LiDAR Missing Measurement Detection for Autonomous Driving in Rain

Autonomous driving in rain remains challenging. Rain causes sensor performance degradation that can affect sensor measurement quality. During the rain, lasers may suffer from energy loss due to raindrop absorption. As a result, some laser measurements reflected from obstacles may not be recognized by the LiDAR sensor, thus raising potential risks for autonomous vehicles. This work investigates a novel task that aims to detect those missing measurements. Our solution uses a two-stage learning method to generate an anomaly score for each missing measurement, representing the likelihood of being caused by rain. We evaluate our method with real-world data and demonstrate its effectiveness in identifying anomalous missing measurements through qualitative and quantitative experiments.

Authors

• Chen Zhang 0018
• Zefan Huang
• Marcelo H. Ang
• Daniela Rus

Keywords

• Degradation
• Rain
• Laser radar
• Snow
• Measurement by laser beam
• Robot sensing systems
• Loss measurement
• Autonomous Vehicles
• Laser Measurement
• Anomaly Score
• Model Performance
• Convolutional Neural Network
• Binary Classification
• Quantitative Evaluation
• Laser Beam
• Extreme Weather
• Attention Mechanism
• Mean Accuracy
• Unlabeled Data
• Anomaly Detection
• Semi-supervised Learning
• Normal Class
• Transformer Architecture
• Static Scenes
• Rainy Weather
• LiDAR Scans
• Transformer Block
• Clear Weather
• 3D LiDAR
• Lidar Measurements
• Semantic Segmentation
• Dynamic Objects
• Static Environment
• Research Problem
• Skip Connections
• Field Of View
• Quantitative Evaluation Results