Patents Assigned to Toyota Research Institute, Inc.
  • SYSTEMS AND METHODS FOR COMMUNICATING A BLENDING PARAMETER
    Publication number: 20230322254
    Abstract: System, methods, and other embodiments described herein relate to communicating a blending parameter. In one embodiment, a method includes obtaining a blending parameter that is indicative of a degree to which control of a vehicle is shared between an operator of the vehicle and an advanced driver-assistance system (ADAS) of the vehicle. The method further includes determining a feedback parameter based upon the blending parameter and a psychophysical model, wherein the psychophysical model optimizes a relationship between the blending parameter and the feedback parameter such that sensory feedback based upon the feedback parameter is perceived to be proportional to the blending parameter. The method further includes causing a feedback modality of a steering apparatus of the vehicle to provide the sensory feedback based upon the feedback parameter.
    Type: Application
    Filed: April 7, 2022
    Publication date: October 12, 2023
    Applicants: Toyota Research Institute, Inc., Toyota Jidosha Kabushiki Kaisha
    Inventors: Manuel Ludwig Kuehner, Hiroshi Yasuda, Guillermo Pita Gil
  • GRIPPING ASSEMBLY AND METHODS OF USE THEREOF
    Publication number: 20230321848
    Abstract: A gripping assembly for gripping an object is provided. The gripping assembly includes a gripping member. The gripping member includes a mounting base and a plurality of fingers. The plurality of fingers include a central finger and a plurality of adjoining fingers. The central finger is slidably coupled to the mounting base such that the central finger is movable in a lateral direction. The plurality of adjoining fingers are positioned on opposing sides of the central finger in a longitudinal direction. Each of the plurality of adjoining fingers are pivotally coupled to the mounting base and coupled to the central finger such that a movement of the central finger in the lateral direction pivots the plurality of adjoining fingers with respect to the mounting base.
    Type: Application
    Filed: April 7, 2022
    Publication date: October 12, 2023
    Applicant: Toyota Research Institute, Inc.
    Inventors: Andrew M. Beaulieu, Alexander Alspach
  • SYSTEM AND METHOD FOR SELF-SUPERVISED MONOCULAR GROUND-PLANE EXTRACTION
    Publication number: 20230326055
    Abstract: A method for controlling an agent to navigate through an environment includes generating a depth map associated with a monocular image of the environment. The method also includes generating a group of surface normal. Each surface normal of the group of surface normals is associated with a respective polygon of a group of polygons associated with the depth map. The method further includes identifying one or more ground planes in the depth map based on the group of surface normal. The method further includes controlling the agent to navigate through the environment based on identifying the one or more ground planes.
    Type: Application
    Filed: June 15, 2023
    Publication date: October 12, 2023
    Applicant: TOYOTA RESEARCH INSTITUTE, INC.
    Inventors: Vitor GUZILINI, Rares A. AMBRUS, Adrien David GAIDON
  • VEHICLE SAFETY OPERATION MANAGER FOR DRIVER ASSISTANCE FUNCTIONS
    Publication number: 20230322273
    Abstract: A method for managing autonomous operation of a vehicle includes detecting, while the vehicle is operating in an autonomous mode, an assistance condition that triggers activation of an assistance component of a set of assistance components associated with a driver assistance system. The method also includes determining whether the operation of the vehicle in the autonomous mode satisfies a safety condition associated with the assistance component. The method further includes adjusting an activation signal that triggers the activation of the assistance component based on determining the operation of the vehicle in the autonomous mode satisfies the safety condition.
    Type: Application
    Filed: April 6, 2022
    Publication date: October 12, 2023
    Applicant: TOYOTA RESEARCH INSTITUTE, INC.
    Inventors: Yiting LIU, Hirofumi YAMAMOTO, Chen BAO, Thomas JOHNSTON, Kazunori NIMURA
  • PROVABLE GUARANTEES FOR SELF-SUPERVISED DEEP LEARNING WITH SPECTRAL CONTRASTIVE LOSS
    Publication number: 20230326188
    Abstract: A method for self-supervised learning is described. The method includes generating a plurality of augmented data from unlabeled image data. The method also includes generating a population augmentation graph for a class determined from the plurality of augmented data. The method further includes minimizing a contrastive loss based on a spectral decomposition of the population augmentation graph to learn representations of the unlabeled image data. The method also includes classifying the learned representations of the unlabeled image data to recover ground-truth labels of the unlabeled image data.
