Gm Global Technolgoy Operations, Inc.

Omer Tsimhoni

Ron M Hecht

Ke Liu

Yi G Glaser

Jingyan Wan

Andrew J MacDonald

Ariel Telpaz

Venkata Naga Siva Vikas Vemuri

Ronit Bustin

Gershon Celniker

Chandra S Namuduri

Gila Kamhi

Vivek Vijaya Kumar

Roy J Mathieu

Claudia V Goldman-Shenhar

Charles Allen Everhart

Yael Shmueli Friedland

Wenyuan Qi

Zahy Bnaya

Shaul Oron

Ashhad Mohammed

Aravind Gangumalla

Daniel S Glaser

Vishnu Chikondla

Andrea Forgacs

John Wesley Phillips

Rajas M Sevekari

Gustav Franz Gerlach, V

Erik Robert Bare

Scott Thomas Martin

Asaf Degani

Ohad Rahamim

A method of training a disparity estimation network. The method includes obtaining an eye-gaze dataset having first images with at least one gaze direction associated with each of the first images. A gaze prediction neural network is trained based on the eye-gaze dataset to develop a model trained to provide a gaze prediction for an external image. A depth database is obtained that includes second images having depth information associated with each of the second images. A disparity estimation neural network for object detection is trained based on an output from the gaze prediction neural network and an output from the depth database.

System and method for eye-gaze direction-based pre-training of neural networks

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

Systems and methods are provided for vehicular computation management. The system includes, onboard a vehicle, electric control units (ECUs), a battery, a communication system, and a controller. The controller is configured to monitor energy consumption, operate the vehicle as a computational hub when the energy consumption is less than a threshold, including providing computational resources to an external node, determine whether the vehicle has excess energy and computational capacity when the energy consumption is equal to or greater than the threshold, including determining a usage of each of the ECUs and determining an energy consumption of tasks executing thereon, and operate the vehicle as a hybrid computational hub when the vehicle has excess energy and computational capacity, including providing excess computational capacity of the ECUs to the external node.

Systems and methods for vehicular computation management

A system of managing charging schedules in a fleet having electric vehicles includes a command unit. The command unit has a processor and tangible, non-transitory memory on which instructions are recorded. The command unit is adapted to define a plurality of discharge categories, including a transportation category, a transfer category and a reserve energy category. The respective battery power in the electric vehicles is proportioned by setting a respective percentage allocation for the plurality of discharge categories. The command unit is adapted to signal the electric vehicles to charge when at least one of the plurality of discharge categories falls below the respective percentage allocation. The command unit may be adapted to group the electric vehicles in respective virtual boxes based in part on their respective physical locations.

Management of charging schedules in fleet having electric vehicles

A system and method for limited rate context-based eye gaze encoding includes generating, based on an outward looking camera situated in a vehicle, a first video stream of a surrounding environment to a controller. The controller generates a scene description based on the first video stream and selects a corresponding scene from a predefined list of known scenes. Further, the controller, based on the selected corresponding scene, selects a codebook of encoding and decoding parameters from a plurality of predefined codebooks. Based on an inward looking camera situated in the vehicle, a second video stream of a face of a driver to an eye tracker controller is generated, where the eye tracker controller estimates a gaze direction of the driver. Encoded data comprising the estimated gaze direction of the driver is transmitted over a bandwidth limited channel to a decoder, based on the selected codebook, the encoded data.

Limited rate context based eye gaze encoding

A system for control of an automated device includes a control system configured to operate a device during an operating mode corresponding to a first state in which the control system automatically controls operation, the operating mode prescribing that a user monitor the device operation during automated control, and a scheduling module configured to, during the operating mode, receive a request for the user to temporarily stop monitoring in order to perform a task unrelated to the device operation, allocate a time period during which automated control is maintained and the user stops monitoring, the time period including a non-monitoring period having a duration based on a minimum amount of time for the task, and put the device into a temporary state at initiation of the allocated time period during which the user stops monitoring and automated control is maintained.

Allocation of non-monitoring periods during automated control of a device

A method of retrieving a lost item from a compartment to an owner of the lost item is provided. The method comprises detecting the lost item in the compartment to define an item image of the lost item relative to the compartment, updating an inventory list of lost objects, and identifying at least one potential user of the lost item. The method further comprises providing notification to the at least one potential user and providing viewable access of the item image. The method further comprises verifying ownership of the lost item to define the owner of the lost item, determining a preferred pickup location for the owner, storing the lost item at the preferred location defining a stored item, and confirming identity of the owner for retrieval of the stored item at the preferred location. The method further comprises allowing access to the stored item from the preferred location.

