Doppler-Assisted Object Mapping for Faster AV Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous driving systems face challenges in accurately and efficiently identifying and tracking objects in dynamic environments due to limitations in conventional lidar technology, which struggles with distinguishing objects based on distance and velocity data from single sensing frames.
Innovation Solution
The implementation of Doppler-assisted velocity sensing using coherent lidars, which utilize phase information to detect radial velocities and enhance object identification and tracking by discarding inconsistent hypotheses and forming more accurate motion models based on velocity data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional lidar technology is used for object detection, then the system can detect objects based on distance data, but the system cannot accurately distinguish and track objects in dynamic environments due to insufficient velocity information
Solution Approach 1:
The patent transitions from conventional lidar that only measures distance (one dimension) to coherent lidar that measures both distance and velocity (adding a temporal dimension through phase information). This dimensional expansion enables the system to distinguish stationary objects from moving objects and accurately track dynamic targets in complex environments.
Solution Approach 2:
The patent changes the measurement parameters from purely spatial (distance) to spatio-temporal (distance and velocity). By utilizing the phase information of coherent light, the system extracts velocity data as an additional parameter, transforming the detection capability from static range measurement to dynamic motion analysis.
2Reliability
If multiple sensing data frames are collected to improve object tracking, then more velocity information is obtained, but the processing time and computational complexity increase
Solution Approach 1:
The patent replaces complex mechanical processing of multiple sensing frames with a more efficient optical-based coherent detection system. The coherent lidar directly encodes velocity information in the phase of the returned light, allowing the system to obtain velocity data from single or fewer frames rather than requiring extensive temporal sequences for analysis.
3Measurement precision
If coherent lidar with Doppler sensing is implemented, then velocity information is obtained to improve object identification, but the device complexity increases
Solution Approach 1:
The patent implements a coherent lidar system that performs multiple functions simultaneously: it measures both distance and velocity using the same optical hardware. The single-shot ranging and Doppler velocity measurement capabilities are integrated into one system, eliminating the need for separate sensing devices and reducing overall system complexity despite the enhanced functionality.
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 improves the precision and speed of object identification and tracking by providing additional velocity information, allowing for more efficient formation and verification of hypotheses, leading to better navigation and obstacle avoidance in autonomous vehicles.
Implementation Method 1
Doppler-assisted velocity sensing using coherent lidars, which utilize phase information to detect radial velocities
Data Source
AI summary
Aspects and implementations of the present disclosure address shortcomings of the existing technology by enabling efficient object identification and tracking in autonomous vehicle (AV) applications by using velocity data-assisted mapping of first set of points obtained for a first sensing data frame by a sensing system of the AV to a second set of points obtained for a second sensing data frame by the sensing system of the AV, the first set of points and the second set of points corresponding to an object in an environment of the AV, and causing a driving path of the AV to be determined in view of the performed mapping.