Back to results
US 12,093,880 B2Granted
Edge computing device and system for vehicle, container, railcar, trailer, and driver verification
AssigneeKoiReader Technologies, Inc.
InventorsAshutosh Prasad, Vivek Prasad
Life of this patent
Estimating the term…
Abstract
Techniques are described for automating the check in and check out process at a logistics facility. For example, a sensor system may be configured to capture sensor data associated with an approaching vehicle. The sensor system may utilize the sensor data to extract information usable to complete forms, assess damage, and authenticate the shipment.
Claims20
A method comprising:
- performing, by a computing system including an imaging sensor, steps comprising:
- capturing by the imaging sensor, image data associated with a vehicle, an operator of the vehicle, and a container associated with the vehicle;
- determining an identity of the vehicle based at least in part on an output of a first machine learned neural network accepting the image data as an input, the first neural network including at least a first connected layer to segment the image data and a second connected layer to classify the segmented image data, the first machine learned neural network trained based at least in part on image data of vehicles;
- determining an identity of the container associated with the vehicle based at least in part on an output of a second machine learned neural network accepting the image data as an input, the second neural network including at least a first connected layer to segment the image data and a second connected layer to classify the segmented image data, the second machine learned neural network trained based at least in part on image data of containers;
- determining an identity of the operator associated with the vehicle based at least in part on an output of a third machine learned neural network accepting the image data as an input, the third neural network including at least a first connected layer to segment the image data and a second connected layer to classify the segmented image data, the third neural network trained based at least in part on image data of operators;
- determining a first status associated with the container based at least in part on the image data;
- identifying a document to be completed based at least in part on the output of the first machine learned neural network and the output of the second machine learned neural network;
- determining an entity associated with the document based at least in part on the identity of the vehicle, the identity of the operator, and the identity of the container;
- completing the document based at least in part on the output of the first machine learned neural network, the output of the second machine learned neural network, and the output of the third machine learned neural network;
- and
- transmitting, via one or more networks, the document to a remote system associated with the entity.
8 more elements
One or more non-transitory computer-readable media storing instructions thereon that, when executed by one or more computing devices, cause the one or more computing devices to perform operations comprising:
- receiving lidar data, associated with a delivery from at least one lidar sensor;
- determining an identity of a vehicle associated with the delivery based at least in part on the lidar data input into a first machine learned neural network, the first machine learned neural network trained on first lidar data of vehicles;
- determining an identity of an entity associated with the delivery based at least in part on the lidar data input into a second machine learned neural network, the second machine learned neural network trained on second lidar data of vehicles;
- identifying a document to be completed based at least in part on the identity of the vehicle and the identity of the entity;
- completing the document based at least in part on content extracted from the lidar data;
- transmitting, via one or more first networks, the document to a remote system associated with the entity;
- detecting damage associated with the delivery based at least in part on the lidar data;
- determining, in response to detecting the damage, an amount of damage associated with the delivery based at least in part on the lidar data and a first recorded status of the vehicle associated with the delivery and a second recorded status of a container associated with the delivery determined at a time of deployment;
- determining, in response to detecting the damage and based at least in part on the lidar data, the first recorded status of the vehicle, and the second recorded status of the container, if the damage occurred during shipping;
- and
- reporting, via one or more second networks, the amount of damage to the remote system associated with the entity.
8 more elements
An EDGE computing system comprising:
- one or more processors;
- and
- one or more computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
- one or more image devices of the EDGE computing system;
- one or more depth sensors of the EDGE computing system;
- receiving, from the one or more image devices, first image data associated with an exterior of a vehicle;
- receiving, from the one or more image devices, second image data associated with an operator of the vehicle;
- receiving, from the one or more image devices, third image data associated with an exterior of a container associated with the vehicle;
- receiving, from the one or more depth sensors, first depth data associated with the exterior of the vehicle;
- receiving, from the one or more depth sensors, second depth data associated with the operator of the vehicle;
- receiving, from the one or more depth sensors, third depth data associated with the exterior of the container associated with the vehicle;
- determining, based at least in part on inputting the first image data and the first depth data into a first machine learned neural network, an identity of the vehicle, the first machine learned neural network trained based at least in part on image data and depth data of vehicles;
- determining, based at least in part on inputting the second image data and the second depth data into a second machine learned neural network, an identity of the operator, the second machine learned neural network trained based at least in part on image data and depth data of operators;
- determining, based at least in part on inputting the third image data and the third depth data into a third machine learned neural network, an identity of the container, the third machine learned neural network trained based at least in part on image data and depth data of containers;
- determining an identity of an entity associated with contents of the container based at least in part on the identity of the vehicle, the identity of the operator, and the identity of the container;
- identifying a document to be completed based at least in part on the identity of an entity;
- completing the document based at least in part on content extracted from the first image data, the second image data, and the third image data;
- and
- transmitting, via one or more networks, the document to a remote system associated with the entity.
16 more elements
Dependencies are inferred from the claim text.