Lidar Trailer Pose Tracking for Articulated Vehicle Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for detecting the positioning of a trailer in autonomous vehicles are not sufficiently accurate, especially when the trailer is not aligned with the tractor, and can be adversely affected by sensor signal variations due to the trailer's orientation during turns.
Innovation Solution
Utilizing onboard Lidar sensors to analyze sensor data for identifying and tracking the pose of the trailer, incorporating a motion filter to smooth the estimated orientation, and determining the major face of the trailer based on sensor data to accurately determine its pose, which can be enhanced by using cameras to detect alignment marks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing sensor techniques are used to detect trailer positioning, then the system can operate with current hardware, but the measurement precision is insufficient especially when the trailer is not aligned with the tractor
Solution Approach 1:
The patent segments the sensor data processing into distinct stages: raw Lidar data acquisition, point cloud generation, trailer identification algorithms, pose estimation, and alignment calculation. This segmentation allows each stage to be optimized independently, improving overall measurement precision while managing computational complexity.
Solution Approach 2:
The patent introduces intermediate computational structures including point cloud representations, feature extraction layers, and alignment mark detection algorithms that serve as intermediaries between raw sensor data and final positioning results. These intermediaries transform complex sensor signals into interpretable geometric features, resolving the difficulty of direct signal interpretation.
2Adaptability or versatility
If the trailer orientation varies during turns, then the vehicle can navigate turns, but the sensor signal information becomes unreliable for accurate positioning
Solution Approach 1:
The patent implements dynamic adaptation of the sensing and processing system to accommodate varying trailer orientations during turns. The system continuously updates the point cloud representation and re-executes alignment mark detection algorithms in real-time, allowing the vehicle to maintain accurate positioning awareness while navigating turns with varying geometry.
Solution Approach 2:
The patent changes key processing parameters including Lidar scanning patterns, point cloud density thresholds, and alignment mark detection sensitivity based on detected trailer orientation and turn conditions. This dynamic parameter adjustment maintains sensor signal reliability across varying operational states including turns, straight-line travel, and articulated configurations.
3Measurement precision
If additional hardware is added to improve positioning accuracy, then measurement precision improves, but the device complexity increases
Solution Approach 1:
The patent makes the existing Lidar sensor system multi-functional by implementing software-based trailer identification, alignment mark detection, and pose estimation algorithms that extract multiple types of information from a single sensor source. This universal approach achieves high measurement precision for trailer positioning without adding dedicated hardware for each function, avoiding increased device complexity.
Solution Approach 2:
The patent creates virtual copies of physical features through computational methods: generating point cloud representations of the trailer, creating digital models of alignment marks, and synthesizing pose estimates from processed sensor data. These computational copies enable accurate positioning measurement without requiring additional physical sensing hardware, maintaining simple device architecture while achieving high precision.
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
Enables precise tracking of the trailer's pose, allowing the vehicle to operate in autonomous mode by accurately controlling its alignment and avoiding collisions, without requiring additional hardware.
Implementation Method 1
analyzing sensor data from one or more onboard Lidar sensors to identify and track the pose
Implementation Method 2
The received Lidar data points that are returned from the trailer
Data Source
AI summary
The technology relates to autonomous vehicles having articulating sections such as the trailer of a tractor-trailer. Aspects include approaches for tracking the pose of the trailer, including its orientation relative to the tractor unit. Sensor data is analyzed from one or more onboard sensors to identify and track the pose. The pose information is usable by on-board perception and/or planning systems when driving the vehicle in an autonomous mode. By way of example, on-board sensors such as Lidar sensors are used to detect the real-time pose of the trailer based on Lidar point cloud data. The orientation of the trailer is estimated based on the point cloud data, and the pose is determined according to the orientation and other information about the trailer. Aspects also include determining which side of the trailer the sensor data is coming from. A camera may also detect trailer marking information to supplement the analysis.