-
公开(公告)号：US20240420356A1
公开(公告)日：2024-12-19
申请号：US18743696
申请日：2024-06-14
Applicant: Torc Robotics, Inc.
Inventor： Felix Heide , Fahim Mannan , Mario Bijelic
Abstract: A perception system including at least one memory, and at least one processor configured to: (i) compute, in a stereo branch, disparity from a pair of stereo images including a left image and a right image; (ii) based on the computed disparity from the pair of stereo images, output, by the stereo branch, a depth for the left image and a depth for the right image; (iii) compute an absolute depth for the left image in a first monocular branch and an absolute depth for the right image in a second monocular branch; (iv) compute, in a first fusion branch, a depth map for the left image; (v) compute, in a second fusion branch, a depth map for the right image; and (vi) generate a single fused depth map based on the depth map for the left image and the depth map for the right image, is disclosed.
-
公开(公告)号：US20240371171A1
公开(公告)日：2024-11-07
申请号：US18311620
申请日：2023-05-03
Applicant: TORC Robotics, Inc.
Inventor： Daniel MOODIE
Abstract: A vehicle comprises one or more sensors, and a processor coupled with the one or more sensors and stored inside a housing of the vehicle. The processor can be configured to collect data regarding the environment surrounding the vehicle from the one or more sensors; detect a second vehicle and an observed trajectory of the second vehicle from the collected data, the observed trajectory indicating a position or speed of the second vehicle over a time period; compare the observed trajectory with one or more expected trajectories of the second vehicle; responsive to determining a deviation between the observed trajectory and at least one of the one or more expected trajectories satisfies a condition, generate a record indicating the deviation and including a video of the second vehicle that corresponds to the observed trajectory; and transmit the record to a remote processor.
-
63.发明公开公开(公告)号：US20240331366A9
公开(公告)日：2024-10-03
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
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：US20240326816A1
公开(公告)日：2024-10-03
申请号：US18194212
申请日：2023-03-31
Applicant: TORC Robotics, Inc.
Inventor： Harish KARUNAKARAN , Joseph ADKISSON , Pradeep ILLAYAPERUMAL SELVARAJU
CPC classification number: B60W30/18163 , B60W60/001 , B60W2520/06
Abstract: Embodiments disclosed herein include systems and methods for generating proposed driving paths for an automated vehicle performing a lane-change. An autonomy system continually generates reference trajectories. The autonomy system then iteratively and recursively generates clothoid points tracing the reference trajectory, by the computer, but constrained by clothoid thresholds. The clothoid points define a clothoid representing a revised trajectory, effectively constrained by the clothoid thresholds. The autonomy system generates and updates driving instructions for the automated vehicle to follow a drive path represented by the clothoid. If the autonomy system determines clothoid points cannot be generated according to the thresholds, then the autonomy system determines the automated vehicle cannot safely or practicably perform the lane change maneuver for the given portion of road. As the autonomy system may continually generate the reference trajectories, the autonomy system may proceed to analyzing a next reference trajectory to perform the lane change maneuver.
-
公开(公告)号：US20240317252A1
公开(公告)日：2024-09-26
申请号：US18335743
申请日：2023-06-15
Applicant: TORC Robotics, Inc.
Inventor： Ryan CHILTON
CPC classification number: B60W50/14 , G06T11/60 , G06V20/582 , B60W2050/146 , B60W2300/12 , B60W2530/00 , B60W2552/00 , G06V10/764
Abstract: Disclosed herein are methods and systems to provide intelligent display for vehicles including a method that comprises determining data associated a road sign; retrieving driving data associated with a vehicle; generating, using the driving data and data associated with the road sign, a graphical overlay presenting a virtual object corresponding to the trajectory of the vehicle or data associated with the vehicle; and presenting on an electronic device associated with the vehicle, the graphical overlay while the electronic device is presenting an image of a surrounding of the vehicle, wherein the graphical overlay is superimposed upon an image of the road sign.
-
Patent Agency Ranking
公开(公告)号：US20240289514A1
公开(公告)日：2024-08-29
申请号：US18192522
申请日：2023-03-29
Applicant: TORC Robotics, Inc.