    Type: Application
    Filed: April 6, 2022
    Publication date: October 12, 2023
    Applicants: TOYOTA RESEARCH INSTITUTE, INC., THE BOARD OF TRUSTEES OF THE LELAND STANFORD JUNIOR UNIVERSITY
    Inventors: Jeff Z. HAOCHEN, Colin WEI, Adrien David GAIDON, Tengyu MA
  • Using a multimode neural network to determine a representation of a spatial structure objects in an image
    Patent number: 11783591
    Abstract: A representation of a spatial structure of objects in an image can be determined. A mode of a neural network can be set, in response to a receipt of the image and a receipt of a facing direction of a camera that produced the image. The mode can account for the facing direction. The facing direction can include one or more of a first facing direction of a first camera disposed on a vehicle or a second facing direction of a second camera disposed on the vehicle. The neural network can be executed, in response to the mode having been set, to determine the representation of the spatial structure of the objects in the image. The representation of the spatial structure of the objects in the image can be transmitted to an automotive navigation system to determine a distance between the vehicle and a specific object in the image.
    Type: Grant
    Filed: June 11, 2020
    Date of Patent: October 10, 2023
    Assignee: Toyota Research Institute, Inc.
    Inventors: Sudeep Pillai, Vitor Guizilini, Rares A. Ambrus, Adrien David Gaidon
  • System and method for estimating depth uncertainty for self-supervised 3D reconstruction
    Patent number: 11783541
    Abstract: A method for three-dimensional (3D) scene reconstruction by an agent includes estimating an ego-motion of the agent based on a current image from a sequence of images and a previous image from the sequence of images. Each image in the sequence of images may be a two-dimensional (2D) image. The method also includes estimating a depth of the current image via a depth estimation model comprising a group of encoder layers and a group of decoder layers. The method further includes generating a 3D reconstruction of the current image based on the estimated ego-motion and the estimated depth. The method still further includes controlling an action of the agent based on the 3D reconstruction.
    Type: Grant
    Filed: May 2, 2022
    Date of Patent: October 10, 2023
    Assignee: TOYOTA RESEARCH INSTITUTE, INC.
    Inventors: Vitor Guizilini, Adrien David Gaidon
  • Monocular depth supervision from 3D bounding boxes
    Patent number: 11783593
    Abstract: A method for navigating a vehicle through an environment includes assigning a first weight to each pixel associated with a dynamic object and assigning a second weight to each pixel associated with a static object. The method also includes generating a dynamic object depth estimate for the dynamic object and generating a static object depth estimate for the static object, an accuracy of the dynamic object depth estimate being greater than an accuracy of the static object depth estimate. The method still further includes generating a 3D estimate of the environment based on the dynamic object depth estimate and the static object depth estimate. The method also includes controlling an action of the vehicle based on the 3D estimate of the environment.
    Type: Grant
    Filed: June 2, 2022
    Date of Patent: October 10, 2023
    Assignee: TOYOTA RESEARCH INSTITUTE, INC.
    Inventors: Vitor Guizilini, Adrien David Gaidon
  • Systems and methods for corridor intent prediction
    Patent number: 11783178
    Abstract: A method includes generating a training data set comprising a plurality of training examples, wherein each training example is generated by receiving map data associated with a road portion, receiving sensor data associated with a road agent located on the road portion, defining one or more corridors associated with the road portion based on the map data and the sensor data, extracting a plurality of agent features associated with the road agent based on the sensor data, extracting a plurality of corridor features associated with each of the one or more corridors based on the sensor data, and for each corridor, labeling the training example based on the position of the road agent with respect to the corridor, and training a neural network using the training data set.
    Type: Grant
    Filed: July 30, 2020
    Date of Patent: October 10, 2023
    Assignee: TOYOTA RESEARCH INSTITUTE, INC.
    Inventors: Blake Warren Wulfe, Wolfram Burgard
  • GENERATING AN AIR CUSHION THROUGH A PERFORATED SURFACE TO PREVENT TRAVEL DIRECTION-FACING SURFACES FROM COLLECTING DEBRIS
    Publication number: 20230311839
    Abstract: Systems and methods are provided for preventing headwind debris from collecting on travel direction-facing housing surfaces of a vehicle by creating protective “air cushions” in front of the travel direction-facing housing surfaces. These air cushions may divert headwind air away from the travel direction-facing housing surfaces, ensuring that headwind debris does not collect on them. Examples may create these protective air cushions by propelling high pressure air through perforated surfaces in a contrary direction to headwind.
