Abstract
Perception sensors such as camera, radar, and lidar have gained considerable popularity in the automotive industry in recent years. In order to reach the next step towards automated driving it is necessary to implement fault diagnosis systems together with suitable mitigation solutions in automotive perception sensors. This is a crucial prerequisite, since the quality of an automated driving function strongly depends on the reliability of the perception data, especially under adverse conditions. This publication presents a systematic review on faults and suitable detection and recovery methods for automotive perception sensors and suggests a corresponding classification schema. A systematic literature analysis has been performed with focus on lidar in order to review the state-of-the-art and identify promising research opportunities. Faults related to adverse weather conditions have been studied the most, but often without providing suitable recovery methods. Issues related to sensor attachment and mechanical damage of the sensor cover were studied very little and provide opportunities for future research. Algorithms, which use the data stream of a single sensor, proofed to be a viable solution for both fault detection and recovery.
Highlights
Advancing the level of automation for vehicles is a major challenge in today’s automotive industry.Automated vehicles are expected to provide great benefits for the driver and enable new transportation use cases and applications, e.g., [1]
Advanced driver assistance system (ADAS) and automated driving (AD) functions have the potential to reduce this number significantly, since most car accidents are traceable to a human error [3,4,5]
The class comparison to other sensor of same type identifies faults based on comparing the output of two sensors of the same type, e.g., two lidar sensors, two radar sensors, or two camera sensors, with overlapping FOV (Figure 3e)
Summary
Advancing the level of automation for vehicles is a major challenge in today’s automotive industry. Vehicles that fulfil SAE level 3 “conditional driving automation” must provide an AD function that allows the driver to remove his attention off the road and only intervene when the system requests In this case, the vehicle is responsible for object and event detection and proper response. To address sensor faults in automated vehicles in a cost effective manner, sensor fault detection, isolation, identification, and recovery (FDIIR) systems, e.g., [8] can be included into each individual perception sensor that is contributing to the SENSE-PLAN-ACT cycle (Figure 1). The publication is structured as follows: Section 2 introduces a new fault classification for automotive perception sensors and relates the fault classes to current and upcoming international safety standards for automated vehicles. A glossary of the technical terms can be found at the end of this paper
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
