Vehicle Data Recorder Resource Segmentation for Overwhelming Stimuli
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Vehicle data recorders are vulnerable to being overwhelmed by malicious stimuli, such as strobe lights, which can cause significant delays in processing normal sensor inputs and impact real-time operations, leading to potential safety issues in autonomous driving systems.
Innovation Solution
Implementing a resource management system that isolates overwhelming stimuli by using a time-sliced approach, where a subset of resources processes the malicious stimuli while the remaining resources handle normal inputs in real-time, utilizing an artificial neural network to optimize the width of the time-sliced portion and adjust based on operating parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all resources are used to process sensor inputs sequentially, then processing completeness is improved, but processing speed and real-time performance deteriorate when overwhelming stimuli are present
Solution Approach 1:
The patent divides the processing resources into multiple independent subsets (first subset and second subset of processing cores). This segmentation allows parallel processing of different input streams, where normal sensor inputs are processed by one subset while overwhelming stimuli are handled by another subset, thereby maintaining both processing completeness and real-time speed performance.
Solution Approach 2:
The system dynamically changes the processing parameters by adjusting which subset of cores handles which type of input based on the detected conditions. When overwhelming stimuli are detected, the system switches to a mode where a dedicated subset processes these stimuli while another subset continues processing normal inputs, thus adapting the processing configuration to maintain real-time performance.
2Device complexity
If a single processing core handles all sensor inputs, then resource utilization is simplified, but processing delay increases when malicious stimuli are present
Solution Approach 1:
The patent segments the processing cores into multiple subsets, creating a more complex resource management structure. However, this segmentation enables parallel processing that significantly reduces processing delays when malicious stimuli are present, as different subsets can handle different types of inputs simultaneously rather than sequentially.
Solution Approach 2:
The system implements periodic monitoring of input characteristics to detect overwhelming stimuli. Based on these periodic assessments, the resource allocation between subsets is dynamically adjusted, allowing the system to switch processing modes as needed to minimize delays while maintaining efficient resource utilization.
3Reliability
If all processing resources are allocated to handle overwhelming stimuli, then protection against malicious inputs is improved, but processing of normal sensor inputs is delayed
Solution Approach 1:
The patent segments processing resources into dedicated subsets for handling different types of inputs. One subset is allocated to process overwhelming stimuli while another subset continues to process normal sensor inputs. This segmentation ensures that protection against malicious inputs is maintained without compromising the processing throughput of normal inputs, as both can be handled in parallel by different subsets.
Solution Approach 2:
Different subsets of processing cores are assigned different functional qualities based on the type of input they handle. The first subset is optimized for handling overwhelming stimuli with appropriate protection mechanisms, while the second subset maintains high-speed processing capabilities for normal sensor inputs. This local differentiation of processing quality ensures both protection and productivity are maintained.
Data Source
AI summary
Systems, methods and apparatuses of processing overwhelming stimuli in vehicle data recorders. For example, a data recorder can have resources, such as memory components, a controller, an inference engine, etc. The resources can be partitioned into a first subset and a second subset. Abnormal stimuli in an input stream to the recorder may cause delay for real time processing. In response, a time sliced segment of the input stream is selected and assigned to the first subset; and a remaining segment is assigned to the second subset. The first and second subsets can separately process the time sliced segment and the remaining segment in parallel and thus avoid delay in the processing of the remaining segment. An artificial neural network (ANN) can determine a width for selecting the segment processed by the first subset; and the processing result can include a preferred width used to train the ANN.