Back to results
US 11,496,707 B1Granted
Fleet dashcam system for event-based scenario generation
AssigneeZoox, Inc.
InventorsAndrew Scott Crego, Josh Alexander Jimenez, James William Vaisey Philbin, Chuang Wang
Life of this patent
Estimating the term…
Abstract
Techniques for receiving and processing sensor data captured by a fleet of vehicle are discussed herein. In some examples, a fleet dashcam system can receive sensor data captured by electronic devices on a fleet of vehicles and can use that data to detect collision and near-collision events. The data of the collision or near-collision event can be used to determine a simulation scenario and a response of an autonomous vehicle control to the simulation scenario and/or it can be used to create a collision heat map to aid in operation of an autonomous vehicle.
Claims20
A method comprising:
- receiving, at one or more processors, first sensor data from a first dashcam of a first vehicle, where the first dashcam comprises a first sensor configured to capture first video data and first memory configured to store the first video data;
- receiving, at the one or more processors, second sensor data from a second dashcam of a second vehicle, where the second dashcam comprises a second sensor configured to capture second video data and second memory configured to store the second video data;
- identifying, within the first video data, an object associated with an adverse event;
- identifying, within the second video data, the object associated with the adverse event;
- aligning, in time, the object in the first video data with the second video data, wherein the aligning the object in the first video data with the second video data includes performing a visual analysis between the first video data and the second video data identifying a first state of the object in the first video data corresponding to a second state of the object in the second video data at a corresponding time;
- generating, based at least in part on data associated with the object from the first video data and data corresponding to the object from the second video data, a simulation including the object;
- and
- determining a simulation comprising an autonomous vehicle and the object.
5 more elements
A method comprising:
- receiving, at one or more processors, image data from a dashcam of a vehicle, wherein the dashcam comprises:
- a first sensor configured to capture first image data associated with an adverse event;
- a second sensor configured to capture second image data associated with the adverse event;
- memory configured to store the image data associated with the adverse event;
- and
- an attachment mechanism configured to removably mount the dashcam to the vehicle;
- identifying, within the first image data, objects associated with the adverse event;
- identifying, within the second image data, the objects associated with the adverse event;
- aligning, in time, the objects in the first image data with the second image data, wherein aligning the objects in the first image data with the second image data includes:
- performing a visual analysis between the first image data and the second image data to determine locations of the objects in the first image data corresponding to locations of the objects in the second image data at a corresponding time;
- generating, based at least in part on the locations of the objects in the first image data corresponding to the locations of the objects in the second image data, a simulation including the objects;
- and
- determining a response of an autonomous vehicle controller to the simulation.
10 more elements
One or more non-transitory computer-readable media storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
- receiving image data from a dashcam of a vehicle, wherein the dashcam comprises:
- a first sensor configured to capture first image data associated with an adverse event;
- a second sensor configured to capture second image data associated with the adverse event;
- memory configured to store the image data associated with the adverse event;
- and
- an attachment mechanism configured to removably mount the dashcam to the vehicle;
- identifying, within the first image data, objects associated with the adverse event;
- identifying, within the second image data, the objects associated with the adverse event;
- aligning, in time, the objects in the first image data with the second image data, wherein aligning the objects in the first image data with the second image data includes:
- performing a visual analysis between the first image data and the second image data to determine locations of the objects in the first image data corresponding to locations of the objects in the second image data at a corresponding time;
- generating, based at least in part on the locations of the objects in the first image data corresponding to locations of the objects in the second image data, a simulation including the objects;
- and
- determining a response of an autonomous vehicle controller to the simulation.
10 more elements
Dependencies are inferred from the claim text.