Vehicle Surround Awareness Radar Layout With On-Sensor AI Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle-surrounding awareness systems using radar sensors have limited field of view and require expensive external processing units, making them costly and unsuitable for driver awareness without autonomous driving features.
Innovation Solution
A vehicle-surrounding awareness system utilizing two 180-degree mm-wave radar sensors with integrated digital processing capabilities, enabling classification and alert generation without the need for external domain controllers, using AI and low-throughput communication protocols.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If two corner radar sensors with 120-degree field of view are used, then the system cost is reduced, but the field of awareness is limited to 240 degrees
Solution Approach 1:
The patent changes the key parameter of field of view from 120 degrees to 180 degrees for the radar sensors. This parameter change allows two sensors to cover 330 degrees of awareness area, resolving the contradiction between limited coverage and system simplicity.
Solution Approach 2:
The patent positions the radar sensors on the rear corners of the vehicle rather than traditional side positions. This spatial reconfiguration maximizes the coverage area achieved by each 180-degree sensor, enabling superior awareness coverage without adding more sensors.
2Adaptability or versatility
If state of the art corner radar sensors are used for blind spot detection, then the system is suitable for autonomous driving, but the system cost increases due to expensive external processing units
Solution Approach 1:
The patent extracts the digital processing functionality from external domain controllers and integrates it directly into the radar sensor modules. This eliminates the need for expensive external processing units while maintaining full processing capability for object classification and alert generation.
Solution Approach 2:
The radar sensor modules perform their own digital processing of radar data, including point cloud generation and object classification, without requiring external processing units. This self-service capability reduces system cost while maintaining versatility.
3Device complexity
If two 180-degree mm-wave radar sensors with integrated processing are used, then system cost and power consumption are reduced, but the field of awareness must exceed 300 degrees
Solution Approach 1:
The patent changes the field of view parameter to exactly 180 degrees and positions sensors at rear corners with specific angular relationships. This precise parameter configuration achieves 330 degrees of coverage, meeting the requirement while maintaining cost-effectiveness.
Solution Approach 2:
The patent uses asymmetric positioning of the two radar sensors on the rear corners of the vehicle, with each sensor oriented to maximize coverage of different angular sectors. This asymmetric arrangement optimizes the total coverage area to exceed 300 degrees.
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
Provides a maximum field of awareness exceeding 300 degrees with reduced system cost and power consumption, enhancing driver safety and comfort by classifying objects and issuing alerts, while being independent of autonomous driving infrastructure.
Implementation Method 1
two mm-wave radar sensor modules, each having a field of view of 180 degrees
Implementation Method 2
The transmitting antenna transmits patterned radiation to an area adjacent to the vehicle
Data Source
Figure 1a~1b
Figure 2a~2b
Figure 3
AI summary
The proposed innovative vehicle awareness surrounding system, based on radar sensing, provides visual information to the vehicle driver, with a maximum field of awareness larger than 300 degrees, typically better than 330 degrees, an affordable total system cost, by using two radar modules, each having a 180-degree field of view, with processing on the radar module. There is no explicit need for processing on domain controllers or vehicle processing units, proposed for autonomous driving. The proposed system utilizes artificial intelligence methodology using radar point cloud data for classifying the objects around the vehicle. An artificial intelligence-backed classification is executed, being previously trained by sets of actual radar measurements annotated data. Additionally, the proposed system may issue alerts to the driver, provide information to the vehicle control system to make autonomous actions, and wirelessly send surrounding data to the cloud. Moreover, the proposed system may provide parking support.