textures, and geometries