专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明公开

EP4431974A1 GENERATING REPRESENTATION OF A SURROUNDING ENVIRONMENT OF A VEHICLE 审中-公开
公开(公告)号：EP4431974A1
公开(公告)日：2024-09-18
申请号：EP23162030.3
申请日：2023-03-15
申请人： Zenseact AB
发明人： JOHNANDER, Joakim , PETERSSON, Christoffer , TONDERSKI, Adam
IPC分类号： G01S7/41 , G01S13/42 , G01S13/86 , G01S13/931 , G01S17/42 , G01S17/86 , G01S17/931
CPC分类号： G01S7/417 , G01S13/86 , G01S13/865 , G01S13/867 , G01S13/931 , G01S13/42 , G01S17/86 , G01S17/42 , G01S17/931
摘要： The present disclosure relates to a method, system, a vehicle, a computer-readable storage medium, and a computer program product. The method comprises obtaining sensor data from a plurality of vehicle-mounted sensor devices, the sensor data of each sensor device comprising one or more sensor data points corresponding to at least one sensor-specific measurement performed by that sensor device at a respective operating frequency. The method further comprises providing the obtained sensor data as input data to a neural network algorithm at a runtime of the neural network algorithm. The method further comprises encoding each sensor data point to a corresponding encoded sensor data point and assigning a header timestamp to each encoded sensor data point. The method further comprises generating one or more prediction outputs representative of the surrounding environment of the vehicle.

2. 发明公开

EP4389551A1 A COMPUTER-IMPLEMENTED METHOD FOR MANAGING AN OPERATIONAL DESIGN DOMAIN S EXPANSION FOR AN AUTOMATED DRIVING SYSTEM 审中-公开
公开(公告)号：EP4389551A1
公开(公告)日：2024-06-26
申请号：EP22215738.0
申请日：2022-12-22
申请人： Zenseact AB
发明人： KROOK, Jonas , FEI, Zhennan
IPC分类号： B60W60/00 , H04W4/44
CPC分类号： B60W60/00 , B60W60/0018 , H04W4/44 , B60W60/0053
摘要： The present invention is related to a computer-implemented method (100) for managing an Operational Design Domain (ODD) expansion for an Automated Driving System (ADS) of a vehicle. The method (100) comprises: obtaining (S102) a plurality of scenario parameters defining the environment of the vehicle, wherein each scenario parameter corresponds to a respective condition of the ODD; in response to the plurality of scenario parameters fulfilling the plurality of ODD conditions: allowing (S104) the ADS to be activated or to remain active; in response to one or more scenario parameter(s) not fulfilling one or more ODD condition(s): querying (S106) a logic formula based on the obtained plurality of scenario parameters, such that if at least one soft constraint of the logical formula is satisfied without violating any hard constraints of the logical formula, the ADS fulfils a plurality of predefined safety requirements; determining (S108), based on the logic formula and the obtained plurality of scenario parameters, a set of values of one or more variable state parameters which satisfies at least one soft constraint without violating any hard constraints; and allowing (S112) the ADS to be activated in a degraded mode or to switch to a degraded mode by limiting one or more variable state parameters of the ADS to conform to the determined set of values of the one or more variable state parameters.

3. 发明公开

EP4361967A1 SITUATION SPECIFIC PERCEPTION CAPABILITY FOR AUTONOMOUS AND SEMI-AUTONOMOUS VEHICLES 审中-公开
公开(公告)号：EP4361967A1
公开(公告)日：2024-05-01
申请号：EP22204464.6
申请日：2022-10-28
申请人： Zenseact AB
发明人： GYLLENHAMMAR, Magnus , ZANDÉN, Carl , KHORSAND VAKILZADEH, Majid
IPC分类号： G06V20/58 , G06F18/20
CPC分类号： G06V20/58 , G06F18/285
摘要： A computer-implemented method and related aspects for providing environment perception for a vehicle having an Automated Driving System (ADS) are disclosed. The ADS comprises a generalized perception network and a plurality of specific perception networks, where each specific perception network comprises a specifically trained machine-learning algorithm that is trained with data associated with a specific traffic situation such that each specifically trained machine-learning algorithm is trained for a different traffic situation as compared to the other specifically trained machine-learning algorithms of the plurality of specific perception networks. The method comprises obtaining sensor data from one or more vehicle-mounted sensors. The obtained sensor data comprises information about a surrounding environment of the vehicle. The method further comprises selecting one or more specific perception networks for activation out of the plurality of specific perception networks based on a current traffic situation indicated in the obtained sensor data. Furthermore, the method comprises feeding at least a portion of the obtained sensor data to each of the selected one or more specific perception networks and to the generalized perception network in order to obtain an output from each of the selected one or more specific perception networks and the generalized perception network. The method further comprises fusing the obtained outputs from each of the selected one or more specific perception networks and the generalized perception network, wherein the fused output comprises one or more perception output in relation to the surrounding environment of the vehicle. Further, the method comprises transmit the fused output to a module of the ADS.