    Type: Application
    Filed: April 5, 2022
    Publication date: October 5, 2023
    Applicants: TOYOTA JIDOSHA KABUSHIKI KAISHA, TOYOTA RESEARCH INSTITUTE, INC.
    Inventors: Manuel Ludwig KUEHNER, Hiroshi YASUDA, Guillermo PITA GIL, Jaime S. CAMHI
  • COMMUNICATING A BLENDING CONTROL PARAMETER USING A SEAT OF A VEHICLE
    Publication number: 20230311924
    Abstract: Systems and methods are provided for communicating a blending parameter via tactile feedback at a driver's seat of a vehicle (examples of tactile feedback may comprise vibrations and temperature/heat applied through the driver's seat). The blending parameter may represent the ratio between the driver's level of authority and an autonomous driving system's level of authority in performing a driving task (e.g., lateral steering). By communicating changes to a blending parameter over time, examples can help a driver form a mental picture of how the vehicle/autonomous driving system is operating. This feedback/understanding may by advantageous for various purposes such as driver coaching and helping drivers become more comfortable with autonomous driving systems.
    Type: Application
    Filed: April 5, 2022
    Publication date: October 5, 2023
    Applicants: TOYOTA JIDOSHA KABUSHIKI KAISHA, TOYOTA RESEARCH INSTITUTE, INC.
    Inventors: MANUEL LUDWIG KUEHNER, HIROSHI YASUDA, GUILLERMO PITA GIL
  • SYSTEMS AND METHODS FOR VISUAL CUES ON A STEERING APPARATUS
    Publication number: 20230311989
    Abstract: System, methods, and other embodiments described herein relate to providing visual cues on a steering apparatus of a vehicle. In one embodiment, a method includes determining a difference between a current angle of a steering apparatus of a vehicle and a recommended angle of the steering apparatus. The method further includes illuminating a region of a grip of the steering apparatus based upon the difference and a position of a hand of an operator of the vehicle on the grip. The method additionally includes unilluminating the region as the steering apparatus is rotated from the current angle to the recommended angle.
    Type: Application
    Filed: April 5, 2022
    Publication date: October 5, 2023
    Applicants: Toyota Research Institute, Inc., Toyota Jidosa Kabushiki Kaisha
    Inventors: Manuel Ludwig Kuehner, Hiroshi Yasuda, Scott Michael Harris
  • System and method for tracking detected objects
    Patent number: 11775615
    Abstract: Systems and methods for tracking objects are disclosed herein. In one embodiment, a system having a processor merges features of detected objects extracted from a point cloud and a corresponding image to generate fused features for the detected objects, generates a learned distance metric for the detected objects using the fused features, determines matched detected objects and unmatched detected objects, applies prior tracking identifiers of the detected objects at the prior time to the matched detected objects, determines a confidence score for the fused features of the unmatched detected objects, and applies new tracking identifiers to the unmatched detected objects based on the confidence score.
    Type: Grant
    Filed: April 28, 2021
    Date of Patent: October 3, 2023
    Assignees: Toyota Research Institute, Inc., The Board of Trustees of the Leland Stanford Junior University
    Inventors: Hsu-kuang Chiu, Jie Li, Rares A. Ambrus, Christin Jeannette Bohg
  • Deterministic agents for simulation
    Patent number: 11775706
    Abstract: Systems and methods simulation of an ego vehicle using deterministic agents may include obtaining a set of deterministic agents for the simulation of the ego vehicle; executing the simulation of the ego vehicle using deterministic agents of the set of deterministic agents to provide simulated traffic in the simulation; determining and outputting a current state of the simulation; determining an agent action based on the determined current state; and requesting an update of a deterministic agent of the set of deterministic agents based on the determined agent action.
    Type: Grant
    Filed: November 16, 2020
    Date of Patent: October 3, 2023
    Assignee: TOYOTA RESEARCH INSTITUTE, INC.
    Inventors: Andrew Best, Liang Fok
  • Systems and methods for traffic light detection and classification
    Patent number: 11776281
    Abstract: A traffic light classification system for a vehicle includes an image capture device to capture an image of a scene that includes a traffic light with multiple light signals, a processor, and a memory communicably coupled to the processor and storing a first neural network module including instructions that when executed by the processor cause the processor to determine, based on inputting the image into a neural network, a semantic keypoint for each light signal in the traffic light, and determine, based on each semantic keypoint, a classification state of each light signal.
