Gm Global Technolgoy Operations, Inc.

Wei Mou

Peter Ming Gao

Siddhartho Bhattacharya

Eric Lujan

Jeremy Allan

Jonathan Uesato

Systems and method are provided for controlling a vehicle. The vehicle includes a first device onboard the vehicle providing first data, a second device onboard the vehicle providing second data, one or more sensors onboard the vehicle, one or more actuators onboard the vehicle, and a controller. The controller detects a stationary condition based on output of the one or more sensors, obtains a first set of the first data from the first device during the stationary condition, filters horizontal edge regions from the first set resulting in a filtered set of the first data, obtains a second set of the second data during the stationary condition, determines one or more transformation parameter values based on a relationship between the second set and the filtered set, and autonomously operates the one or more actuators onboard the vehicle in a manner that is influenced by the transformation parameter values.

Calibration methods for autonomous vehicle operations

Systems and method are provided for controlling a vehicle. In one embodiment, a vehicle includes: an imaging device, a ranging device, a data storage element to maintain calibration data associated with a relationship between the imaging device and the ranging device, one or more actuators, and a controller. The controller obtains image data from the imaging device, classifies portions of the image data as ground, obtains ranging data from the ranging device, identifies a ground subset of the ranging data corresponding to the portions of the image data using the calibration data; and operates the one or more actuators onboard the vehicle in a manner that is influenced by the ground subset of the ranging data.

Ground reference determination for autonomous vehicle operations

Systems and method are provided for controlling a vehicle. In one embodiment, an obstacle management method includes receiving, via one or more sensing devices, sensor data relating to an environment associated with a vehicle, wherein the vehicle is substantially stationary and has an intended path corresponding to entering a traffic flow of a first lane. The method includes determining the presence of an obstacle that at least partially occludes a view of the first lane by a first sensing device of the one or more sensing devices, and positioning, with a processor, the vehicle with respect to the obstacle to improve the view of the first lane by the first sensing device without significantly obstructing the first lane. The first lane is then monitored via the first sensing device to determine when the intended path clear.

Systems and methods for entering traffic flow in autonomous vehicles

Systems and method are provided for controlling an autonomous vehicle. A camera configured to capture an image, and a controller can execute an autonomous driving system (ADS) that classify that image. The ADS comprises a classification system for classifying objects in an environment within a driveable area of the autonomous vehicle. The classification system comprises a processor configured to execute a region proposal generator module and an image classification module. The region proposal generator module generates a set of bounding box region proposals for the image. The bounding box region proposals are selected areas of the image that include objects to be classified. The image classification module classifies, via a neural network executed by the processor, the objects from the image that are within one of the bounding box region proposals.

Systems and methods for visual classification with region proposals

Systems and method are provided for controlling a vehicle. In one embodiment, a vehicle includes a camera onboard the vehicle, a lidar device onboard the vehicle, a data storage element onboard the vehicle maintaining one or more transformation parameter values associated with a pairing of the camera and the lidar device, one or more sensors onboard the vehicle, and a controller. The controller detects a stationary condition based on output of the one or more sensors, obtains a first set of image data from the camera during the stationary condition, filters horizontal edge regions from the first set, obtains a second set of the ranging data during the stationary condition, and validates the one or more transformation parameter values based on a relationship between the filtered set of the image data and the second set of the ranging data.

Growing community of inventors

South San Francisco, CA, United States of America

Wei Mou