4. 发明公开

EP4357213A1 A METHOD FOR DETERMINING WHETHER AN AUTOMATIC COLLISION AVOIDANCE STEERING MANEUVER SHOULD BE EXECUTED OR NOT 审中-公开
公开(公告)号：EP4357213A1
公开(公告)日：2024-04-24
申请号：EP22201807.9
申请日：2022-10-17
申请人： Zenseact AB
发明人： GIORDANO, Giuseppe , JOHANNESSON MÅRDH, Lars
IPC分类号： B60W30/09 , B60W30/095 , B60W10/20 , B60W10/184
CPC分类号： B60W30/09 , B60W30/0953 , B60W2720/12520130101 , B60T2230/0420130101 , B60W10/20 , B60W10/184
摘要： The present invention relates to a computer-implemented method (100) for determining whether an automatic collision avoidance steering maneuver for a vehicle equipped with an automated driving system, ADS, should be executed or not. The method (100) comprising: obtaining (S102) a predicted vehicle trajectory for execution of the collision avoidance steering maneuver, wherein the predicted vehicle trajectory comprises a predicted lateral acceleration and a predicted lateral jerk of the vehicle along the predicted vehicle trajectory; obtaining (S106) a first threshold of attainable lateral acceleration and a second threshold of attainable lateral jerk of the vehicle; determining (S108) whether the predicted vehicle trajectory is attainable or not by comparing the predicted lateral acceleration with the first threshold and the predicted lateral jerk with the second threshold; in response to the predicted vehicle trajectory being attainable, communicating (S110), to a control system of the vehicle, that the automatic collision avoidance steering maneuver shall be executed; in response to the predicted vehicle trajectory not being attainable: determining (S112) a lateral offset of the vehicle along the predicted vehicle trajectory based on the predicted lateral acceleration and the predicted lateral jerk of the predicted vehicle trajectory and the first and second threshold; in response to the lateral offset being smaller than or equal to a third threshold, communicating (S114), to the control system of the vehicle, that the automatic collision avoidance steering maneuver shall be executed; in response to the lateral offset being greater than the third threshold, communicating (S116) to the control system of the vehicle, that the automatic collision avoidance steering maneuver shall not be executed. The present invention further relates to a device and vehicle thereof.

5. 发明授权

EP4083871B1 METHOD FOR AUTOMATED DEVELOPMENT OF A PATH PLANNING MODULE FOR AN AUTOMATED DRIVING SYSTEM 有权
公开(公告)号：EP4083871B1
公开(公告)日：2023-11-15
申请号：EP21171222.9
申请日：2021-04-29
发明人： GYLLENHAMMAR, Magnus , ZANDÉN, Carl , KHORSAND VAKILZADEH, Majid
IPC分类号： G06N3/08 , G01M17/00 , B60W60/00 , B60W50/00

6. 发明授权

EP4219261B1 ESTIMATION OF RISK EXPOSURE FOR AUTONOMOUS VEHICLES 有权
公开(公告)号：EP4219261B1
公开(公告)日：2024-09-18
申请号：EP22154072.7
申请日：2022-01-28
IPC分类号： B60W60/00 , G06F30/27
CPC分类号： G06F8/20 , B60W2556/2020200201 , B60W60/0015

7. 发明公开

EP4394705A1 A METHOD AND DEVICE FOR CALIBRATING A CAMERA MOUNTED ON A VEHICLE 审中-公开
公开(公告)号：EP4394705A1
公开(公告)日：2024-07-03
申请号：EP22216952.6
申请日：2022-12-28
申请人： Zenseact AB
发明人： STENBORG, Erik , KJELLSON-FREIJ, Harald , TINGDAHL, David , SAMUELSSON, David
IPC分类号： G06T7/80
CPC分类号： G06T2207/3025220130101 , G06T2207/1001620130101 , G06T7/80 , G06T2207/3024420130101 , G06T2207/1002820130101
摘要： The present invention is related to a computer-implemented method (100) for calibrating a set of extrinsic parameters of a camera mounted on a vehicle. The method (100) comprises: obtaining (S102) a sequence of images, captured by the camera, wherein each image of the sequence of images depicts a portion of a surrounding environment of the vehicle in a respective time instance of a plurality of time instances; determining (S104) a set of feature points in the sequence of images; determining (S106) an area representing a sky in the sequence of images; removing (S114), from the set of feature points, a subset of feature points, the subset of feature points belonging to the area representing the sky, thereby forming an updated set of feature points; determining (S118) a first motion trajectory of the vehicle over the plurality of time instances, based on the updated set of feature points; obtaining (S120) a second motion trajectory of the vehicle over the plurality of time instances, wherein the second motion trajectory is based on motion data obtained from one or more other sensors of the vehicle; and calibrating (S122) the camera by adjusting the set of extrinsic parameters of the camera based on a difference between the first motion trajectory and the second motion trajectory.

