Autonomous Vehicle Yaw Detection Using Phase-Coherent LIDAR
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately determining the yaw parameter of additional vehicles in their environment, which is crucial for safe navigation and control.
Innovation Solution
The method involves using phase coherent LIDAR data to identify and classify points corresponding to additional vehicles, and then determining their yaw parameters based on spatially offset data points and machine learning models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If phase coherent LIDAR data is used to determine yaw parameters of additional vehicles, then measurement precision of yaw rate is improved, but device complexity increases due to sophisticated data processing requirements
Solution Approach 1:
The LIDAR data processing is segmented into distinct functional modules: data reception from phase coherent LIDAR, point cloud generation, vehicle detection, yaw parameter calculation, and control adaptation. Each module handles a specific aspect of the processing chain, making the overall complex system manageable and maintainable while preserving measurement precision.
Solution Approach 2:
A processor acts as an intermediary between the phase coherent LIDAR component and the autonomous control system. This intermediary processes the raw LIDAR data to extract yaw parameters and translates them into control-relevant information, simplifying the interface between sensing and control while maintaining measurement accuracy.
2Reliability
If yaw parameters of additional vehicles are determined using spatially offset data points, then reliability of autonomous control is improved, but loss of time increases due to extensive data analysis
Solution Approach 1:
The system performs preliminary processing of LIDAR data to generate point clouds and detect vehicles before yaw parameter calculation. By preparing the data structure in advance and identifying vehicles of interest beforehand, the system reduces the computational burden during critical control moments, balancing reliability with timely response.
Solution Approach 2:
The system processes a subset of LIDAR data points that are spatially offset and relevant to yaw determination, rather than analyzing all collected points. This partial processing approach provides sufficient reliability for yaw parameter determination while reducing overall processing time and computational load.
3Measurement precision
If machine learning models are used to classify LIDAR data points, then measurement precision of vehicle identification is improved, but use of energy increases due to computational requirements
Solution Approach 1:
Machine learning models are applied selectively to classify only those LIDAR data points that have been identified as potentially corresponding to vehicles, rather than processing all points. This partial application of computationally intensive algorithms maintains high identification precision while reducing overall energy consumption.
Solution Approach 2:
The system performs preliminary vehicle detection and candidate identification before applying machine learning classification. This preliminary filtering reduces the number of data points requiring energy-intensive machine learning processing, thereby reducing overall energy consumption while maintaining identification 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
This approach enables the autonomous vehicle to adapt its control accordingly, ensuring safe navigation and avoiding potential collisions by accurately determining the yaw rate and direction of additional vehicles.
Implementation Method 1
receiving, from a phase coherent Light Detection and Ranging (LIDAR) component of a vehicle, a group of phase coherent LIDAR data points of a sensing cycle
Implementation Method 2
Each of the phase coherent LIDAR data points of the group indicates a corresponding range and a corresponding velocity
Data Source
AI summary
Determining an instantaneous vehicle characteristic (e.g., at least one yaw rate) of an additional vehicle that is in addition to a vehicle being autonomously controlled, and adapting autonomous control of the vehicle based on the determined instantaneous vehicle characteristic of the additional vehicle. For example, autonomous steering, acceleration, and/or deceleration of the vehicle can be adapted based on a determined instantaneous vehicle characteristic of the additional vehicle. In many implementations, the instantaneous vehicle characteristics of the additional vehicle are determined based on data from a phase coherent Light Detection and Ranging (LIDAR) component of the vehicle, such as a phase coherent LIDAR monopulse component and/or a frequency-modulated continuous wave (FMCW) LIDAR component.