Automated Vehicle Sensor Control System Field of View Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated vehicles equipped with different sensors, such as cameras, radar units, and lidar units, face challenges in efficiently detecting and classifying objects due to the limitations of each sensor technology, leading to increased data processing burdens and reduced accuracy in object identification.
Innovation Solution
A sensor-control system that utilizes a first sensor to detect object locations and select the field of view for a second sensor with a different sensing technology, optimizing data processing and object classification by determining the appropriate field of view based on the detected object's location and characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple sensors with different sensing technologies are used to detect objects, then object detection reliability is improved, but data processing burden increases
Solution Approach 1:
The system segments the sensing and processing tasks by dividing the field of view into multiple zones, with each sensor responsible for specific zones. This segmentation allows the controller to process data from each sensor independently and efficiently, reducing the overall processing burden while maintaining reliable detection across the entire field of view.
Solution Approach 2:
The controller preliminarily determines a field of view based on sensor data before triggering detailed processing. By pre-identifying relevant areas and filtering out unnecessary data, the system prepares the data stream in advance, reducing the computational load during critical detection and classification operations.
2Area of stationary object
If the field of view of the second sensor is set to cover the entire area, then object detection coverage is improved, but data processing load increases
Solution Approach 1:
Different zones within the field of view are assigned different levels of processing priority and attention. High-priority zones requiring detailed classification receive focused processing resources, while low-priority zones use simpler detection methods. This local differentiation maintains comprehensive coverage while optimizing processing efficiency for each area.
Solution Approach 2:
The system applies partial processing to the entire field of view by using simplified detection methods for most areas and reserving detailed classification processing only for specific zones of interest. This partial action approach maintains adequate detection coverage while significantly reducing the overall data processing load.
3Productivity
If the field of view of the second sensor is reduced based on object location, then data processing load is reduced, but detection accuracy may worsen
Solution Approach 1:
The field of view of the second sensor is dynamically adjusted based on the detected object's location and characteristics. The system continuously adapts the sensing parameters and processing resources allocated to different zones, maintaining high detection accuracy for relevant objects while reducing processing load for less critical areas.
Solution Approach 2:
The controller uses feedback from the first sensor's object location data to adjust the second sensor's field of view and processing priorities. This feedback loop ensures that detection accuracy is maintained for objects of interest while dynamically optimizing processing efficiency based on real-time conditions.
Data Source
AI summary
A sensor-control system for operating an automated vehicle includes a first sensor, a second sensor, and a controller. The first sensor is used to detect objects proximate to a host-vehicle. The first sensor is characterized by a first-sensing-technology. The second sensor is used to detect objects proximate to the host-vehicle. The second sensor is characterized by a second-sensing-technology different from the first-sensing-technology. The controller is in communication with the first sensor and the second sensor. A location of an object detected by the first-sensor is used to select a field-of-view of the second-sensor.