Inventor： Darrell BOWMAN
CPC classification number: G06F30/20 , B60W50/0205 , B60W60/0051
Abstract: A system can include a driving simulator. The driving simulator can include one or more input devices corresponding to controls of a vehicle; a display; and one or more processors communicatively coupled with the one or more input devices and the display. The one or more processors can be configured to simulate, on the display, an autonomous vehicle driving through a simulated environment in a manual mode based on inputs from the one or more input devices, automatically in an autonomous mode, and transition between manual mode and autonomous mode. The system can include a remote computing device. The remote computing device can be configured to receive an input from a user interface displayed at the remote computing device during a simulation of the autonomous vehicle in the autonomous mode, the input causing a fault in the operation of the autonomous vehicle in the autonomous mode.
-
公开(公告)号：US20240286650A1
公开(公告)日：2024-08-29
申请号：US18192504
申请日：2023-03-29
Applicant: TORC Robotics, Inc.
Inventor： Darrell BOWMAN
CPC classification number: B60W60/0053 , G06F30/20 , B60W2540/10 , B60W2540/12 , B60W2756/10
Abstract: A driving simulator can include one or more input devices; a display; and one or more processors communicatively coupled with the one or more input devices and the display. The one or more processors can be configured to store, in memory, a predetermined path for a simulated vehicle to travel in a simulated environment; execute an application to cause the simulated environment to appear on the display in a autonomous mode in which the application is configured to simulate the simulated vehicle driving by updating the display over time according to the predetermined path; receive an input from at least one of the one or more input devices; and responsive to receiving the input, change the mode of the application from the autonomous mode to a manual mode in which the application is configured to update the display according to inputs from the one or more input devices.
-
公开(公告)号：US20240286609A1
公开(公告)日：2024-08-29
申请号：US18302520
申请日：2023-04-18
Applicant: TORC Robotics, Inc.
Inventor： Adam SHOEMAKER , Christopher HARRISON
IPC: B60W30/095 , B60Q9/00 , B60W60/00
CPC classification number: B60W30/0956 , B60Q9/008 , B60W60/0011 , B60W2554/404
Abstract: Disclosed herein are methods and systems to avoid collisions with animals. In an example, a method comprises receiving, by a processor, an indication that a current trajectory of an autonomous vehicle is associated with a likelihood of a collision that satisfies a collision threshold indicating a potential collision with an animal having an attribute that satisfies a threshold; disabling, by the processor, at least one lighting apparatus associated with the autonomous vehicle; and enabling, by the processor, a sound-generating device associated with the autonomous vehicle.
-
公开(公告)号：US20240278722A1
公开(公告)日：2024-08-22
申请号：US18129275
申请日：2023-03-31
Applicant: TORC Robotics, Inc.
Inventor： John HUTCHINSON
CPC classification number: B60R1/12 , B60R1/076 , B60W60/001 , G01P5/165 , B60R2001/1223 , B60W10/18 , B60W10/20 , B60W2555/00
Abstract: Embodiments described herein include an automated vehicle having a pitot tube mounted to a side-view mirror of the automated vehicle. The pitot gathers samples of wind speed information for calculating three-dimensional wind measurements using the information gathered by the pitot tube. The pitot tube is installed at an area that offers the pitot tube access to outside “clean air,” undisturbed by the vehicle's movement. A controller and/or driving software ingest the three-dimensional wind measurements and generate driving tasks of the automated vehicle based upon the three-dimensional wind measurements.
-
公开(公告)号：US20240101147A1
公开(公告)日：2024-03-28
申请号：US18303460
申请日：2023-04-19
Applicant: TORC Robotics, Inc.
Inventor： Ryan CHILTON , Harish PULLAGURLA , Joseph STAMENKOVICH
IPC: B60W60/00 , G06V10/774 , G06V20/56
CPC classification number: B60W60/001 , G06V10/774 , G06V20/588 , B60W2556/40
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.
-
-
-
-
-
-
-
-
-
Search Results
123
records
(took 0.019 seconds)
