Trailer Pose Localization Using Sector LIDAR Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomy-related technologies face challenges in accurately and efficiently localizing autonomous tractor-trailers within their surroundings, particularly in reducing computational resources and mitigating saturated data points for trailer identification.
Innovation Solution
The method involves generating trailer pose instances using LIDAR data, specifically utilizing phase coherent and polarized LIDAR components, and motion-compensated point clouds to reduce search space and eliminate saturated data, thereby enhancing localization accuracy and resource efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional LIDAR components and full LIDAR data processing are used for trailer identification, then comprehensive data coverage is achieved, but computational resources are wasted and processing efficiency decreases
Solution Approach 1:
The patent segments the LIDAR data processing by dividing the full LIDAR point cloud into multiple sections and identifying only the relevant section containing the trailer. This selective processing approach processes only the necessary portion of data rather than the entire dataset, thereby improving identification efficiency while reducing computational resource consumption.
2Measurement precision
If conventional LIDAR sensors are used without phase coherent or polarization components, then device simplicity is maintained, but saturated data points from certain materials reduce localization accuracy
Solution Approach 1:
The patent changes the physical parameters of the LIDAR sensor by incorporating phase coherent detection capabilities and polarization components. These parameter changes enable the sensor to differentiate between saturated and non-saturated data points through phase and polarization information, thereby improving measurement precision for trailer localization despite the increased device complexity.
3Measurement precision
If motion-compensated point clouds are not used, then processing speed is maintained, but the moving LIDAR sensor creates inaccurate trailer identification
Solution Approach 1:
The patent applies motion compensation as a preliminary action before trailer identification. By pre-compensating for the LIDAR sensor's motion based on known vehicle movement data, the system creates accurate point clouds that account for sensor displacement. This preliminary correction ensures accurate trailer detection without requiring slower processing speeds during the actual identification phase.
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 reduces computational waste by focusing on a sector area predicted to include the trailer, resulting in more reliable and accurate trailer pose instances for controlling the autonomous tractor-trailer.
Implementation Method 1
a LIDAR sensor that includes a phase coherent LIDAR component
Implementation Method 2
a LIDAR sensor that includes a polarization LIDAR component
Data Source
AI summary
Systems and methods for localization of a trailer of an autonomous tractor-trailer are described herein. Some implementations can determine a sector area in an environment of the autonomous tractor-trailer that is predicted to include the trailer, determine a subset of an LIDAR data that is generated by LIDAR sensor(s) of an autonomous tractor of the autonomous tractor-trailer and that is predicted to include the trailer based on the sector area, generate a trailer pose instance of a trailer pose of the trailer based on the subset of the LIDAR data, and cause the trailer pose instance to be utilized in controlling the autonomous tractor-trailer. Additional or alternative implementations can utilize particular LIDAR sensor(s) in generating the trailer pose instance, such as phase coherent LIDAR sensor(s) or polarized LIDAR sensor(s).