公开(公告)号：US20240233351A1

公开(公告)日：2024-07-11

申请号：US18545874

申请日：2023-12-19

Applicant: Torc Robotics, Inc.

Inventor： Emmanuel Luc Julien Onzon ,  Felix Heide ,  Maximilian Rufus Bömer ,  Fahim Mannan

IPC: G06V10/80 ,  G06T5/70 ,  G06V10/60 ,  G06V10/82

CPC classification number: G06V10/806 ,  G06T5/70 ,  G06V10/60 ,  G06V10/82

Abstract: Departing from conventional HIDR image fusion approach, a learned task-driven fusion in the feature domain is disclosed. Instead of using a single companded image, the disclosed method exploits semantic features from all exposures learned in an end-to-end fashion with supervision from downstream detection losses. The method outperforms all tested conventional HDR exposure fusion and auto-exposure methods in challenging automotive HIDR scenarios.

公开(公告)号：US20240217544A1

公开(公告)日：2024-07-04

申请号：US18343109

申请日：2023-06-28

Applicant: TORC Robotics, Inc.

Inventor： Harish PULLAGURLA ,  Ryan CHILTON ,  Jason William HARPER ,  Jordan Grant STONE

IPC: B60W60/00

CPC classification number: B60W60/001 ,  B60W2552/00 ,  B60W2554/4046 ,  B60W2556/40 ,  B60W2556/45 ,  B60W2720/10

Abstract: A method of controlling an autonomous vehicle, including: collecting perception data representing a perceived environment of the vehicle using a perception system on board the autonomous vehicle; comparing the perception data collected with digital map data; and modifying operation of the vehicle based on an amount of difference between the perception data and the digital map data.

公开(公告)号：US20240208492A1

公开(公告)日：2024-06-27

申请号：US18194243

申请日：2023-03-31

Applicant: TORC Robotics, Inc.

Inventor： Ryan CHILTON

IPC: B60W30/095 ,  B60W30/09 ,  B60W60/00

CPC classification number: B60W30/095 ,  B60W30/09 ,  B60W60/0015 ,  B60W2554/20 ,  B60W2554/402 ,  B60W2554/80

Abstract: Systems and methods for path planning for autonomous vehicles err on the side of a safer road position and safer type of collision if one were to occur. An autonomous vehicle perception module detects target objects within a region of interest (ROI). An autonomous vehicle processor estimates relative velocity between the ego vehicle and target objects, and estimates mass of target objects. Collision-aware path planning calculates a cost function that assigns higher costs for paths that take the vehicle close to objects that have a large velocity difference and higher costs for objects with large estimated mass. Path planning provides a cost map that yields a path that has appropriate buffer distances between the autonomous vehicle and surrounding objects. In the event the ego vehicle balances buffer distance margins to multiple surrounding target objects, target objects that would create more severe collisions are given greater buffer distance.

公开(公告)号：US20240127584A1

公开(公告)日：2024-04-18

申请号：US18526787

申请日：2023-12-01

Applicant: Torc Robotics, Inc.

Inventor： Emmanuel Luc Julien Onzon ,  Felix Heide ,  Maximilian Rufus Bömer ,  Fahim Mannan

IPC: G06V10/776 ,  G06T5/40 ,  G06T5/50 ,  G06T7/11 ,  G06V10/77 ,  G06V10/80 ,  G06V10/94 ,  G06V20/00

CPC classification number: G06V10/776 ,  G06T5/40 ,  G06T5/50 ,  G06T7/11 ,  G06V10/7715 ,  G06V10/806 ,  G06V10/955 ,  G06V20/38 ,  G06T2207/10144 ,  G06T2207/20161

Abstract: A computer-vision pipeline is organized as a closed loop of a sensor-processing phase, an image-processing phase, and an object-detection phase, each comprising a respective phase processor coupled to a master processor. The sensor-processing phase creates multiple exposure images, and derives multi-exposure multi-scale zonal illumination-distributions, to be processed independently in the image-processing phase. In a first implementation of the object-detection phase, extracted exposure-specific features are pooled prior to overall object detection. In a second implementation, exposure-specific objects, detected from the exposure-specific features, are fused to produce the sought objects of a scene under consideration. The two implementations enable detecting fine details of a scene under diverse illumination conditions. The master processor performs loss-function computations to derive updated training parameters of the processing phases. Several experiments applying a core method of operating the computer-vision pipelines, and variations thereof, ascertain performance gain under challenging illumination conditions.

公开(公告)号：US20240104938A1

公开(公告)日：2024-03-28

申请号：US18303456

申请日：2023-04-19

Applicant: TORC Robotics, Inc.

Inventor： Ryan CHILTON ,  Harish PULLAGURLA ,  Joseph STAMENKOVICH

IPC: G06V20/56 ,  G01S19/47 ,  G06V10/774

CPC classification number: G06V20/588 ,  G01S19/47 ,  G06V10/774

Abstract: Systems and methods for training and executing machine learning models to generate lane index values are disclosed. A method includes identifying a set of image data captured by at least one autonomous vehicle when the at least autonomous vehicle is positioned in a lane of a roadway and respective ground truth localization data; determining a plurality of lane index values for the set of image data based on the ground truth localization data; labeling the set of image data with the plurality of lane index values, the lane index values representing a number of lanes from a leftmost or rightmost lane to the lane in which the at least one autonomous vehicle was positioned; and training, using the labeled set of image data, a plurality of machine learning models that generate a left lane index value and a right lane index value as output.

