Gm Global Technolgoy Operations, Inc.

Michael Baltaxe

Dan Levi

Ron M Hecht

Ariel Telpaz

Kobi Nistel

Ruben Mergui

Gila Kamhi

Tzvi Philipp

Scott David Thomas

Omer Tsimhoni

Dorel M Sala

Michael Slutsky

Claudia V Goldman-Shenhar

Asaf Degani

Yael Shmueli Friedland

Ke Liu

Noa Garnett

Nadav Baron

Christopher A Stanek

Ravid Erez

Barak Hershkovitz

Lisa A Fallon

Amit Batikoff

Andrea Forgacs

Doron Portnoy

Tal Furman

Gershon Celniker

Itai Druker

Shahar Ben Ezra

Tomer Pe'er

Ariel Rubanenko

A computer-implemented method when executed by data processing hardware causes the data processing hardware to perform operations. The operations include generating, at an occupancy estimation network, an occupancy probability at one or more voxels, predicting, via a gaze prediction model, a gaze direction of a gaze prediction, and identifying, based on the predicted gaze direction, an object of interest. The operations also include generating, via an occupancy estimation application, a gaze saliency map based on the gaze direction and identified object of interest, and updating, based on the determined gaze direction and the gaze saliency map, the occupancy probability of the one or more voxels.

Occupancy estimation system for a vehicle

A disclosure is presented for estimating height of an object using ultrasonic sensors carried onboard a vehicle. The height may be estimated by generating ultrasonic distance measurements based on a time of flight associated with ultrasonic reflections detected with the ultrasonic sensors, generating a three-dimensional (3D) occupancy grid to volumetrically represent at least a portion of an environment within field of view of the ultrasonic sensors, the 3D occupancy grid including a plurality of volumetric pixels (voxels), assigning a count value to each of the voxels based on the distance measurements, and estimating the height according to a relative spatial relationship between the vehicle and the voxel having the count value with a greatest value.

Object height estimation using ultrasonic sensors

A detection system for a host vehicle includes a camera, global positioning system ('GPS') receiver, compass, and electronic control unit (“ECU”). The camera collects polarimetric image data forming an imaged drive scene inclusive of a road surface illuminated by the Sun. The GPS receiver outputs a present location of the vehicle as a date-and-time-stamped coordinate set. The compass provides a directional heading of the vehicle. The ECU determines the Sun's location relative to the vehicle and camera using an input data set, including the present location and directional heading. The ECU also detects a specular reflecting area or areas on the road surface using the polarimetric image data and Sun's location, with the specular reflecting area(s) forming an output data set. The ECU then executes a control action aboard the host vehicle in response to the output data set.

Automated detection of specular reflecting road surfaces using polarimetric image data

A system for vehicle trajectory planning. The system may include a polarized camera system configured to generate polarized images of a roadway to be driven over with a vehicle, a prior controller configured to generate a prior for the roadway based at least in part on the polarized images, and a driving assistance system configured to provide a driving assistance according to the prior.

Vehicle trajectory planning

A system for a host vehicle operating on a road surface includes a polarimetric camera, a global positioning system ('GPS') receiver, a compass, and an electronic control unit (“ECU”). The camera collects polarimetric image data of a drive scene, including a potential driving path on the road surface. The ECU receives the polarimetric image data, estimates the Sun location using the GPS receiver and compass, and computes an ideal representation of the road surface using the Sun location. The ECU normalizes the polarimetric image data such that the road surface has a normalized representation in the drive scene, i.e., an angle of linear polarization (“AoLP”) and degree of linear polarization (“DoLP”) equal predetermined fixed values. The ECU executes a control action using the normalized representation.

Vehicle with polarimetric image normalization logic

A system in a vehicle includes an image sensor to obtain images in an image sensor coordinate system and a depth sensor to obtain point clouds in a depth sensor coordinate system. Processing circuitry implements a neural network to determine a validation state of a transformation matrix that transforms the point clouds in the depth sensor coordinate system to transformed point clouds in the image sensor coordinate system. The transformation matrix includes rotation parameters and translation parameters.

