Virtual Sensor Model for Multi-Sensor Latency Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Sensor latency and inefficiencies in processing data from multiple sensors lead to delays and inaccuracies, particularly impacting user satisfaction and device performance, especially in applications like virtual reality.
Innovation Solution
A machine-learned virtual sensor model that refines and predicts sensor outputs by leveraging correlations among multiple sensors, using neural networks to generate refined and predicted future sensor values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sensor data from multiple sensors is processed independently at their own frequencies, then each sensor can operate autonomously, but sensor latency occurs and device responsiveness deteriorates
Solution Approach 1:
The patent combines data from multiple independent sensors into a unified processing framework using a shared dictionary structure. This merging allows the system to process sensor data collectively rather than independently, reducing latency by eliminating redundant processing steps while maintaining the accuracy benefits of multi-sensor data fusion.
Solution Approach 2:
The system performs preliminary actions by pre-defining a shared dictionary structure that anticipates the data formats and correlations from multiple sensors. This pre-prepared framework enables faster processing when sensor data arrives, reducing the time needed for data fusion and correlation analysis without sacrificing measurement accuracy.
2Device complexity
If multiple sensors operate independently at different frequencies, then sensor hardware complexity is reduced, but data fusion efficiency deteriorates
Solution Approach 1:
The patent introduces a shared dictionary structure as an intermediary between multiple independent sensors and the processing system. This mediator standardizes data from sensors operating at different frequencies into a unified format, enabling efficient data fusion without requiring complex synchronization logic in each sensor, thus maintaining hardware simplicity while improving fusion efficiency.
3Ease of operation
If sensor readings are processed in real-time without prediction, then processing simplicity is maintained, but application responsiveness particularly in VR deteriorates
Solution Approach 1:
The system performs preliminary actions by analyzing historical sensor data patterns and making predictions about future sensor states before actual readings are needed. This predictive approach prepares the system in advance, allowing VR applications to display anticipated states rather than waiting for real-time sensor data, thereby reducing perceived latency without significantly complicating the processing architecture.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present disclosure provides systems and methods that leverage machine learning to refine and/or predict sensor outputs for multiple sensors. In particular, systems and methods of the present disclosure can include and use a machine-learned virtual sensor model that has been trained to receive sensor data from multiple sensors that is indicative of one or more measured parameters in each sensor's physical environment, recognize correlations among sensor outputs of the multiple sensors, and in response to receipt of the sensor data from multiple sensors, output one or more virtual sensor output values. The one or more virtual sensor output values can include one or more of refined sensor output values and one or more predicted future sensor output value.