8. 发明公开

EP4394667A1 TARGETED DATA GENERATION BY NEURAL NETWORK ENSEMBLES 审中-公开
公开(公告)号：EP4394667A1
公开(公告)日：2024-07-03
申请号：EP22216937.7
申请日：2022-12-28
申请人： Zenseact AB
发明人： VERBEKE, Willem , LJUNGBERGH, William
IPC分类号： G06N20/20
CPC分类号： G06N20/20 , G06N3/09 , G06N3/045 , G06N3/098 , G06N3/0985 , G06N3/096 , G06N3/094 , G06N3/091 , B60W60/00
摘要： The present disclosure relates to methods, systems, a vehicle and a computer-readable storage medium and a computer program product. The method comprises obtaining a trained ensemble of machine learning, ML, algorithms, comprising a plurality of ML algorithms that are trained at least partly based on a first set of training data. The method further comprises forming an input data set for the trained ensemble of ML algorithms. The method further comprises providing the formed input data set to the trained ensemble of ML algorithms for generating, for each of the one or more input data samples, an ensemble prediction output. In response to a determined discrepancy in the ensemble prediction output for a particular input data sample, the method further comprises forming a second training data set based on that particular input data sample.

9. 发明公开

EP4383216A1 METHODS AND APPARATUSES FOR ADAPTIVE HIGH BEAM CONTROL FOR A VEHICLE 审中-公开
公开(公告)号：EP4383216A1
公开(公告)日：2024-06-12
申请号：EP22212034.7
申请日：2022-12-07
申请人： Zenseact AB
发明人： FU, Junsheng , EKMARK, Jonas
IPC分类号： G06V20/58 , B60Q1/14 , G06V20/56
CPC分类号： G06V20/588 , G06V20/584 , B60Q1/143 , B60Q2300/05620130101 , B60Q2300/4220130101
摘要： A computer-implemented method and related aspects for adaptive high beam control for a vehicle are disclosed. The method comprises obtaining a pose of the vehicle, the pose being indicative of the vehicle's position and orientation on a road. The method further comprises obtaining a Three-Dimensional (3D) road model of a surrounding environment of the vehicle based on High-Definition (HD) map data and the determined vehicle pose. Furthermore, the method comprises generating a 3D region of interest (3D-ROI) in the form of voxels defining a volume along the obtained 3D road model. The method further comprises forming a dataset for processing by an Adaptive High Beam Control (AHBC) unit configured to adaptively control an illumination of a space in front of the vehicle by controlling an illumination of one or more headlights of the vehicle. The formed dataset is based on the generated 3D-ROI and perception data indicative of one or more detected road users in the surrounding environment of the vehicle. The perception data is based on sensor data obtained from one or more sensors for monitoring a surrounding environment of the vehicle. Furthermore, the method comprises transmitting the formed dataset to the AHBC unit so to control the illumination of the space in front of the vehicle based on the formed dataset so to avoid casting high beam illumination towards road users detected within the 3D-ROI.

10. 发明公开

EP4372584A1 A METHOD FOR PERFORMING A PERCEPTION TASK OF AN ELECTRONIC DEVICE OR A VEHICLE USING A PLURALITY OF NEURAL NETWORKS 审中-公开
公开(公告)号：EP4372584A1
公开(公告)日：2024-05-22
申请号：EP22208125.9
申请日：2022-11-17
申请人： Zenseact AB
发明人： TONDERSKI, Adam , JOHNANDER, Joakim , PETERSSON, Christoffer
IPC分类号： G06F18/25 , G06V10/96 , G06V20/52 , G06V20/56 , G06F18/243
CPC分类号： G06V10/96 , G06F18/254 , G06V20/56 , G06V20/52 , G06F18/24317
摘要： The present invention related to a computer-implemented method (200) for performing a perception task of an electronic device or a vehicle, using a plurality of neural networks trained to generate a perception output based on an input image, wherein at least two neural networks of the plurality of neural networks are different from each other. The computer-implemented method (200) comprises: for a time instance of a plurality of consecutive time instances: obtaining (S202) an image depicting at least a portion of a surrounding environment of the electronic device or the vehicle at the time instance; processing (S204) the image associated with the time instance by means of a subset of neural network(s) of the plurality of neural networks, thereby obtaining a network output for the time instance; and determining (S206) an aggregated network output by combining (S208) the obtained network output for the time instance with network outputs obtained for a number of preceding time instances, wherein the obtained network output for the time instance and the network outputs obtained for the number of preceding time instances are obtained from different subsets of neural networks of the plurality of neural networks.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式