Magna Electronics Inc.

Anuj S Potnis

Krishna Koravadi

William Joseph Chundrlik, Jr

G Edzko Smid

A method for testing a vehicular driving assist system includes providing a neural network and training the neural network using a database of images, with each image of the database of images including an image of a headlight or a taillight of a vehicle. The trained neural network is provided with an input image that does not include a headlight or a taillight. The neural network, using the input image, generates an output image, with the output image including an image of a headlight or taillight generated by the neural network. The output image is provided as an input to the driving assist system to test the driving assist system.

Vehicular system for testing performance of headlamp detection systems

A vehicular driving assist system includes an electronic control unit (ECU). When the equipped vehicle is driving in the autonomous mode, driving of the vehicle is controlled by the ECU without human intervention. When the vehicle is being driven in a non-autonomous mode, a particular driver at least partially drives the vehicle. The vehicular driving assist system learns a driving style of the particular driver and, when the vehicle is being driven in the non-autonomous mode by the particular driver, the system restricts learning of the driving style of the particular driver responsive to determination by the system that the particular driver is (i) driving the vehicle erratically and/or (ii) performing an illegal driving maneuver. When the vehicle is driving in the autonomous mode, and responsive to the particular driver being present in the vehicle, the vehicle drives in accordance with the learned driving style of the particular driver.

Vehicular driving assist system that learns different driving styles

A driving assistance system for a vehicle includes a control operable to control the vehicle in an autonomous or semi-autonomous mode. When operating in the autonomous mode, driving of the vehicle is controlled by the control without human intervention and, when operating in the semi-autonomous mode, an occupant of the vehicle at least partially drives the vehicle. The control learns a driving style of a particular occupant when the vehicle is being driven by that particular occupant and when the control is operating in the semi-autonomous mode. The control, when operating in the autonomous mode, controls the vehicle in accordance with the learned driving style of the particular occupant of the vehicle. Responsive to a determination of a characteristic of an occupant in the vehicle, the control, when operating in the autonomous, may adjust control of the vehicle irrespective of the learned driving style of the particular occupant.

Vehicle control system that learns different driving characteristics

A communication system for a vehicle includes a communication device disposed in the vehicle. Responsive to the communication device receiving an input from a vehicle system indicative of a potential service need, the communication device requests an input from the driver of the vehicle pertaining to a desired characteristic of a service provider that can address the potential service need. Responsive to the communication device receiving the input from the driver, the communication system determines a plurality of service providers that (i) can address the potential service need and (ii) has the desired characteristic. The communication device communicates a list of potential service providers to the driver and, responsive to a selection by the driver of a selected service provider, the communication system sets a navigation system of the vehicle to the selected service provider.

Vehicle communication system

A camera simulation system or method or process for simulating performance of a camera for a vehicle includes providing a camera having a lens and imager and providing a learning algorithm. Image data is captured from a raw image input of the camera and the captured image data and raw image input are output from the camera. The output image data and the raw image input are provided to the learning algorithm. The learning algorithm is trained to simulate performance of the lens and/or the imager using the output captured image data and the raw image data input. The performance of the lens and/or the imager is simulated responsive to the learning algorithm receiving raw images.

Vehicle camera model for simulation using deep neural networks

A method for determining trailer angle includes determining angles of a trailer hitch relative to a data recording device via an angle measuring device while the trailer hitch pivots about a hitch ball of the device. While the trailer hitch pivots about the hitch ball of the device, trailer hitch information is determined responsive to processing of captured image data and responsive to determined angles of the trailer hitch. After determining trailer hitch information, data representative of the determined information is provided to an electronic device, which is disposed at a vehicle having a rear backup camera that has a field of view that encompasses a hitch ball of the vehicle and at least a portion of a hitch of a trailer hitched to the vehicle. Using the provided data, and responsive to processing of captured image data, an angle of the trailer relative to the vehicle is determined.

Growing community of inventors

Pune, India

Anuj S Potnis