-
公开(公告)号:US11731492B2
公开(公告)日:2023-08-22
申请号:US17334898
申请日:2021-05-31
IPC分类号: B60J3/04 , G06V10/22 , G06V20/59 , G06V20/58 , G06V40/20 , G02F1/1333 , G02F1/163 , G02F1/133 , G02F1/137 , G06V40/18
CPC分类号: B60J3/04 , G06V10/22 , G06V20/584 , G06V20/59 , G06V40/20 , G02F1/137 , G02F1/13306 , G02F1/133302 , G02F1/163 , G06V40/193
摘要: Systems and methods for guiding a vehicle occupant's attention are disclosed herein. One embodiment selects automatically a particular region of an environment external to a vehicle and guides an occupant of the vehicle to look at the particular region by automatically adjusting the transparency of one or more windows of the vehicle such that a first portion of the one or more windows through which the occupant is able to see the particular region is more transparent than a second portion of the one or more windows that is adjacent to the first portion.
-
公开(公告)号:US20230256608A1
公开(公告)日:2023-08-17
申请号:US18167584
申请日:2023-02-10
发明人: Zhenjia Xu , Cheng Chi , Benjamin Burchfiel , Eric Cousineau , Siyuan Feng , Shuran Song
CPC分类号: B25J9/1682 , B25J9/1697 , B25J15/0019
摘要: Systems and methods for manipulating deformable objects using air are disclosed. In one embodiment, a system for manipulating a deformable object, the system includes a first robot arm having a first gripper, a second robot arm having a second gripper, a blower robot arm having an air pump, and one or more processors programmed to control the first robot arm and the second robot arm to grasp the deformable object using the first gripper and the second gripper, respectively, and to control the blower robot arm to perform a plurality of blowing actions onto the deformable object until an objective is satisfied.
-
63.
公开(公告)号:US11727589B2
公开(公告)日:2023-08-15
申请号:US17377684
申请日:2021-07-16
发明人: Vitor Guizilini , Rares Andrei Ambrus , Adrien David Gaidon , Igor Vasiljevic , Gregory Shakhnarovich
IPC分类号: G06T7/55 , B60R1/00 , G06T3/00 , G05D1/02 , G06N3/08 , G06T7/579 , G06T7/292 , G06T7/11 , B60W60/00 , G06T3/40 , G06F18/214 , H04N23/90
CPC分类号: G06T7/55 , B60R1/00 , B60W60/001 , G05D1/0212 , G05D1/0246 , G06F18/214 , G06F18/2148 , G06N3/08 , G06T3/0012 , G06T3/0093 , G06T3/40 , G06T7/11 , G06T7/292 , G06T7/579 , H04N23/90 , B60R2300/102 , B60W2420/42 , G05D2201/0213 , G06T2207/10028 , G06T2207/20081 , G06T2207/20084 , G06T2207/30244 , G06T2207/30252
摘要: A method for multi-camera monocular depth estimation using pose averaging is described. The method includes determining a multi-camera photometric loss associated with a multi-camera rig of an ego vehicle. The method also includes determining a multi-camera pose consistency constraint (PCC) loss associated with the multi-camera rig of the ego vehicle. The method further includes adjusting the multi-camera photometric loss according to the multi-camera PCC loss to form a multi-camera PCC photometric loss. The method also includes training a multi-camera depth estimation model and an ego-motion estimation model according to the multi-camera PCC photometric loss. The method further includes predicting a 360° point cloud of a scene surrounding the ego vehicle according to the trained multi-camera depth estimation model and the ego-motion estimation model.
-
64.
公开(公告)号:US20230252799A1
公开(公告)日:2023-08-10
申请号:US17667876
申请日:2022-02-09
发明人: Naoki Nagasaka , Blake Wulfe , Kuan-Hui Lee , Jia-En Marcus Pan
CPC分类号: G06V20/584 , G06T7/254
摘要: In one embodiment, a signal light state detection system includes one or more processors, an a non-transitory memory module storing computer-readable instructions. The computer-readable instructions are configured to cause the one or more processors to receive a first image of a vehicle and receiving a second image of the vehicle, wherein the second image is later in time from the first image, and generate a warped image from the first image and the second image, wherein the warped image has individual pixels of one of the first image and the second image that are shifted to locations of corresponding pixels of the other of the first image and the second image. The one or more processors further generate a difference image from the warped image and one of the first image and the second image, and determine, using a classifier module, a probability of a state of vehicle signal lights.
-
公开(公告)号:US20230252796A1
公开(公告)日:2023-08-10
申请号:US18077974
申请日:2022-12-08
申请人: TOYOTA RESEARCH INSTITUTE, INC. , THE REGENTS OF LTHE UNIVERSITY OF CALIFORNIA , THE BOARD OF TRUSTEES OF THE UNIVERSITY OF ILLINOIS , CARNEGIE MELLON UNIVERSITY
发明人: Zhipeng BAO , Pavel TOKMAKOV , Adrien David GAIDON , Allan JABRI , Yuxiong WANG , Martial HEBERT
IPC分类号: G06V20/58 , G06T7/215 , G06T7/246 , G06V10/774 , G06V10/77
CPC分类号: G06V20/58 , G06T7/215 , G06T7/246 , G06V10/7753 , G06V10/7715 , G06T2207/10016 , G06T2207/20081 , G06T2207/30252 , G06T2207/20084
摘要: A method of compositional feature representation learning for video understanding is described. The method includes individually processing a sequence of video frames received as an input of a feature map network to generate a plurality of feature maps. The method also includes binding the plurality of feature maps to a fixed set of slot variables using an attention model according to a motion segmentation signal. The method further includes combining slot states corresponding to the fixed set of slot variables into a combined feature map. The method also includes decoding the combined feature map to form a reconstructed sequence of video frames, in which objects discovered in the reconstructed sequence of video frames are identified.
