-
公开(公告)号:US20210150899A1
公开(公告)日:2021-05-20
申请号:US16689255
申请日:2019-11-20
发明人: Jianyu Su , Kyungtae Han , Rui Guo , Roger D. Melen
IPC分类号: G08G1/0967 , G06N3/04 , B60W30/12 , B60W30/16
摘要: Systems and methods for providing driving recommendations are disclosed herein. One embodiment receives, at an ego vehicle, first vehicle data and first encoded information from one or more other vehicles; constructs, from the first vehicle data, graph data representing how the ego vehicle and the one or more other vehicles are spatially related; inputs the graph data, the first vehicle data, second vehicle data pertaining to the ego vehicle, and the first encoded information to a graph convolutional network that outputs second encoded information; inputs the second encoded information and previously stored encoded information to a recurrent neural network that outputs a set of parameters to a mixture model; predicts acceleration of the one or more other vehicles using the mixture model; and generates a driving recommendation for the ego vehicle based, at least in part, on the predicted acceleration of the one or more other vehicles.
-
42.
公开(公告)号:US20210049404A1
公开(公告)日:2021-02-18
申请号:US16542715
申请日:2019-08-16
发明人: Rui Guo , Hongsheng Lu , Prashant Tiwari
摘要: An embodiment of the present disclosure takes the form of a method carried out by a perception-network device. The perception-network device provides a first perspective view of a scene to a first branch of a neural network, and generates a feature map via the first branch based on the first perspective view. The perception-network device augments the generated feature map with features of a complementary feature map generated by a second branch of the neural network provided with a second perspective view of the scene. The perception-network device generates a perception inference via the neural network based on the augmented feature map.
-
公开(公告)号:US11935254B2
公开(公告)日:2024-03-19
申请号:US17342853
申请日:2021-06-09
发明人: Rui Guo , Xuewei Qi , Kentaro Oguchi , Kareem Metwaly
CPC分类号: G06T7/50 , G06N3/045 , G06T7/70 , G06T2207/10028 , G06T2207/20081 , G06T2207/20084
摘要: System, methods, and other embodiments described herein relate to improving depth prediction for objects within a low-light image using a style model. In one embodiment, a method includes encoding, by a style model, an input image to identify content information. The method also includes decoding, by the style model, the content information into an albedo component and a shading component. The method also includes generating, by the style model, a synthetic image using the albedo component and the shading component. The method also includes providing the synthetic image to a depth model.
-
公开(公告)号:US11709258B2
公开(公告)日:2023-07-25
申请号:US16937523
申请日:2020-07-23
发明人: Rui Guo , Mahmoud Ashour , Ahmed Sakr , Bin Cheng , Hongsheng Lu , Prashant Tiwari
CPC分类号: G01S13/931 , B60W50/00 , G01S19/01 , G05D1/0276 , G05D1/0287 , H04W4/025 , H04W4/46 , B60W2050/0083 , G05D2201/0213 , H04W84/18
摘要: The disclosure includes embodiments for a location data correction service for connected vehicles. A method includes receiving, by an operation center via a serverless ad-hoc vehicular network, a first wireless message that includes legacy location data that describes a geographic location of a legacy vehicle. The method includes causing a rich sensor set included in the operation center to record sensor data describing the geographic locations of objects in a roadway environment. The method includes determining correction data that describes a variance between the geographic location of the legacy vehicle as described by the sensor data and the legacy location data. The method includes transmitting a second wireless message to the legacy vehicle, wherein the second wireless message includes the correction data so that the legacy vehicle receives a benefit by correcting the legacy location data to minimize the variance.
-
公开(公告)号:US20230230471A1
公开(公告)日:2023-07-20
申请号:US17576082
申请日:2022-01-14
发明人: MEHMET ALI GUNEY , Rui Guo , Prashant Tiwari
IPC分类号: G08G1/01 , G08G1/0965 , B60W60/00
CPC分类号: G08G1/012 , G08G1/0141 , G08G1/0965 , B60W60/001 , G06V20/58
摘要: Systems and methods are provided to implement cooperative traffic congestion detection, and enhance the accuracy of detection of traffic congestion for enhanced routing and maneuvering vehicles along a travel route. A vehicle is configured to receive vehicle data from an ad-hoc network of a plurality of vehicles that are communicatively connected (and proximately located). A subset of the plurality of vehicles can be sensor-rich vehicles that are equipped with ranging sensors (e.g., cameras, LIDAR, radar, ultrasonic sensors), which enables real-time detection of the multiple traffic parameters, such as the presence of other vehicles, vehicle speed, vehicle movement, traffic, and the like, within the vicinity along the route. The vehicle employs cooperative traffic congestion detection, and fuses data from the plurality of vehicles, including sensor-rich vehicles and legacy vehicles, and applies a learning-based algorithm, such as a machine-learning (ML) algorithm, to generate a real-time and more accurate estimate of traffic congestion.
