Dual-Lidar Denoising for Particulate False Return Suppression
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Lidar systems produce false positive detections due to reflections from fine particulate matter such as fog, smoke, and debris, which can obscure true detections and lead to unsafe vehicle maneuvers.
Innovation Solution
A method using two lidar sensors to cluster lidar points and apply metric-based or machine-learned approaches to suppress false returns by determining differences in range and classifying points as irrelevant to vehicle travel, thereby improving detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If lidar systems detect all reflected light signals, then detection sensitivity is improved, but false positive detections increase due to particulate matter reflections
Solution Approach 1:
The patent segments the lidar detection process into multiple stages: initial detection of all reflected light signals, followed by classification of detected points into true objects versus particulate matter using machine learning models. This segmentation allows the system to maintain high detection sensitivity while filtering out false positives through systematic categorization of detected signals.
Solution Approach 2:
The patent introduces machine learning classification models as intermediary components between the lidar sensor and the final detection output. These models act as mediators that analyze characteristics of reflected light signals and determine whether they originate from solid objects or particulate matter, thereby resolving the contradiction between detecting all signals and filtering false positives.
2Reliability
If lidar systems suppress returns from particulate matter, then false positive detections are reduced, but detection of true objects in adverse conditions deteriorates
Solution Approach 1:
The patent changes the parameters used for lidar signal analysis by incorporating multiple characteristics (intensity, range, clustering patterns, temporal variations) into the machine learning classification process. By analyzing multiple parameters simultaneously, the system can distinguish true objects from particulate matter more accurately, maintaining detection accuracy while suppressing false positives.
Solution Approach 2:
The patent implements feedback mechanisms where the machine learning models continuously learn from detected patterns and adjust their classification thresholds. The system uses feedback from classified results to refine its discrimination between true objects and particulate matter, improving reliability without sacrificing detection accuracy in adverse conditions.
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
Enhances the safety and accuracy of vehicle operations by reducing false returns and ensuring detection of true positives, even in adverse weather conditions, by distinguishing between solid objects and particulate matter.
Implementation Method 1
When the emitted light is incident on a surface, a portion of the light is reflected and received by the light sensor
Implementation Method 2
fine particulate matter may also reflect light. Problematically, fog, smoke, fog, exhaust, steam, and other such vapors may reflect light emitted by a lidar system
Implementation Method 3
the system may measure the propagation time of a light signal as it travels from the laser emitter, to the surface, and back to the light sensor. A distance is then calculated based on the flight time and the known speed of light
Data Source
AI summary
Particulate matter, such as fog, snow, rain, steam, vehicle exhaust, debris (plastic bags), etc. may cause one or more sensor types to generate false positive solid surface detections. In particular, various depth measurements may be impeded by particulate matter. Identifying false positive return(s) may comprise clustering lidar points, determining differences in range indicated by two different lidar devices having lidar points in the cluster, determining first differences that are more negative than a negative difference threshold and second differences that are more positive than a positive difference threshold, determining a first portion of lidar data in the cluster associated with the first differences and the second differences is associated with particulate matter or debris, and controlling a vehicle based at least in part on suppressing the first portion of the lidar data or indicating that the first portion of the lidar data is associated with particulate matter or debris.