Alignment validation in vehicle-based sensors

Presented are intelligent vehicle systems for off-road driving incident prediction and assistance, methods for making/operating such systems, and vehicles networking with such systems. A method for operating a motor vehicle includes a system controller receiving geolocation data indicating the vehicle is in or entering off-road terrain. Responsive to the vehicle geolocation data, the controller receives, from vehicle-mounted cameras, camera-generated images each containing the vehicle's drive wheel(s) and/or the off-road terrain's surface. The controller receives, from a controller area network bus, vehicle operating characteristics data and vehicle dynamics data for the motor vehicle. The camera data, vehicle operating characteristics data, and vehicle dynamics data is processed via a convolutional neural network backbone to predict occurrence of a driving incident on the off-road terrain within a prediction time horizon. The system controller commands a resident vehicle system to execute a control operation responsive to the predicted occurrence of the driving incident.

Intelligent vehicle systems and control logic for incident prediction and assistance in off-road driving situations

Methods, systems, and apparatuses to build an explainable user output to receive input feature data by a neural network of multiple layers of an original classifier; determine a semantic function to label data samples with semantic categories; determine a semantic accuracy for each layer of the original classifier within the neural network; compare each layer based on results from the comparison of the semantic accuracy; designate a layer based on an amount of computed semantic accuracy; extend the designated layer by a category branch to the neural network to extract semantic data samples from the semantic content to train a set of new connections of an explainable classifier to compute a set of output explanations with an accuracy measure associated each output explanation for each semantic category of the plurality of semantic categories, and compare the accuracy measure for each output explanation to generate the output explanation in a user understandable format.

Methods, systems, and apparatuses for user-understandable explainable learning models

Vision-based airbag enablement may include capturing two-dimensional images of a passenger, segmenting the image, classifying the image, and determining seated height of the passenger from the image. Enabling or disabling deployment of the airbag may be controlled based at least in part upon the determined seated height.

Vision-based airbag enablement

A system and method for error estimation in an eye gaze tracking system in a vehicle may include an operator monitoring system providing measured eye gaze information corresponding to an object outside the vehicle and an external object monitoring system providing theoretical eye gaze information and an error in the measured eye gaze information based upon the measured eye gaze information and the theoretical eye gaze information.

Eye gaze tracking calibration

A system includes a seat belt routing module and a user interface device (UID) control module. The seat belt routing module is configured to: determine a routing of a seat belt relative to an occupant in a vehicle seat based on input from a webbing payout sensor; and determine the seat belt routing based on an input from an in-cabin sensor. The in-cabin sensor includes at least one of a camera, an infrared sensor, an ultrasonic sensor, a radar sensor, and a lidar sensor. The UID control module is configured to control a user interface device to indicate that the seat belt is being worn improperly when: the seat belt routing determined using at least one of the webbing payout sensor and the in-cabin sensor is improper; and the seat belt routing determined using the webbing payout sensor corresponds to the seat belt routing determined using the in-cabin sensor.

System and method for monitoring seat belt routing using both a webbing payout sensor and an in-cabin sensor

A vehicle, system and a computer-implemented method for setting a height of a seat belt in a vehicle. The system includes a computer vision module, a motor and a controller. The computer vision module determines a seatbelt-neck distance (SND) and a seatbelt-shoulder distance (SSD) for an occupant of the vehicle. The motor adjusts the height of the seat belt. The controller control the motor to set the height of the seat belt based on the SND and the SSD.

System and method to automatically set the height of the torso section of a seat belt

A system for detecting seatbelt routing includes: a state module configured to, based on a series of images over a period of time from a camera of a vehicle facing a seat, determine and output a routing state of a seatbelt of the seat; and a remediation module configured to, based on the routing state of the seatbelt of the seat, selectively perform at least one remedial action.

Time based seatbelt routing detection via in-cabin sensors

A seat belt status determining system and method for a vehicle that evaluate a seat belt and determine if it is buckled and if it is properly routed on a passenger. In order to evaluate the seat belt status, the system and method use seat belt sensors and cameras inside the vehicle cabin to generate data that is then analyzed in conjunction with machine learning techniques (e.g., supervised machine learning techniques implemented through the use of neural networks) to classify the seat belt status into one or more categories, such as: passenger not present, passenger present/seat belt not being worn, passenger present/seat belt being worn improperly, passenger present/seat belt being worn properly, and blocked view.

Seat belt status determining system and method

Systems and methods to mitigate an effect of an errant signal on an image sensor of a vehicle involve collecting light and separating the light to obtain signals at different wavelengths. A method includes determining an intensity of the light at each of the different wavelengths, and identifying the errant signal based on the intensity of the light exceeding a threshold value at an errant signal wavelength among the different wavelengths. The errant signal is mitigated using the controller.

Growing community of inventors

Raanana, Israel

Michael Baltaxe