Motion Pattern Object Classification Using Doppler Coherent LiDAR
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous vehicle technologies face challenges in accurately and efficiently classifying moving objects in driving environments, particularly due to the inability to effectively utilize velocity data for motion pattern recognition.
Innovation Solution
The implementation of a method and system that utilize Doppler-assisted velocimetry data to classify objects based on their motion patterns, employing coherent lidar technology to detect radial velocities and segment point clouds into clusters representing distinct objects and their motions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If velocity data is collected using coherent lidar technology, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent uses Doppler effect as an intermediary mechanism to extract velocity information from reflected lidar signals. Instead of directly measuring velocity, the system measures frequency shifts caused by the Doppler effect, which serves as a mediator between the lidar sensor and the moving objects, enabling precise velocity measurement without direct contact or complex mechanical sensors.
Solution Approach 2:
The patent replaces traditional mechanical velocity sensors (such as radar or dedicated speed sensors) with coherent lidar technology that uses optical interference and Doppler frequency analysis. This substitution eliminates mechanical moving parts and uses electromagnetic field interactions to achieve velocity measurement, reducing mechanical complexity while improving precision.
2Measurement precision
If motion pattern recognition is implemented using velocity data, then classification accuracy is improved, but loss of time in data processing increases
Solution Approach 1:
The patent performs preliminary clustering of return points based on spatial coordinates before applying velocity-based classification. By pre-organizing the data structure and identifying potential object groups based on position, the system reduces the computational complexity of subsequent velocity analysis, enabling faster processing while maintaining high classification accuracy.
Solution Approach 2:
The patent segments the point cloud data into distinct clusters representing different objects based on spatial proximity, then analyzes velocity patterns within each cluster separately. This segmentation approach breaks down the complex task of classifying all points simultaneously into smaller, more manageable sub-tasks, reducing overall processing time while improving classification precision through focused analysis.
3Measurement precision
If point clouds are segmented into clusters representing distinct objects, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent applies segmentation by clustering return points based on spatial coordinates to separate different objects in the environment. This divides the complex point cloud data into manageable clusters, each representing a distinct object, enabling precise measurement and classification while using efficient clustering algorithms to minimize processing complexity.
Solution Approach 2:
The patent implements a two-stage processing approach where not all return points are fully analyzed with velocity data - instead, points are first grouped into clusters based on simple spatial criteria, and then velocity-based classification is applied selectively. This partial application of complex processing reduces overall computational burden while maintaining high precision for object detection.
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 precise and efficient classification of objects, such as pedestrians and vehicles, by analyzing their motion patterns, thereby improving the accuracy and safety of autonomous driving systems.
Implementation Method 1
A coherent sensor (e.g., a coherent light detection and ranging (lidar) sensor) may be employed to sense both the spatial locations of the objects and the velocities of such objects, including by determining a Doppler frequency shift of the reflected signals
Data Source
AI summary
Aspects and implementations of the present disclosure address shortcomings of the existing technology by enabling motion pattern-assisted object classification of objects in an environment of an autonomous vehicle (AV) by obtaining, from a sensing system of the AV, a plurality of return points, each return point comprising one or more velocity values and one or more coordinates of a reflecting region that reflects a signal emitted by the sensing system, identifying an association of the plurality of return points with an object in an environment of the AV, identifying, in view of the one or more velocity values of at least some of the plurality of return points, a type of the object or a type of a motion of the object, and causing a driving path of the AV to be determined in view of the identified type of the object.