Phase-Coherent LiDAR Object Classification for Autonomous Vehicle Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in reliably navigating complex environments due to limitations in collecting and interpreting environmental data, planning vehicle motion, and executing commands to ensure safe navigation.
Innovation Solution
The implementation of a method using phase coherent LIDAR data, which includes range-Doppler images and intermediate frequency waveforms, to determine the pose, classification, and velocity of objects in a vehicle's environment, enabling adaptive autonomous control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If phase coherent LIDAR data is used to determine object parameters, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent replaces traditional mechanical scanning LIDAR systems with phase coherent LIDAR technology that uses optical phase detection to measure object parameters. This substitution enables precise determination of object position, velocity, and classification through phase difference measurements of coherent light waves, achieving high measurement precision while reducing mechanical complexity
Solution Approach 2:
The patent utilizes phase coherent LIDAR to detect changes in optical phase parameters of reflected light waves. By measuring phase differences in the coherent light signals, the system can precisely determine object parameters such as distance, velocity, and classification without requiring complex mechanical structures, thus improving measurement precision while managing device complexity
2Reliability
If multiple LIDAR data types are processed, then reliability of environment perception is improved, but loss of time in data processing increases
Solution Approach 1:
The patent performs preliminary classification and filtering of LIDAR data points before full processing. By pre-identifying potential objects and their categories using phase coherent data characteristics, the system prepares data structures in advance that enable faster subsequent processing, thus improving reliability through comprehensive data analysis while reducing overall processing time
Solution Approach 2:
The patent segments the LIDAR point cloud data into multiple spatial regions and processes each region independently using parallel computation. This segmentation allows simultaneous processing of multiple data types (range, Doppler, intensity) across different spatial zones, improving environment perception reliability through comprehensive analysis while reducing total processing time through parallelization
3Reliability
If adaptive autonomous control is implemented, then safety of vehicle navigation is improved, but device complexity increases
Solution Approach 1:
The patent implements adaptive autonomous control that continuously receives feedback from phase coherent LIDAR data about object parameters, vehicle state, and environment conditions. The control system adjusts vehicle trajectory and speed in real-time based on this feedback, improving navigation safety through dynamic adaptation while using model predictive control algorithms to manage complexity through systematic decision-making frameworks
Solution Approach 2:
The patent employs dynamic control strategies that adapt vehicle behavior based on real-time LIDAR measurements of object velocity, distance, and classification. The control system transitions between different operational modes (cruising, braking, steering) dynamically in response to changing environmental conditions, improving safety through adaptability while using standardized control modules to manage system complexity
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 enhances the ability of autonomous vehicles to accurately determine object parameters and adapt their trajectory to avoid collisions, improving safety and reliability in complex environments.
Implementation Method 1
a LIDAR component to determine, based on instantaneous data from a sensing cycle, a pose and a classification for one or more objects in an environment of the vehicle. The phase coherent LIDAR data indicates, for each of a plurality of points in an environment, a corresponding range and a corresponding velocity
Implementation Method 2
phase coherent LIDAR data includes an intermediate frequency waveform generated based on mixing of a local optical oscillator with time delayed reflections during the corresponding sensing events
Implementation Method 3
transmits an encoded waveform to a plurality of points in an environment and detects, during a sensing cycle, a reflection of the encoded waveform from each of the plurality of points
Data Source
Figure 1
Figure 2A~2B
Figure 3A
AI summary
Determining classification(s) for object(s) in an environment of autonomous vehicle, and controlling the vehicle based on the determined classification(s). For example, autonomous steering, acceleration, and/or deceleration of the vehicle can be controlled based on determined pose(s) and/or classification(s) for objects in the environment. The control can be based on the pose(s) and/or classification(s) directly, and/or based on movement parameter(s), for the object(s), determined based on the pose(s) and/or classification(s). In many implementations, pose(s) and/or classification(s) of environmental object(s) 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.