Lidar Intensity Normalization via Channel Median Multipliers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Lidar intensity values in autonomous vehicles are non-uniform due to signal noise and environmental factors, leading to inaccuracies in localization, perception, prediction, and motion planning.
Innovation Solution
A method for normalizing Lidar intensity values by determining an intensity normalization multiplier for each channel based on median intensity values and predefined reflectivity values, using a reference map to align intensity returns with surface reflectivity, and recalculating periodically to account for temperature changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If Lidar intensity values are used directly from each channel, then the system provides ranging information and surface reflectivity data, but the intensity values are non-uniform and inaccurate due to signal noise and environmental factors
Solution Approach 1:
The patent introduces an intermediary normalization process that mediates between the raw Lidar intensity measurements and the final intensity values used for localization and perception. A normalization multiplier is calculated based on reference data and applied to correct the raw intensity values, effectively filtering out noise and environmental interference while preserving the underlying reflectivity information.
Solution Approach 2:
The system implements feedback by using reference map data and historical intensity information to calculate normalization multipliers. These multipliers are derived from comparing expected reflectivity values with actual measured intensities, creating a closed-loop correction mechanism that continuously improves measurement accuracy by compensating for systematic errors and environmental variations.
2Measurement precision
If intensity normalization is applied to each channel, then uniformity and accuracy of intensity values improve, but computational complexity and processing time increase
Solution Approach 1:
The patent applies preliminary action by pre-calculating normalization multipliers using reference map data and historical information before processing real-time Lidar data. This allows the system to establish correction factors in advance based on known surface reflectivity characteristics, reducing the computational burden during real-time operation while maintaining high normalization accuracy.
3Reliability
If normalization multipliers are recalculated frequently, then accuracy is maintained under changing environmental conditions, but processing time and computational load increase
Solution Approach 1:
The system implements periodic action by recalculating normalization multipliers at predetermined time intervals rather than continuously. This periodic recalculation strategy maintains accuracy under changing environmental conditions such as temperature variations while avoiding excessive computational overhead by updating normalization factors only when necessary, striking a balance between reliability and processing efficiency.
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 method provides more accurate and detailed information about reflected surfaces and objects, improving autonomous vehicle localization, perception, and motion planning by ensuring consistency across Lidar channels.
Implementation Method 1
The Lidar unit also includes circuitry to measure the time of flight—i.e., the elapsed time from emitting the laser signal to detecting the return signal.
Implementation Method 2
The intensity of the return signal provides information about the surface reflecting the signal
Data Source
AI summary
Aspects of the present disclosure involve a vehicle computer system comprising a computer-readable storage medium storing a set of instructions, and a method for online light detection and ranging (Lidar) intensity normalization. Consistent with some embodiments, the method may include accumulating point data output by a channel of a Lidar unit during operation of an autonomous or semi-autonomous vehicle. The accumulated point data includes raw intensity values that correspond to a particular surface type. The method further includes calculating a median intensity value based on the raw intensity values and generating an intensity normalization multiplier for the channel based on the median intensity value. The intensity normalization multiplier, when applied to the median intensity value, results in a reflectivity value that corresponds to the particular surface type. The method further includes applying the intensity normalization multiplier to the point data output by the channel to produce normalized intensity values.