Autonomous vehicles are poised to be the next evolution in road safety and traffic efficiency. Many cars already have some AV functionality, and there has been some piloting of various AV buses and taxis. Despite the technological advances, there are some issues preventing large scale adoption. Existing roadway infrastructure and signage poses a big hurdle. Lane markings are a critical input to ensure vehicles maintain their position on the road. Nonexistent, confusing, or obscured road markings affect AV performance. Most AVs use camera-based lidar (light detection and ranging) sensors that can be negatively affected by oil and mud deposits on roads or adverse weather conditions, such as sun glare, rain, and snow. Understanding the impact of road markings on AV performance through both real-world trials and simulations will help to expand AV adoption.
Researchers Nicolette Formosa, Mohammed Quddus, Cheuk Ki Man, Mohit Kumar Singh, Craig Morton, and Cansu Bahar Masera used an instrumented vehicle equipped with a suite of sensors mimicking the data input of an AV to conduct real-world trials. Their research, “Evaluating the Impact of Lane Marking Quality on the Operation of Autonomous Vehicles,” was performed on both a live highway and at a controlled facility. The authors examined factors affecting computer vision lane detection and classification and developed an algorithm to overcome poor lane marking limitations. Further testing was performed virtually using data from real-world trials to determine the quality of the lane markings. This study in the Journal of Transportation Engineering, Part A: Systems provides guidance to AV developers and infrastructure providers regarding the quality of lane markings in real-world conditions at https://doi.org/10.1061/JTEPBS.TEENG-7688. The abstract is below.
Abstract
The quality of lane markings is pivotal for safe operations and efficient trajectory generations of connected and autonomous vehicles (AVs). However, most studies are devoted to enhancing in-vehicle detection systems and ignore the impact of faulty lane markings. An instrumented vehicle was employed to mimic the data input of an AV and real-world trials were conducted on (1) live motorways; and (2) a controlled motorway facility. From the live motorway data, causal factors affecting computer vision lane detection and classification algorithms were examined, and an enhanced lane classification algorithm was developed to overcome the limitations posed by poor lane markings. In the controlled motorway facility, experiments to modify the physical appearance of the lane markings were conducted to further test the performance of the developed algorithm. The detection rates of the developed lane classification algorithm were compared with the lane departure warning (LDW) system already implemented in the vehicle. Findings revealed that the LDW system is accurate over 95% and 54% of the time when lanes are faded by 50% and 75% respectively. Further testing on the quality of the lane markings was carried out virtually in such a way that the experiments were replicated in a simulation environment to (1) identify lane marking conditions that can be reliably adopted for safe operations of AVs, (2) estimate the effect of adverse weather and lighting conditions on road markings detection, and (3) address localization issues for AVs. Simulation results show that poor lane markings have a significant negative impact on AV safety, especially in inclement weather and poor light conditions inducing an increase in conflicts and delays. This can be compensated for if more sophisticated sensors are employed in AVs, and the operators of road networks develop lane-based digital road maps.
Delve into the team’s lane marking research and solutions for AVs: https://doi.org/10.1061/JTEPBS.TEENG-7688.
