Overlapping LiDAR Sensing for Blooming-Corrected Object Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Lidar sensors experience blooming, causing detected objects to appear larger than they are due to reflected light bleeding into adjacent photodetectors, leading to inaccurate vehicle control and potential safety issues.
Innovation Solution
Utilizing multiple lidar sensors with overlapping fields of view to detect and correct for blooming by identifying differences in sensor data patterns, such as azimuthal extent and range variations, and removing or flagging returns associated with blooming.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single lidar sensor is used to detect objects, then the device complexity is reduced, but measurement precision deteriorates due to blooming causing objects to appear larger than they are
Solution Approach 1:
The patent combines data from multiple lidar sensors with overlapping fields of view to detect and correct blooming artifacts. By merging the sensor data and comparing azimuthal extent measurements across sensors, the system achieves more accurate object size measurements while compensating for the blooming effect that causes objects to appear larger than they actually are.
2Reliability
If lidar sensor data is used directly for vehicle control, then the response time is reduced, but reliability deteriorates due to blooming-induced inaccuracies leading to sudden and energetically inefficient vehicle actions
Solution Approach 1:
The patent performs preliminary detection and correction of blooming artifacts in the lidar data before the data is used for vehicle control decisions. By identifying and removing blooming-induced distortions in advance, the system ensures that subsequent control actions are based on accurate object representations, preventing sudden and energetically inefficient vehicle responses while maintaining timely decision-making.
3Area of stationary object
If multiple photodetectors are used in a lidar sensor to increase detection coverage, then the field of view is improved, but object-generated harmful factors worsen due to reflected light bleeding into adjacent photodetectors causing blooming
Solution Approach 1:
The patent uses feedback from multiple lidar sensors with overlapping fields of view to detect blooming artifacts. By comparing the azimuthal extent measurements of the same object across multiple sensors, the system identifies discrepancies caused by light bleeding into adjacent photodetectors and corrects these measurements, thereby compensating for the blooming distortion that results from using multiple photodetectors to expand field of view coverage.
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
Improves the accuracy of vehicle control by providing a more precise representation of the environment, reducing sudden and energetically inefficient actions, and enhancing safety by correcting for blooming-induced distortions.
Implementation Method 1
A lidar sensor can measure distances to visible surfaces by emitting light and measuring properties of light reflected from those surfaces
Implementation Method 2
A lidar sensor can measure distances to visible surfaces by emitting light and measuring properties of light reflected from those surfaces
Implementation Method 3
a lidar sensor may comprise multiple photodetectors corresponding to different positions of detected objects
Data Source
AI summary
Techniques comprise receiving sensor data comprising first sensor data collected by a first lidar sensor and a second sensor data collected by a second lidar sensor of a vehicle. An object is detected based at least in part on the first sensor data and the second sensor data. A difference between the first sensor data associated with the object and the second sensor data associated with the object is determined, the difference corresponding with blooming of the first sensor data or the second sensor data. The vehicle is controlled based at least in part on the difference between the first sensor data and the second sensor data.