Gm Global Technolgoy Operations, Inc.

Yasen Hu

Shuqing Zeng

Upali Priyantha Mudalige

Mohannad F Murad

Wei Tong

Yao Hu

David R Petrucci

Gregg R Kittinger

Shiming Duan

Nicholas W Pinto

Kausalya Singuru

Syed B Mehdi

Bradley R Frieberg

Donald K Grimm

Bakhtiar Brian Litkouhi

Igal Bilik

Jordan B Chipka

A vehicle system includes a lidar system that obtains an initial point cloud and obtains a dual density point cloud by implementing a first neural network and based on the initial point cloud. The dual density point cloud results from reducing point density of the initial point cloud outside a region of interest (ROI). Processing the dual density point cloud results in a detection result that indicates any objects in a field of view (FOV) of the lidar system. A controller obtains the detection result from the lidar system and controls an operation of the vehicle based on the detection result.

Vehicle lidar system with neural network-based dual density point cloud generator

A system includes first and second sensors and a controller. The first sensor is of a first type and is configured to sense objects around a vehicle and to capture first data about the objects in a frame. The second sensor is of a second type and is configured to sense the objects around the vehicle and to capture second data about the objects in the frame. The controller is configured to down-sample the first and second data to generate down-sampled first and second data having a lower resolution than the first and second data. The controller is configured to identify a first set of the objects by processing the down-sampled first and second data having the lower resolution. The controller is configured to identify a second set of the objects by selectively processing the first and second data from the frame.

Object detection in vehicles using cross-modality sensors

A system and method for personalization of adjustable features of a vehicle. The system includes a processor and an actuator. The processor detectors key points of a person from a two-dimensional image and predicts a pose of the person. The processor translates a respective position of the key points from a two-dimensional coordinate system to a three-dimensional coordinate system based in part on the pose and measurements of distances between the key points. The processor determines a baseline configuration of an adjustable feature of the vehicle based in part on measurements between the key points in the three-dimensional coordinate system. The processor causes an actuator to adjust the adjustable feature to conform to the baseline configuration.

Personalization settings based on body measurements

A vehicle including an advanced driver-assistance system (ADAS) and operator-adjustable devices is described. Controlling the vehicle includes identifying a vehicle operator, and capturing a plurality of operator-selectable settings associated with the plurality of operator-adjustable devices for the vehicle operator. A base profile and a second profile are determined for the vehicle operator based upon the first subset associated with non-autonomous operation of the vehicle and the second subset associated with ADAS, respectively. The plurality of operator-adjustable devices are controlled to the operator-selectable settings associated with the base profile when the vehicle is operating in the non-autonomous mode, and the plurality of operator-adjustable devices are controlled to the operator-selectable settings associated with the second profile when the vehicle is being controlled at least in part by one or more of the subsystems of the ADAS.

Method and apparatus for managing operator-selectable settings on-vehicle

A system and method to resolve ambiguity in a radar system involve detecting one or more objects with the radar system. The detecting includes obtaining range, azimuth, and an ambiguous range rate of a first object of the one or more objects. A plurality of Kalman filters are generated with state variables that include parameters based on the range, the azimuth, and the ambiguous range rate. Each of the plurality of Kalman filters provides a different estimate for an unambiguous range rate. The method also includes updating the plurality of Kalman filters using additional detections by the radar system, selecting a selected Kalman filter from among the plurality of Kalman filters that exhibits a highest probability mass among a plurality of probability mass corresponding with and derived from the plurality of Kalman filters, and determining the unambiguous range rate of the object using the selected Kalman filter.

Resolution of doppler ambiguity in a radar system through tracking

A method of updating an identification algorithm of a vehicle includes sensing an image and drawing boundary boxes in the image. The algorithm attempts to identify an object-of-interest within each respective boundary box. The algorithm also attempts to identify a component of the object-of-interest within each respective boundary box, and if component is identified, calculates an excluded amount of a component boundary that is outside an object boundary. When the excluded amount is greater than a coverage threshold, the algorithm communicates the image to a processing center, which may identify a previously un-identified the object-of-interest in the image. The processing center may add the image to a training set of images to define a revised training set of images, and retrain the identification algorithm using the revised training set of images. The updated identification algorithm may then be uploaded onto the vehicle.

Automated data collection for continued refinement in the detection of objects-of-interest

A system and method to perform dynamic bandwidth adjustment among two or more vehicle sensors includes receiving input. The input includes data from each of the two or more vehicle sensors. The two or more vehicle sensors include a camera, an audio detector, a radar system, or a lidar system. The method also includes determining a bandwidth at which each of the two or more vehicle sensors should provide the data, and providing a control signal to each of the two or more vehicle sensors to adjust the bandwidth based on the determining.

Dynamic bandwidth adjustment among vehicle sensors

A method for controlling an operating vehicle includes: (a) determining, via a controller, a confidence level that the light of the other vehicle is ON based on images captured by a camera of the operating vehicle; and (b) controlling, via the controller, an alarm of the operating vehicle based on the confidence level that the light of the other vehicle is ON.

Vehicle behavior using information from other vehicles lights

A system and method to perform detection based on sensor fusion includes obtaining data from two or more sensors of different types. The method also includes extracting features from the data from the two or more sensors and processing the features to obtain a vector associated with each of the two or more sensors. The method further includes concatenating the two or more vectors obtained from the two or more sensors to obtain a fused vector, and performing the detection based on the fused vector.

Growing community of inventors

Warren, MI, United States of America

Yasen Hu