Crowdsourced Virtual Sensor Generation for Vehicle Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Vehicles equipped with sensors face high costs and limited sensing capabilities due to the line of sight limitations of individual sensors, necessitating a solution to enhance sensing capabilities while reducing costs.
Innovation Solution
A crowdsourced virtual sensor generator system that aggregates and filters data from multiple vehicles to create virtual sensors, processing data from various sources to provide enhanced sensing capabilities to target vehicles, including the use of a server or onboard processor to generate and transmit virtual sensor data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sensors are installed on vehicles to enable object tracking, collision detection, and environmental sensing, then sensing capabilities are improved, but sensor costs increase and sensing is limited to line of sight
Solution Approach 1:
The patent creates virtual sensor data that copies and simulates sensor readings from other vehicles' actual sensors. Instead of installing expensive physical sensors on every vehicle, the system generates virtual copies of sensor data from contributing vehicles, allowing target vehicles to access sensing capabilities they would otherwise lack while avoiding the cost of duplicating expensive hardware
Solution Approach 2:
The patent merges sensor data from multiple contributing vehicles to create aggregated sensor information for target vehicles. By combining data from multiple sources through the communication network, the system achieves comprehensive environmental sensing that exceeds what any single vehicle's sensors could provide, while distributing the sensing burden across the fleet
2Area of stationary object
If individual vehicle sensors are used for environmental sensing, then sensing coverage is limited to line of sight, but installing more sensors increases cost
Solution Approach 1:
The patent extends sensing coverage from the single-vehicle dimension to the multi-vehicle fleet dimension. By aggregating sensor data from multiple contributing vehicles across the communication network, the system creates virtual sensing coverage that spans a much larger geographic area and angular range than any single vehicle's physical sensors could achieve alone
Solution Approach 2:
The patent introduces a communication network as an intermediary to transfer sensor data between contributing vehicles and target vehicles. This intermediary enables the sharing of sensing information across the vehicle fleet, allowing target vehicles to access sensor data from vehicles in different locations and orientations, thereby expanding effective sensing coverage without installing additional physical sensors
3Reliability
If virtual sensor data is generated from multiple contributing vehicles, then sensing capabilities beyond line of sight are achieved, but data filtering and aggregation complexity increases
Solution Approach 1:
The patent applies preliminary filtering and aggregation operations to sensor data from contributing vehicles before generating virtual sensor output for target vehicles. By pre-processing the raw sensor data through filtering (to remove irrelevant or low-quality readings) and aggregation (to combine multiple readings into consolidated information), the system reduces data complexity early in the processing chain, making subsequent virtual sensor generation more efficient and reliable
Data Source
AI summary
A crowdsourced virtual sensor generator is provided which could be generated by a vehicle or provided to the vehicle as, for example, a service. The crowdsourced virtual sensor generator may include, but is not limited to, a communication system configured to receive contributing vehicle sensor data from one or more contributing vehicles, a location of the one or more contributing vehicles and a target vehicle, and a processor, the processor configured to filter the received contributing vehicle sensor data based upon the location of the one or more contributing vehicles and the location of the target vehicle, aggregate the filtered contributing vehicle sensor data into at least one of a data-specific dataset and an application-specific data set, and generate a virtual sensor for the target vehicle, the virtual sensor processing the filtered and aggregated contributing vehicle sensor data to generate output data relative to the location of the target vehicle.