Lidar-Assisted Visibility-Reducing Media Detection in Autonomous Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately detecting and characterizing visibility-reducing media (VRM) such as fog, rain, and dust, which can impair sensor visibility and lead to sub-optimal responses to environmental conditions, as existing systems lack independent information to differentiate between reduced perception due to VRM or system malfunctions.
Innovation Solution
The implementation of lidar-assisted detection and characterization of VRM, where elongated reflected signals and multiple low-intensity returns are used to identify and quantify VRM, allowing for the determination of its density and impact on sensor visibility, utilizing reference objects with known properties to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional sensing systems are used without lidar-assisted detection, then the system complexity is lower, but the ability to detect and characterize visibility-reducing media is insufficient and cannot provide ground truth on visibility conditions
Solution Approach 1:
The patent combines traditional sensing systems with lidar technology to create an integrated detection system. The lidar sensor operates alongside existing sensors to provide complementary data specifically for detecting visibility-reducing media, merging the capabilities of both systems to achieve accurate VRM characterization without replacing the entire sensing infrastructure
Solution Approach 2:
The lidar sensor acts as an intermediary component that bridges the gap between traditional sensing systems and the need for accurate visibility condition detection. It provides independent ground truth measurements of VRM properties that other sensors cannot obtain, serving as a mediator that enhances overall system capability without requiring complete system redesign
2Measurement precision
If lidar-assisted detection with multiple low-intensity returns is used to identify VRM, then the detection accuracy of VRM characteristics is improved, but the data processing complexity increases
Solution Approach 1:
The patent segments the detection process into distinct stages: first identifying visibility-reducing media through multiple low-intensity return points, then separately characterizing the media using elongated reflected signals. This segmentation allows the system to process different types of data through specialized algorithms, reducing overall processing complexity while maintaining high characterization accuracy
Solution Approach 2:
The system applies partial action by focusing processing resources on specific signal characteristics that are most indicative of VRM properties. Rather than analyzing all returned signals equally, the system selectively processes elongated reflected signals and multiple low-intensity returns that provide the most valuable information about visibility conditions, optimizing the balance between accuracy and processing complexity
3Measurement precision
If reference objects with known properties are used to enhance VRM detection accuracy, then the measurement precision of VRM density is improved, but the requirement for additional calibration data increases system complexity
Solution Approach 1:
The system uses reference objects with known properties that are already present in the environment, such as road signs, vehicles, or other detectable objects. These objects serve themselves as calibration references without requiring external calibration equipment or additional system components. The known properties of these objects provide the baseline needed to calculate VRM density directly from the detection data
Solution Approach 2:
Reference objects serve multiple functions: they act as calibration standards for density measurement, provide spatial reference points for localization, and can themselves be detected and tracked as environmental objects. This multi-functionality reduces the need for separate calibration systems and infrastructure, as the same objects used for navigation and mapping also provide calibration data for VRM detection
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables quick and accurate detection and characterization of VRM, improving the safety and efficiency of autonomous driving by providing ground truth on visibility conditions and enabling more reliable prediction of driving patterns and road conditions.
Implementation Method 1
a plurality of return points, wherein each of the plurality of return points comprises i) a direction of a respective sensing signal emitted by the sensing system and reflected by an outside environment
Implementation Method 2
elongated reflected signals and multiple low-intensity returns are used to identify and quantify VRM
Data Source
Figure 1A
Figure 1B~2
Figure 3A~3B
AI summary
Aspects and implementations of the present disclosure address challenges of the existing technology by enabling lidar-assisted identification and characterization of visibility-reducing media (VRM) such as fog, rain, snow, dust in autonomous vehicle applications, using lidar sensing. VRM can be identified and characterized using a variety of techniques, including analyzing a spatial distribution of low-intensity lidar returns, detecting pulse elongation of VRM-returns associated with reflection from VRM, determining intensity of VRM-returns, determining reduction of intensity of returns from various reference objects, and other techniques.