-
公开(公告)号：US12073318B2
公开(公告)日：2024-08-27
申请号：US16937503
申请日：2020-07-23
摘要： Described is an attack system for generating perturbations of input signals in a recurrent neural network (RNN) based target system using a deep reinforcement learning agent to generate the perturbations. The attack system trains a reinforcement learning agent to determine a magnitude of a perturbation with which to attack the RNN based target system. A perturbed input sensor signal having the determined magnitude is generated and presented to the RNN based target system such that the RNN based target system produces an altered output in response to the perturbed input sensor signal. The system identifies a failure mode of the RNN based target system using the altered output.
-
公开(公告)号：US12061673B1
公开(公告)日：2024-08-13
申请号：US17167001
申请日：2021-02-03
发明人： Sean Soleyman , Deepak Khosla
CPC分类号： G06F18/2185 , G06N3/086
摘要： Described is a system for controlling multiple autonomous platforms. A training process is performed to produce a trained learning agent in a simulation environment. In each episode, each controlled platform is assigned to one target platform that produces an observation. A learning agent processes the observation using a deep learning network and produces an action corresponding to each controlled platform until an action has been produced for each controlled platform. A reward value is obtained corresponding to the episode. The trained learning agent is executed to control each autonomous platform, where the trained agent receives one or more observations from one or more platform sensors and produces an action based on the one or more observations. The action is then used to control one or more platform actuators.
-
公开(公告)号：US12034536B2
公开(公告)日：2024-07-09
申请号：US17294665
申请日：2019-11-18
CPC分类号： H04L1/0082 , H04L5/16 , H04L45/20 , H04L47/6225 , H04L49/252 , H04L69/22
摘要： A method of communicating between nodes in a network where a node receives a sequence of symbols that will form a packet on a first communications channel and has a planned packet that it would send on a second communications channel. A destination is encoded into an arbitration portion of a header sequence of the packet, the header sequence comprising a sequence of symbols. The transmission on the second communications channel is as per the planned packet, for as long as the symbols of the planned packet match the symbols being received on the first channel. An arbitration decision is made when the symbols do not match, with the node either continuing to send the rest of the planned packet, or the rest of the packet being received on the first communications channel.
-
公开(公告)号：US12008079B1
公开(公告)日：2024-06-11
申请号：US17368635
申请日：2021-07-06
发明人： Soheil Kolouri , Heiko Hoffmann , David W. Payton
IPC分类号： G06F18/24 , G06F18/21 , G06F18/214 , G06F18/232 , G06F21/56 , G06N3/08 , G06V10/22
CPC分类号： G06F18/24 , G06F18/214 , G06F18/2163 , G06F18/217 , G06F18/232 , G06F21/566 , G06N3/08 , G06V10/22 , G06F2221/034
摘要： Described is a system for object detection that is robust to adversarial attacks. An initial hypothesis of an identity of an object in an input image is generated using a sparse convolutional neural network (CNN) and a distribution aware classifier. A foveated hypothesis verification process is performed for identifying a region of the input image that supports the initial hypothesis. Using a part-based classifier, an identity of a part of the object in the region of the input image is predicted. An attack probability for the predicted identity of the part, and the initial hypothesis is updated based on the predicted identity of the part and the attack probability. The foveated hypothesis verification process and updating of hypotheses is performed until a hypothesis reaches a certainty threshold. The object is labeled based on the hypothesis that reached the certainty threshold.
-
公开(公告)号：US11941870B1
公开(公告)日：2024-03-26
申请号：US17699038
申请日：2022-03-18
发明人： Hyukseong Kwon , Amit Agarwal , Kevin Lee , Amir M. Rahimi , Alexie Pogue , Rajan Bhattacharyya
IPC分类号： G06K9/00 , B60W60/00 , G06V10/72 , G06V10/774 , G06V10/776 , G06V20/40 , G06V20/58 , G06V20/70 , G08G1/16
CPC分类号： G06V10/776 , B60W60/0015 , G06V10/72 , G06V10/774 , G06V20/41 , G06V20/58 , G06V20/70 , G08G1/166 , B60W2420/42 , B60W2710/20
摘要： Described is a system for action recognition error detection and correction using probabilistic signal temporal logic. The system is initiated by training an action recognition system to generate true positive (TP)/false positive (FP) axioms. Thereafter, the system ca be used to classify one or more actions in a video sequence as true action classifications by using the TP/FP axioms to remove false action classifications. With the remaining true classifications, a device can be controlled given the situation and relevant true classification.
