Dynamic Computational Resource Allocation for Peripheral Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Advanced driver-assistance and autonomous driving systems face computational resource deficiencies, leading to inadequate recognition of objects in the vehicle's surroundings due to prioritization of high-priority sensing processes, which can result in missed detections.
Innovation Solution
A peripheral recognition device that dynamically allocates computational resources based on the moving environment, using a control unit to determine resource allocation rates for each sensing process, ensuring appropriate object detection within available resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If computational resources are prioritized for high-priority sensing processes, then detection accuracy for critical objects is improved, but computational resources for low-priority sensing processes become deficient, causing missed detections
Solution Approach 1:
The patent implements dynamic allocation of computational resources to sensing processes based on real-time evaluation of moving environment and object characteristics. The control unit adjusts resource distribution dynamically, allowing the system to adapt resource allocation to changing detection requirements rather than using fixed priority assignments
Solution Approach 2:
The system changes the parameter of computational resource allocation by evaluating multiple factors including moving environment, object distance, object size, and object type. These parameter changes enable the system to optimize detection accuracy for critical objects while maintaining adequate resource allocation for other sensing processes
2Measurement precision
If a large amount of computational resources is allocated to increase detection accuracy, then sensing range and detection resolution are improved, but computational resource deficiency occurs when simultaneously performing multiple sensing processes
Solution Approach 1:
The patent applies local quality by allocating different amounts of computational resources to different sensing processes based on their specific requirements and the characteristics of objects in their respective monitoring areas. High-resource allocation is applied locally to critical detection tasks while lower resources are allocated to less critical areas
Solution Approach 2:
The system dynamically adjusts computational resource allocation across multiple sensing processes based on real-time evaluation of the moving environment. This dynamic approach allows the system to maintain high detection accuracy for critical objects while efficiently managing overall sensing throughput
Data Source
AI summary
A control unit (21) determines an allocation rate of computational resources to be allocated to each of a plurality of sensing processes of analyzing sensor data output from a plurality of sensors that observe an area around a moving body (100), based on a moving environment of the moving body (100), such as the type of a road where the moving body (100) travels, behavior of the moving body (100), and visibility from the moving body (100). A detection unit (22) detects an object in the area around the moving body (100) by using, for a corresponding sensing process, computational resources of an allocated amount specified based on the allocation rate determined by the control unit (21).