[Paper Review] Perception and Sensing for Autonomous Vehicles Under Adverse Weather Conditions: A Survey

Yuxiao Zhang, Alexander Carballo+2 more|arXiv (Cornell University)|Dec 16, 2021

Air Quality Monitoring and Forecasting24 citations

TL;DR

This survey analyzes how adverse weather affects ADS sensors, reviews perception-enhancement and sensor-robustness techniques, and discusses datasets, simulators, and future directions.

ABSTRACT

Automated Driving Systems (ADS) open up a new domain for the automotive industry and offer new possibilities for future transportation with higher efficiency and comfortable experiences. However, autonomous driving under adverse weather conditions has been the problem that keeps autonomous vehicles (AVs) from going to level 4 or higher autonomy for a long time. This paper assesses the influences and challenges that weather brings to ADS sensors in an analytic and statistical way, and surveys the solutions against inclement weather conditions. State-of-the-art techniques on perception enhancement with regard to each kind of weather are thoroughly reported. External auxiliary solutions, weather conditions coverage in currently available datasets, simulators, and experimental facilities with weather chambers are distinctly sorted out. Additionally, potential future ADS sensors candidates and approaches beyond common senses are provided. By looking into all kinds of major weather problems the autonomous driving field is currently facing, and reviewing both hardware and computer science solutions in recent years, this survey points out the main moving trends of adverse weather problems in autonomous driving, i.e., advanced sensor fusions, more sophisticated networks, and V2X & IoT technologies; and also the limitations brought by emerging 1550 nm LiDARs. In general, this work contributes a holistic overview of the obstacles and directions of ADS development in terms of adverse weather driving conditions.

Motivation & Objective

• Assess how weather phenomena impact ADS sensors and perception tasks.
• Survey hardware and algorithmic solutions for perception enhancement under adverse weather.
• Catalog datasets, simulators, and facilities supporting weather-related ADS research.
• Identify trends and future directions for robust autonomous driving in adverse weather.

Proposed method

• Statistical and analytic assessment of weather influences on ADS sensors.
• Review of sensor fusion and mechanical solutions for weather robustness.
• Organize perception enhancement methods by weather type with experimental validations.
• Discuss datasets, simulators, and weather facilities used in research.
• Highlight trends toward advanced fusion, networks, and V2XIoT in adverse conditions.

Experimental results

Research questions

• RQ1 How do rain, fog, snow, and other adverse weather phenomena quantitatively affect LiDAR, camera, radar, and other sensors?
• RQ2 What perception enhancement and sensor-robustness techniques mitigate weather-induced performance degradation?
• RQ3 What datasets, simulators, and facilities exist to study ADS under adverse weather, and what are their limitations?
• RQ4 What are the main trends and future directions in making ADS robust to adverse weather?

Key findings

• Weather phenomena impose measurable influences on sensors and perception, with varying severity across modalities.
• Advanced sensor fusion, more sophisticated networks, and V2X/IOT technologies are identified as key moving trends for robustness.
• Limitations of emerging 1550 nm LiDARs are discussed as a bottleneck for weather-robust sensing.
• The survey provides a holistic overview linking hardware and computer science solutions for adverse weather.
• Experimental validations are reported for perception-enhancement approaches under adverse weather.