公开(公告)号：US20250153739A1

公开(公告)日：2025-05-15

申请号：US18505782

申请日：2023-11-09

Applicant: Torc Robotics, Inc.

Inventor： Akshay Pai Raikar ,  Joseph R. Fox-Rabinovitz ,  William Davis ,  Dakota James Hebert ,  Justin Yurkanin

IPC: B60W60/00 ,  B60W50/06 ,  E01H10/00 ,  G06Q50/30

Abstract: An autonomous vehicle is provided. The autonomous vehicle includes one or more sensors and an autonomy computing system. The autonomy computing system includes at least one processor in communication with at least one memory device. The at least one processor is programmed to receive sensor data from the one or more sensors, and receive weather-related data from a mission control computing system. The weather-related data include fleet data from autonomous vehicles in a fleet. The fleet includes the autonomous vehicle. The at least one processor is further programmed to determine an icy condition is present based on the sensor data and the fleet data, and determine de-icing strategies based on the icy condition.

公开(公告)号：US20250069238A1

公开(公告)日：2025-02-27

申请号：US18238439

申请日：2023-08-25

Applicant: TORC Robotics, Inc.

Inventor： Dalong Li ,  Syed Taha Shoaib ,  Juncong Fei

IPC: G06T7/246

Abstract: Aspects of this technical solution can include obtaining, by one or more processors coupled with non-transitory memory, a first plurality of images each including corresponding first time stamps, the plurality of images corresponding to video data of a physical environment, extracting, by the one or more processors and from among the first plurality of images, a second plurality of images each having corresponding second time stamps and each having corresponding features indicating an object in the physical environment, and training, by the one or more processors and with input including the features and the second time stamps corresponding to the features, a machine learning model to generate an output indicating a pattern of movement of one or more objects corresponding to the features and the second time stamps corresponding to the features.

公开(公告)号：US20250065914A1

公开(公告)日：2025-02-27

申请号：US18238437

申请日：2023-08-25

Applicant: TORC Robotics, Inc.

Inventor： Justin CHONG

IPC: B60W60/00

Abstract: A method of determining a location of an autonomous vehicle hub including receiving from one or more sensors associated with a portable sensor apparatus, a signal associated with a drivable area; applying the signal associated with the drivable area to a viability model, wherein the viability model is configured to: simulate an entrance procedure of one or more autonomous vehicles into the drivable area; determine, based at least on the signal associated with the drivable area, a drivable surface on which an autonomous vehicle may travel to enter the drivable area; determine, based at least on the signal associated with the drivable area, a frequency in which the drivable surface is available for the autonomous vehicle to enter the drivable area; and output a viability score associated with the drivable area, the viability score indicating a viability of establishing the autonomous vehicle hub proximate the drivable area.

公开(公告)号：US20250065904A1

公开(公告)日：2025-02-27

申请号：US18238433

申请日：2023-08-25

Applicant: TORC Robotics, Inc.

Inventor： Justin CHONG

IPC: B60W60/00 ,  G06V20/54 ,  G06V20/56

Abstract: A system including a supervisory computing device and a sensor apparatus positioned at a drivable intersection, the sensor apparatus remote from an autonomous vehicle and in communication with the autonomous vehicle. The sensor apparatus includes one or more sensors and one or more processors configured to receive from the sensors an indication of a presence of the autonomous vehicle at the drivable intersection and alert the supervisory computing device of the presence of the autonomous vehicle. The processors then receive a signal associated with a drivable area on which the autonomous vehicle may travel and predict a drivable path for the autonomous vehicle. The processors transmit an indication of the drivable path to the supervisory computing device to request approval to travel the drivable path. Upon receiving approval, the one or more processors transmit a signal to adjust an operating parameter to initiate travelling on the drivable path.

公开(公告)号：US20250058803A1

公开(公告)日：2025-02-20

申请号：US18235793

申请日：2023-08-18

Applicant: TORC Robotics, Inc.

Inventor： Adam SHOEMAKER ,  John BLANKENHORN ,  Garrett MADSEN ,  Joshua PETRIN ,  Ajay TULSYAN ,  Paul BROWN ,  Savio PEREIRA ,  William DAVIS ,  Daniel FERNÁNDEZ ,  Yexuan HAO

IPC: B60W60/00 ,  G08G1/16

Abstract: Embodiments herein include systems and methods of generating lane selection cost values to control autonomous vehicles to accommodate merging vehicles in a tapering lane (or merge lane). An autonomy system can identify a tapering lane in map data and detect a merging vehicle situated in the tapering lane using perception sensor data. The autonomy system includes a lane-selection cost function that generates lane-selection cost values for the lanes available to the automated vehicle, which the autonomy system references to determine whether to continue traveling a current lane or change lanes into an adjacent lane. The lane-selection cost function may apply a courtesy weight when detecting the merging vehicle, such that the autonomy system causes the automated vehicle to change lanes as a courtesy to the merging vehicle, but without overriding other safety-related factors of the lane-selection cost function or trajectory planning functions.