Stereo Radar Velocity Image Generation for Vehicle Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Vehicle radar systems using radial speed measurements provide limited information about object movement, failing to capture lateral movement and often struggle with distinguishing between multiple objects, especially in complex scenarios, leading to challenges in accurately predicting object trajectories and intents.
Innovation Solution
Utilizing stereo radars positioned at different locations on a vehicle to generate multi-axis radar velocity images, which are processed by neural networks to estimate velocity vectors and attribute information such as pose, orientation, and intent of objects, enhancing object detection and navigation capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If single radar radial speed measurements are used, then the system is simple, but the measurement precision of object velocity is insufficient
Solution Approach 1:
The patent combines data from multiple radars positioned at different locations on the vehicle to generate multi-axis velocity images. By merging the radial velocity measurements from at least two radars, the system achieves more precise velocity vector estimation than any single radar could provide alone, resolving the contradiction between measurement precision and device complexity.
Solution Approach 2:
The patent transitions from single-axis radial velocity measurements to multi-axis velocity imaging by incorporating measurements from multiple radars at different positions. This dimensional expansion allows the system to reconstruct full velocity vectors (including lateral components) that cannot be obtained from a single radar's line-of-sight measurement alone.
2Adaptability or versatility
If multiple objects are present in complex scenarios, then the detection coverage is comprehensive, but the difficulty of detecting and measuring increases
Solution Approach 1:
The patent segments the velocity information into multi-axis components by processing data from multiple radars independently and then combining them. This segmentation approach allows the system to handle complex scenarios with multiple objects by treating each object's velocity vector as a separate entity that can be independently reconstructed from the combined radar measurements.
Solution Approach 2:
The patent applies local quality by generating velocity images with different resolutions or processing depths for different regions of interest. The neural network can focus computational resources on critical areas with multiple objects while maintaining adequate detection capability in other regions, thereby managing the complexity of detecting and measuring multiple objects effectively.
3Reliability
If stereo radars are used to generate multi-axis velocity images, then the reliability of object detection is improved, but the loss of energy increases
Solution Approach 1:
The patent implements partial action by using at least two radars rather than a full array, and by processing velocity images at appropriate resolutions. The system performs sufficient radar measurements to achieve reliable velocity vector estimation without unnecessarily increasing the number of radars or processing power, thereby balancing detection reliability with energy consumption.
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
Enables quicker and more reliable object detection by providing comprehensive 3D positional data, improving vehicle navigation and collision avoidance in various weather conditions, particularly in adverse weather scenarios where optical sensors may fail.
Implementation Method 1
The vehicle radar system emits a radio signal from a transmitter, which then bounces off nearby objects and returns to a receiver
Implementation Method 2
By analyzing the characteristics of the returned signal, the vehicle radar system can determine the location, speed, and direction of objects
Data Source
AI summary
Example embodiments relate techniques and systems for generating multi-axis radar velocity images using stereo radar. A vehicle radar system receives radar first radar data from a first radar and second radar data from a second radar, which are coupled at different locations on a vehicle traveling in an environment. The system determines a first radial speed and a second radial speed for an object based on the first and second radar data, respectively, and then estimates a velocity vector for the object relative to the vehicle based on the first and second radial speeds. The system can provide the estimated velocity vector as an input into a neural network and enable vehicle systems to control the vehicle based on the output from the neural network.