Lidar Trailer Pose Estimation Using Point Clouds and Alignment Marks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for detecting the pose of a trailer in autonomous vehicles are not sufficiently accurate, especially when the trailer is oriented relative to the tractor during turns, affecting the vehicle's ability to operate in autonomous mode.
Innovation Solution
The system uses onboard Lidar sensors to analyze sensor data, identify and track the pose of the trailer by estimating its orientation and determining the major face from the received data points, smoothing the orientation with a motion filter, and using alignment marks for precise positioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional sensor techniques are used to detect trailer pose, then the system can operate with simpler equipment, but the measurement precision is insufficient for autonomous mode operation
Solution Approach 1:
The patent replaces traditional mechanical or simple optical sensing methods with Lidar (Light Detection and Ranging) technology. The Lidar system uses laser beams to measure distances and detect the trailer's pose with high precision, substituting mechanical measurement approaches with optical-based laser ranging to achieve the required accuracy for autonomous operation.
Solution Approach 2:
The patent transitions from 2D camera-based detection to 3D spatial measurement using Lidar. By utilizing three-dimensional point cloud data and range measurements from multiple angles, the system achieves comprehensive pose detection including position, orientation, and articulation angle with significantly improved precision over traditional 2D imaging methods.
2Productivity
If the vehicle operates in autonomous mode with trailer tracking, then the productivity increases, but the reliability decreases due to sensor signal variations during turns
Solution Approach 1:
The patent implements a feedback mechanism where the Lidar system continuously monitors the trailer's pose and provides real-time data to the control system. The system processes sensor signals from multiple angles and uses feedback algorithms to compensate for signal variations during turns, maintaining reliable tracking throughout the autonomous operation cycle.
Solution Approach 2:
The Lidar system is designed to perform multiple functions: detecting the trailer's position, orientation, articulation angle, and relative motion simultaneously. This multi-functional sensor platform maintains consistent performance across various operating conditions including straight-line travel, turning, and different articulation states, ensuring reliability throughout diverse autonomous operation scenarios.
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 enables accurate tracking of the trailer's pose, enhancing the vehicle's ability to operate in autonomous mode by improving the accuracy of sensor data interpretation and maintaining vehicle stability during turns.
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
Figure 1A~1B
Figure 1C~1D
Figure 2A
AI summary
The technology relates to autonomous vehicles having articulating sections such as the trailer of a tractor-trailer (Figs. 1A-D). Aspects include approaches for tracking the pose of the trailer, including its orientation relative to the tractor unit (502). Sensor data is analyzed from one or more onboard sensors (232) 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 (1002). The orientation of the trailer is estimated based on the point cloud data (1004), and the pose is determined according to the orientation and other information about the trailer (1006). 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.