-
公开(公告)号:US20230237339A1
公开(公告)日:2023-07-27
申请号:US17582687
申请日:2022-01-24
CPC分类号: G06N3/088 , G06N3/0481
摘要: A machine learning system includes a processor and a memory communicably coupled to the processor. The memory stores an acquisition module, a mapping module, a machine learning module, a fitting module, and a minimization module that include instructions that when executed by the processor cause the processor to: select a training dataset, map the training dataset from an input space to an output space such that the mapped training dataset is convex; train a machine learning model to learn a convex function that approximates the mapped training dataset in the output space; learn a minimum of the convex function; map the minimum of the convex function to the input space; and predict, based at least in part on the minimum of the convex function mapped to the input space, an optimum material property value and a corresponding material composition.
-
公开(公告)号:US11710324B2
公开(公告)日:2023-07-25
申请号:US16901358
申请日:2020-06-15
CPC分类号: G06V20/56 , G06F18/2178 , G06V10/454 , G06V10/82 , G06V20/20
摘要: Systems, methods, and other embodiments described herein relate to improving the classification of objects depicted in a scene. In one embodiment, a method includes generating, using an ontological detector, a type classification of a detected object according to a detector ontology of known classes. The detected object is represented as segmented data from sensor data about a surrounding environment. The method includes, in response to determining that the type classification specifies an unknown class that is not defined in the detector ontology, annotating the segmented data as unknown. The method includes providing the segmented data to specify that the type classification for the detected object is unknown.
-
公开(公告)号:US20230227070A1
公开(公告)日:2023-07-20
申请号:US17578233
申请日:2022-01-18
发明人: Manuel Ludwig Kuehner , Jaime Camhi
CPC分类号: B60W60/0015 , B60W30/18109 , B60W2510/20 , B60W2552/40
摘要: System and methods are provided for implementing friction circle safety controls in a vehicle, such as an autonomous vehicle. A system can apply a friction circle analysis during the vehicle's operation, in order to perform a safety-based evaluation of maneuvers that impact the dynamic relationship between a vehicle's tires and a road surface. The system also establishes a link between the vehicle's lateral controls (e.g., steering wheel) and the vehicle's longitudinal controls (e.g., brake and throttle pedals), such that a frictional force of the tires against the road's surface, does not does not exceed a traction limit (e.g., limit of a tire's grip on the road surface) for the particular vehicle. For example, friction circle safety controls can automatically provide feedback and/or automatic driving actions to adjust a relationship between the steering wheel and brake/throttle pedals of the vehicle to maintain operation of the vehicle within the friction circle.
-
公开(公告)号:US11688090B2
公开(公告)日:2023-06-27
申请号:US17377161
申请日:2021-07-15
发明人: Vitor Guizilini , Rares Andrei Ambrus , Adrien David Gaidon , Igor Vasiljevic , Gregory Shakhnarovich
IPC分类号: G06T7/55 , G06N3/08 , G06T7/579 , B60R1/00 , G06T3/00 , G05D1/02 , G06T7/292 , G06T7/11 , B60W60/00 , G06T3/40 , G06F18/214 , H04N23/90
CPC分类号: G06T7/55 , B60R1/00 , B60W60/001 , G05D1/0212 , G05D1/0246 , G06F18/214 , G06F18/2148 , G06N3/08 , G06T3/0012 , G06T3/0093 , G06T3/40 , G06T7/11 , G06T7/292 , G06T7/579 , H04N23/90 , B60R2300/102 , B60W2420/42 , G05D2201/0213 , G06T2207/10028 , G06T2207/20081 , G06T2207/20084 , G06T2207/30244 , G06T2207/30252
摘要: A method for multi-camera self-supervised depth evaluation is described. The method includes training a self-supervised depth estimation model and an ego-motion estimation model according to a multi-camera photometric loss associated with a multi-camera rig of an ego vehicle. The method also includes generating a single-scale correction factor according to a depth map of each camera of the multi-camera rig during a time-step. The method further includes predicting a 360° point cloud of a scene surrounding the ego vehicle according to the self-supervised depth estimation model and the ego-motion estimation model. The method also includes scaling the 360° point cloud according to the single-scale correction factor to form an aligned 360° point cloud.
-
公开(公告)号:US20230182755A1
公开(公告)日:2023-06-15
申请号:US17547056
申请日:2021-12-09
CPC分类号: B60W50/12 , B60W30/09 , B60W30/16 , F16D57/002 , G09B19/167 , B60W2540/10 , B60W2554/4041 , B60W2520/10 , B60W2554/4042 , B60W2554/802 , B60W2754/30 , B60W2420/52 , B60W2420/42 , B60W2420/54
摘要: Systems and methods are provided for improved collision prevention. Systems and methods may provide for the prevention of rear-end vehicle collisions by locking the forward movement of the throttle pedal when a threshold is reached. An end stop or mechanical linkage may completely lock the throttle pedal in situations in which continued acceleration is likely to result in a rear-end collision. The systems and methods disclosed herein may provide from a complete locking of the throttle pedal which may physically avoid or eliminate a rear-end collision due to improper throttle actuation. The systems and methods disclosed herein may also improve a driver's mental model for safe driving by teaching a driver that certain maneuvers are not available in certain conditions.
-
-
-
-
-
-
-
-
-