The Perception System of Intelligent Ground Vehicles in All Weather Conditions: A Systematic Literature Review

Abstract

Perception is a vital part of driving. Every year, the loss in visibility due to snow, fog, and rain causes serious accidents worldwide. Therefore, it is important to be aware of the impact of weather conditions on perception performance while driving on highways and urban traffic in all weather conditions. The goal of this paper is to provide a survey of sensing technologies used to detect the surrounding environment and obstacles during driving maneuvers in different weather conditions. Firstly, some important historical milestones are presented. Secondly, the state-of-the-art automated driving applications (adaptive cruise control, pedestrian collision avoidance, etc.) are introduced with a focus on all-weather activity. Thirdly, the most involved sensor technologies (radar, lidar, ultrasonic, camera, and far-infrared) employed by automated driving applications are studied. Furthermore, the difference between the current and expected states of performance is determined by the use of spider charts. As a result, a fusion perspective is proposed that can fill gaps and increase the robustness of the perception system.

Sensors and Sensor’s Fusion in Autonomous Vehicles

“…In the article by Mohammed A.S. et al [ 13 ], an overview of sensor technologies used to detect the environment and obstacles during driving maneuvers in various weather conditions is presented. First, some important historical milestones are presented.…”

Potential Effectiveness of Bicycle-Automatic Emergency Braking using the Washtenaw Area Transportation Study Data Set

“…The cyclist was assumed to be visible for 40 m. Although current radar systems can detect pedestrians at ranges upwards of 90 m in ideal conditions (11). A detection range of 40 m was chosen because camera-based detection and non-ideal conditions can reduce pedestrian detection ranges (12,13). The relative speed was the difference between the cyclist's estimated speed and the vehicle's estimated speed as shown in Equation 2.…”

Robust Target Detection and Tracking Algorithm Based on Roadside Radar and Camera

“…In addition to the detection accuracy, we also need to consider the cost of the whole solution for large-scale deployment [ 4 ]. In [ 40 ], the authors evaluated sensors using five criteria: range, resolution, contrast, weather, and cost. In ideal conditions, the vehicle-detection range can reach up to 100 m, and the pedestrian-detection range can reach up to 43 m using a 16-line lidar [ 29 ].…”

“…Although a higher beam lidar can increase detection accuracy and effective range, the high cost of lidar hinders its large-scale market application. According to the investigation in [ 40 ], the cost of a 16-line lidar is more than 10 times that of a 77 GHz millimeter-wave radar or a mono-camera, and the price of a 64-line lidar is between USD 40,000 and 70,000. Cameras are currently the most widely used sensor, and image-processing algorithms based on deep learning have evolved tremendously.…”