    Type: Grant
    Filed: December 22, 2020
    Date of Patent: October 3, 2023
    Assignee: Toyota Research Institute, Inc.
    Inventors: Kun-Hsin Chen, Kuan-Hui Lee, Jia-En Pan, Sudeep Pillai
  • Systems and methods for predicting control handback
    Patent number: 11772671
    Abstract: Embodiments described herein include systems and methods for predicting a transfer of control of a vehicle to a driver. A method includes receiving information about an environment of the vehicle, identifying at least one condition represented in the information about the environment of the vehicle that corresponds to at least one of one or more known conditions that lead to a handback of operational control of the vehicle to the driver, and predicting the transfer of control of the vehicle to the driver based on the at least one condition identified from the information about the environment of the vehicle.
    Type: Grant
    Filed: June 3, 2019
    Date of Patent: October 3, 2023
    Assignee: Toyota Research Institute, Inc.
    Inventor: Simon A. I. Stent
  • Systems and methods for predicting battery life using data from a diagnostic cycle
    Patent number: 11768249
    Abstract: System, methods, and other embodiments described herein relate to improving the estimation of battery life. In one embodiment, a method includes measuring electrochemical data of a battery cell associated with an electrochemical reaction triggered by a test during a diagnostic cycle. The method also includes determining a feature associated with the degradation of the battery cell from the electrochemical data. The method also includes predicting an end-of-life (EOL) of the battery cell by using the feature in a machine learning (ML) model.
    Type: Grant
    Filed: March 31, 2021
    Date of Patent: September 26, 2023
    Assignees: Toyota Research Institute, Inc., Massachusetts Institute of Technology, The Board of Trustees of the Leland Stanford Junior University
    Inventors: William C. Chueh, Bruis van Vlijmen, William E. Gent, Vivek Lam, Patrick K. Herring, Chirranjeevi Balaji Gopal, Patrick A. Asinger, Benben Jiang, Richard Dean Braatz, Xiao Cui, Gabriel B. Crane
  • Systems and methods for remotely assisting an operator
    Patent number: 11767021
    Abstract: System, methods, and other embodiments described herein relate to remotely assisting an operator that is impaired using alerts from a vehicle. In one embodiment, a method includes receiving, by a first vehicle using a communications network, assistance information about an operator and a second vehicle near the first vehicle, wherein the assistance information indicates a state of the operator and a position of the second vehicle. The method also includes, upon approving an action according to the state and the position, selecting an alert that changes the state according to the position and attributes determined according to sensor data of the first vehicle. The method also includes activating the alert by the first vehicle.
    Type: Grant
    Filed: September 15, 2021
    Date of Patent: September 26, 2023
    Assignee: Toyota Research Institute, Inc.
    Inventors: Hiroshi Yasuda, Manuel Ludwig Kuehner
  • Distinguishing, in a point cloud data set represented by an image, a first object from a second object
    Patent number: 11769272
    Abstract: In a point cloud data set represented by an image, a first object can be caused to be distinguished from a second object. Current positions of points in the point cloud data set can be arguments for functions of a set of functions. The set of functions can include attraction functions for the points and repulsion functions for the points. Results of the set of functions can be calculated. Based on the results, at least some of the points can be caused to move from the current positions to new positions. In the point cloud data set represented by the image with the at least some of the points being at the new positions, the first object can be distinguished from the second object.
    Type: Grant
    Filed: July 30, 2020
    Date of Patent: September 26, 2023
    Assignee: Toyota Research Institute, Inc.
    Inventor: Jacopo Serafin
  • MULTI-CAMERA COST VOLUMES FOR SELF-SUPERVISED DEPTH ESTIMATION
    Publication number: 20230298191
    Abstract: A method may include receiving a first image of a scene captured by a first camera at a first time step and plurality of other images of the scene captured by a plurality of other cameras at a plurality of time steps, determining a geometric relationship between the first camera at the first time step and each of the other cameras at the plurality of time steps, determining a cost volume for the first image captured by the first camera at the first time step based on the first image, the plurality of other images, and the geometric relationship between the first camera at the first time step and each of the other cameras at the plurality of time steps, and determining a depth map for the first image based on the cost volume, the depth map comprises a depth value of each pixel of the first image.
    Type: Application
    Filed: March 16, 2022
    Publication date: September 21, 2023
    Applicant: Toyota Research Institute, Inc.
    Inventors: Vitor Guizilini, Jie Li