Infant Track Velocity Transfer Using Radar-Lidar Association
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles require precise position and velocity information from surrounding actors, which lidar provides efficiently but with latency, while radar offers instantaneous doppler information with noise, leading to latency in velocity estimation.
Innovation Solution
A system that classifies tracks as infant or mature based on sensor type, number of detections, object type, and speed, then uses radar data to modify velocity for infant tracks, associating and dealiasing radar detections to reduce latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If lidar sensor is used to capture precise position, then position accuracy is improved, but velocity estimation latency increases
Solution Approach 1:
The patent combines lidar position data with radar velocity data into a unified track object. The lidar sensor provides precise position information while the radar sensor provides instantaneous velocity information through Doppler effect measurement. By merging these complementary data sources, the system achieves both high position accuracy and low velocity latency.
Solution Approach 2:
The track object serves as an intermediary that integrates information from multiple sensors. The track manager receives detections from both lidar and radar sensors, associates them with existing tracks, and maintains unified position and velocity information. This intermediary structure allows seamless fusion of complementary sensor data.
2Loss of time
If radar sensor is used to provide instantaneous velocity, then velocity latency is reduced, but measurement noise increases
Solution Approach 1:
The system merges radar velocity measurements with lidar position-based velocity estimates. The radar provides instantaneous velocity data while the lidar provides complementary position information that can be used to calculate velocity. By combining these sources, the system reduces radar-specific noise while maintaining low latency.
Solution Approach 2:
The track manager uses feedback mechanisms to continuously update track information based on new sensor detections. When radar detections are noisy or unreliable, the system can rely more on lidar-based velocity estimates, and vice versa. This adaptive feedback approach optimizes the use of each sensor based on current conditions.
3Reliability
If multiple sensor detections are accumulated to initialize a track, then track reliability is improved, but initialization time increases
Solution Approach 1:
The patent implements dynamic track initialization thresholds that adapt based on sensor type and detection quality. For high-confidence radar detections, the system can initialize tracks with fewer detections, while for noisier sensor types, more detections are required. This dynamic approach balances reliability requirements with initialization speed.
Solution Approach 2:
Different initialization requirements are applied to different sensor types and track contexts. The system evaluates detection quality, sensor reliability, and track state locally to determine appropriate initialization thresholds. This allows flexible trade-offs between reliability and speed depending on specific conditions.
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
Reduces latency in velocity estimation by fusing radar doppler information with lidar, providing instantaneous velocity data for improved autonomous vehicle operations.
Implementation Method 1
a radar sensor provides instantaneous doppler information
Data Source
AI summary
Disclosed herein are systems, methods, and computer program products for operating a sensor system. The methods comprise: receiving, by a computing device, a track for an object; classifying, by the computing device, the track as an infant track or a mature track based on a type of sensor detection used to generate the track, a total number of cycles in which the lidar detections were generated, a total number of sensor detections included in the track, an object type associated with the track, an object speed, and/or a distance between the object and the sensor system; using, by the computing device, radar data to modify a speed of the track in response to the track being classified as an infant track.