-
公开(公告)号：US11928585B2
公开(公告)日：2024-03-12
申请号：US16950803
申请日：2020-11-17
CPC分类号： G06N3/08 , G05D1/0221 , G05D1/0276 , B60W60/001 , B60W2556/45 , G06F7/544
摘要： Described is a system for training a neural network for estimating surface normals for use in operating an autonomous platform. The system uses a parallelizable k-nearest neighbor sorting algorithm to provide a patch of points, sampled from the point cloud data, as input to the neural network model. The points are transformed from Euclidean coordinates in a Euclidean space to spherical coordinates. A polar angle of a surface normal of the point cloud data is estimated in the spherical coordinates. The trained neural network model is utilized on the autonomous platform, and the estimate of the polar angle of the surface normal is used to guide operation of the autonomous platform within the environment.
-
公开(公告)号：US11899839B1
公开(公告)日：2024-02-13
申请号：US17965566
申请日：2022-10-13
发明人： Steven W. Skorheim , Tiffany Hwu
摘要： Described is a system for multimodal machine-aided comprehension analysis. The system can be implemented in an augmented reality headset that, in conjunction with a processor, generates an initial scene graph of a scene proximate the user. Items and labels are presented, with the headset tracking eye movements of the user as the user gazes upon the subject labels, item labels, and relationship labels. A resulting scene graph (having relationship triplets) is generated based on the eye movements of the user and an amount of time the user spends gazing upon each of the display components. A comprehension model is generated by estimating a user's comprehension of the relationship triplets, with a knowledge model being generated based on a known knowledge graph and the comprehension model. Cues are then presented to the user based on the comprehension and knowledge models to assist the user in their comprehension of the scene.
-
公开(公告)号：US11854252B1
公开(公告)日：2023-12-26
申请号：US17700802
申请日：2022-03-22
发明人： Hyukseong Kwon , Amit Agarwal , Amir M. Rahimi , Kevin Lee , Alexie Pogue , Rajan Bhattacharyya
IPC分类号： G06K9/62 , G06V10/98 , G06V20/56 , G06V10/762 , G06V10/764 , G06V10/10
CPC分类号： G06V10/993 , G06V10/10 , G06V10/763 , G06V10/764 , G06V20/56
摘要： Described is a system for evaluating and correcting perception errors in object detection and recognition. The system receives perception data from an environment proximate a mobile platform. Perception probes are generated from the perception data which describe perception characteristics of object detections in the perception data. For each perception probe, probabilistic distributions for true positive and false positive values are determined, resulting in true positive and false negative perception probes. Statistical characteristics of true positive perception probes and false positive perception probes are then determined. Based on the statistical characteristics, true positive perception probes are clustered. An axiom is generated to determine statistical constraints for perception validity for each perception probe cluster. The axiom is evaluated to classify the perception probes as valid or erroneous. Optimal perception parameters are generated by solving an optimization problem based on the axiom. The perception module is adjusted based on the optimal perception parameters.
-
公开(公告)号：USD998725S1
公开(公告)日：2023-09-12
申请号：US29690971
申请日：2019-05-13
申请人： JAKKS Pacific, Inc.
摘要： FIG. 1 is an elevated, exploded-view illustration of the doll eye assembly; and
FIG. 2 is an elevated-view illustration of the doll eye assembly.
The broken line showing of the Doll Eye Assembly are for the purpose of illustrating portions of the article that form no part of the claimed design.-
10.发明授权公开(公告)号：US11694120B2
公开(公告)日：2023-07-04
申请号：US17190346
申请日：2021-03-02
摘要： Described is a system for detecting and correcting perception errors in a perception system. In operation, the system generates a list of detected objects from perception data of a scene, which allows for the generation of a list of background classes from backgrounds in the perception data associated with the list of detected objects. For each detected object in the list of detected objects, a closest background class is identified from the list of background classes. Vectors can then be used to determine a semantic feature, which is used to identify axioms. An optimal perception parameter is then generated, which is used to adjust perception parameters in the perception system to minimize perception errors.
-
-
-
-
-
-
-
-
-
搜索结果
697 条记录 (耗时 0.024 秒)