-
公开(公告)号:US20230110132A1
公开(公告)日:2023-04-13
申请号:US17498201
申请日:2021-10-11
发明人: Hansi Liu , Hongsheng Lu , Rui Guo
摘要: A method of matching objects in collaborative perception messages is provided. The method includes obtaining a first collaborative perception message (CPM) message from a first node, obtaining a second CPM from a second node, calculating an adaptive threshold based on uncertainty of the first CPM and uncertainty of the second CPM, calculating scores for pairs of objects, each of the pairs of objects including one object in the first CPM and one object in the second CPM, filtering out one or more pairs whose score is greater than the adaptive threshold to obtain a filtered matrix; and implementing a fusion algorithm on the filtered matrix to obtain correspondence identification among objects.
-
47.
公开(公告)号:US11485377B2
公开(公告)日:2022-11-01
申请号:US16784084
申请日:2020-02-06
发明人: Hongsheng Lu , Rui Guo
IPC分类号: B60W50/04 , B60R16/023 , B60W10/18 , B60W10/20 , G07C5/00 , H04W4/40 , B60W50/08 , B60W50/00
摘要: The disclosure includes embodiments for vehicular cooperative perception for identifying a subset of connected vehicles from a plurality to aid a pedestrian. In some embodiments, a method includes analyzing pedestrian data to determine a scenario depicted by the pedestrian data and a subset of the connected vehicles from the plurality that have a clearest line of the pedestrian. The method includes identifying a group of conflicted vehicles from the subset whose driving paths conflict with a walking path of the pedestrian. The method includes determining, based on the scenario, digital twin data describing a digital twin simulation that corresponds to the scenario. The method includes determining, based on the digital twin data and the pedestrian data, a group of modified driving paths for the group of conflicted vehicles. The method includes causing the group of conflicted vehicles to travel in accordance with the group of modified driving paths.
-
公开(公告)号:US20220038872A1
公开(公告)日:2022-02-03
申请号:US16943421
申请日:2020-07-30
发明人: Hongsheng Lu , Rui Guo
摘要: The disclosure includes embodiments for adaptive sensor data sharing by a connected vehicle. A method includes calculating, by a processor of an ego vehicle, a view angle overlap between a first sensor of the ego vehicle and a second sensor of a roadway device, wherein the view angle overlap is an amount of sensor view overlap shared by first sensor and the second sensor. The method includes determining an amount of ego sensor data to share with the roadway device based on the view angle overlap. The method includes building a sharing message that includes the amount of ego sensor data in a payload of the sharing message. The method includes transmitting, by a communication unit of the ego vehicle, the sharing message to the roadway device.
-
公开(公告)号:US20220036098A1
公开(公告)日:2022-02-03
申请号:US16944891
申请日:2020-07-31
发明人: Bin Cheng , Hongsheng Lu , Rui Guo
摘要: Two vehicles—an ego vehicle and an other vehicle—can share sensor data in a streamlined manner. One or more sensors can be configured to acquire first environment data of an external environment of the ego vehicle. A data summary based on second environment data of an external environment of the other vehicle can be received. Whether there is a common region of sensor coverage between the ego vehicle and the other vehicle can be determined. In response to there being a common region, the first environment data that is located within the common region can be identified and the resolution level of the identified first environment data can be reduced. The first environment data that has the reduced resolution level and a remainder of the first environment data excluding the identified first environment data can be transmitted to the other vehicle.
-
公开(公告)号:US11240707B2
公开(公告)日:2022-02-01
申请号:US16886553
申请日:2020-05-28
发明人: Rui Guo , Hongsheng Lu
摘要: The disclosure includes embodiments for providing adaptive vehicle ID generation. A method includes determining a set of channel loads for a V2X network. The method includes analyzing the set of channel loads to determine if a threshold is satisfied by broadcasting a V2X message including a standard vehicle identifier. Satisfying the threshold is indicative of a channel congestion. The method includes activating a digital switching decision that switches the connected vehicle from broadcasting the standard vehicle identifier to broadcasting a compressed vehicle identifier. The method includes inputting vehicle feature data describing the connected vehicle to a compression module. The compression module analyzes the vehicle feature data and outputs compressed vehicle identifier data describing the compressed vehicle identifier so that the compressed vehicle identifier is determined independently of the standard vehicle identifier. The method includes broadcasting a V2X message including the compressed vehicle identifier data which identifies the connected vehicle.
-
-
-
-
-
-
-
-
-