System and method of retrieving a lost item

A system comprises a computer including a processor and a memory. The memory includes instructions such that the processor is programmed to: execute an autonomous vehicle algorithm simulating vehicle operations determine whether a notification that provides information on how a driver intervention for actuation by system feature functions has been at least one of previously presently or confirmed and cause the notification to be generated. The notification includes information for responding to a finite number of driving options determined by the driver intervention for actuation by system.

Minimal-prerequisite interaction protocol for driver-assisted automated driving

A full speed range adaptive cruise control system for a vehicle that stops at an intersection includes one or more controllers that execute instructions to receive localization data and situational data related to the vehicle. The one or more controllers determine, based on localization data and situational data, that the vehicle is approaching an intersection and will come to a stop at the intersection, where the vehicle is part of a queue including one or more surrounding vehicles. In response to determining the vehicle has come to a stop, the controller determines a position of the vehicle within the queue and an overall length of the queue. The controller calculates an adaptive launch time based on at least the position of the vehicle within the queue, the overall length of the queue, the situational data, and a timing delay associated with the queue.

Full speed range adaptive cruise control system for determining an adaptive launch time for a vehicle

A method of managing operator take-over of autonomous vehicle. The method includes gathering information on an external surrounding of the autonomous vehicle; analyzing the gathered information on the external surrounding of the autonomous vehicle to determine an upcoming traffic pattern; gathering information on an operator of the autonomous vehicle; analyzing the gathered information on the operator of the autonomous vehicle to determine an operator behavior; predicting an operator action based on the determined upcoming traffic pattern and the determined operator behavior; and initiating a predetermined vehicle response based on the predicted operator action. The predicting the operator action includes comparing the determined upcoming traffic pattern with a similar historic traffic pattern and retrieving a historical operator action in response to the similar historical pattern.

System and method of managing a driver take-over from an autonomous vehicle based on monitored driver behavior

A control system for a vehicle comprises a controller comprising a processor and a non-transitory computer-readable medium including instructions. The system comprises first, second, and third inputs configured to be manipulated by an operator. The system comprises first, second, and third displays adjacent the first, second, and third inputs, respectively. The first, second and third displays are configured to show first, second, and third indicia, respectively. Manipulation of the first input by the operator transmits a selection input signal to the controller. The controller receives the selection input signal. The processor compares the selection input signal to the instructions in the non-transitory computer-readable medium, transmits a selection output signal to the second and third displays, removes the second and third indicia from the second and third displays, and shows a first sub-selection indicium on the second display and a second sub-selection indicium on the third display.

Control system comprising first, second, and third inputs and first, second, and third displays, and a method of operating the same

A vehicle system includes: at least one of (a) an advanced driving system configured to aid a driver of a vehicle in performance of at least one driving maneuver based on input from at least one of a sensor and a camera and (b) an advanced driving feature; and a usage module configured to: when the at least one of (a) the advanced driving system and (b) the advanced driving feature is off, determine whether the at least one of (a) the advanced driving system and (b) the advanced driving feature could be on and used based on at least one of: at least one present vehicle operating parameter; at least one present road parameter; at least one present traffic parameter; and at least one present environmental parameter.

Advanced driving system and feature usage monitoring systems and methods

A method of notifying an owner of a lost item in a vehicle having a vehicle compartment is provided. The method comprises providing at least one sensor to sense the lost item in the vehicle compartment. The method further comprises sensing the lost item on a point relative to a spherical coordinate system to define a sensed item data and determining a position of the lost item in cartesian coordinates based on the sensed item data to define a position data. The method further comprises translating the sensed item data and the position data for visualization of the lost item to define an item image of the lost item relative to the vehicle compartment, and updating an inventory list of lost objects to include the lost item with the item image. The method further comprises identifying the owner of the lost item by way of a perception algorithm, providing notification to the owner of the lost item, and providing viewable access of the item image such that the image is viewed by the owner of the lost item.

System and method of notifying an owner of a lost item in a vehicle

A risk assessment system is provided and includes a transceiver, an output device, and activity, localization, tracking, and risk assessment modules. The activity module: receives signals from sensors or electrical devices of a supporting structure; and tracks activities in or within a set distance of the supporting structure to generate an activity history log. The localization module relates the activities to aspects of the supporting structure and generates corresponding localization data. The transceiver receives a notification key identifying a network device used by a user exposed to a contaminant. The tracking module, in response to the notification key, tracks contamination states of the aspects of the supporting structure contacted directly or indirectly by the user. The risk assessment module determines and reports an exposure risk level of an occupant of the supporting structure based on the contamination states, the localization data and the activity history log.

Growing community of inventors

Bloomfield Hills, MI, United States of America

Omer Tsimhoni