Systems and methods for automotive sensing
AssigneePolyN Technology Limited
InventorsDmitrii Godovskii, Boris Maslov, Aleksandrs Timofejevs
Life of this patent
Estimating the term…
Abstract
Systems, devices, integrated circuits, and methods are directed to on-vehicle data processing using analog hardware realization of neural networks. A vehicle obtains a temporal sequence of sensor data that is collected by a microphone of a sensor system. The sensor system is physically coupled to a tire of a vehicle. The neural network circuit generates one or more output data items based on the sensor data, and the one or more output data items indicate the condition of a road, the vehicle, or a component of the vehicle. The sensor system, including an electronic device that includes the microphone, is also described herein. A method of training the neural network is also described herein.
Claims17
An electronic device, comprising:
- one or more sensors physically coupled to a tire of a vehicle, wherein:
- the one or more sensors includes a first sensor configured to collect a temporal sequence of first sensor data used to provide a plurality of first parallel data items and a second sensor configured to collect a temporal sequence of second data used to provide a plurality of second parallel data items;
- the first sensor is different from the second sensor;
- the temporal sequence of first sensor data is different from the temporal sequence of second sensor data;
- and
- the plurality of first parallel data items is different from the plurality of second parallel data items;
- and
- a neural network circuit coupled to the sensor, wherein:
- the neural network circuit is configured to receive the plurality of first parallel data items and the plurality of second parallel data items and generate one or more output data items based on analysis of the plurality of first parallel data items and the plurality of second parallel data items;
- and
- the one or more output data items indicate a condition of a road, the vehicle, and/or a component of the vehicle.
A method for processing vehicle data, comprising:
- obtaining a first temporal sequence of sensor data that is collected by a first sensor that is physically coupled to a tire of a vehicle;
- obtaining a second temporal sequence of data that is collected by a second sensor, wherein the second sensor is different from the first sensor and the second temporal sequence of data is different from the first temporal sequence of data;
- transmitting the first temporal sequence of sensor data and the second temporal sequence of sensor data to a neural network circuit that is coupled to each of the first sensor and the second sensor;
- analyzing in parallel, by the neural network circuit, the first temporal sequence of sensor data and the second temporal sequence of sensor data;
- and
- generating, by the neural network circuit, one or more outputs indicating a condition of a road, the vehicle, and/or a component of the vehicle, wherein the one or more outputs are generated based on the first temporal sequence of data and the second temporal sequence of data.
A method, comprising:
- obtaining a first temporal sequence of sensor data samples that is collected by a first sensor that is physically coupled to a tire of a vehicle;
- obtaining a second temporal sequence of data samples that is collected by a second sensor, wherein the second sensor is different from the first sensor and the second temporal sequence of data samples is different from the first temporal sequence of data samples;
- converting the first temporal sequence of sensor data samples into a plurality of first parallel data items;
- converting the second temporal sequence of sensor data samples into a plurality of second parallel data items;
- providing the plurality of first parallel data items as a plurality of first inputs to a neural network circuit;
- providing the plurality of second parallel data items as a plurality of second inputs to the neural network circuit;
- and
- generating, by the neural network circuit, one or more output data items based on the first plurality of parallel data items and the plurality of second parallel data items, the one or more output data items indicating a condition of a road, the vehicle, and/or a component of the vehicle.
Dependencies are inferred from the claim text.