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

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.

2. 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.

3. 发明公开

EP4279869A1 DETERMINING A STATE OF A VEHICLE ON A ROAD 审中-公开
公开(公告)号：EP4279869A1
公开(公告)日：2023-11-22
申请号：EP22173553.3
申请日：2022-05-16
申请人： Zenseact AB
发明人： BEAUVISAGE, Axel , FU, Junsheng , STENHAMMAR, Theodor , BEJMER, David
IPC分类号： G01C21/30 , G01C21/16 , G06V20/56
摘要： The present disclosure relates to a method, system, a vehicle and a computer-readable storage medium for determining a state of a vehicle on a road portion having two or more lanes. The vehicle comprises an Automated Driving System (ADS) feature. The method comprises obtaining map data associated with the road portion and obtaining positioning data indicating a pose of the vehicle on the road and obtaining sensor data from a sensor system of the vehicle. Further, the method comprises initializing a plurality of filters for the road portion wherein one filter is initialized per lane of the road portion. The method further comprises associating one or more sensor data point(s) in the obtained sensor data to a corresponding map-element of the obtained map data and determining one or more normalized similarity score(s) between the associated obtained map data and the obtained sensor data. Even further the method comprises determining one or more multivariate time-series data based on the determined one or more normalized similarity score(s), wherein each multivariate time-series data is attributed to a corresponding initialized filter among the plurality of initialized filters. Further the method comprises providing the one or more multivariate time-series data as input to a trained machine-learning algorithm and selecting one of the initialized filters by means of the machine learning algorithm.

4. 发明公开

EP4279350A1 LANE KEEPING BASED ON LANE POSITION UNAWARENESS 审中-公开
公开(公告)号：EP4279350A1
公开(公告)日：2023-11-22
申请号：EP22173583.0
申请日：2022-05-16
申请人： Zenseact AB
发明人： OLSSON, Claes , LOVISARI, Enrico
IPC分类号： B60W30/12 , B60W30/182 , B60W30/095 , B60W50/14 , B60W10/20
摘要： A computer-implemented method and a device for controlling a lane support system of a vehicle are disclosed. The method comprises obtaining data indicative of a driver of the vehicle being in an inattentive state, and determining an intended path of the driver at a point in time when the driver enters the inattentive state. The method further comprise determining an unintended lateral deviation from the intended path by computing a function representative of a lateral deviation from the intended path of the driver. Moreover, the function is dependent upon at least one of a change in steering wheel angle while the driver is in the inattentive state, and a change in road geometry along the vehicle's traveling direction while the driver is in the inattentive state. The method further comprises activating the lane support system when the determined unintended lateral deviation violates a threshold value, wherein the lane support system is configured to output a warning to the driver and/or to execute an intervention so to control a steering of the vehicle upon detection of a lane departure of the vehicle.

5. 发明公开

EP4242989A1 DYNAMIC ADJUSTMENT OF AN EVENT SEGMENT LENGTH OF A VEHICLE EVENT RECORDING BUFFER 审中-实审
公开(公告)号：EP4242989A1
公开(公告)日：2023-09-13
申请号：EP22161065.2
申请日：2022-03-09
申请人： Zenseact AB
发明人： GYLLENHAMMAR, Magnus , VAKILZADEH, Majid Khorsand
IPC分类号： G07C5/08
摘要： The present disclosure relates to a method performed by a buffer segment length adjusting system (1) for dynamically adjusting an event segment length of data stored in an event recording buffer (3) of an Automated Driving System, ADS (21), of a vehicle (2). The buffer segment length adjusting system obtains (1001) sensor data of one or more sensors (22) onboard the vehicle. The buffer segment length adjusting system further identifies (1002), upon the sensor data rendering fulfilment - and/or a state of a software of the ADS rendering fulfilment - of event recording triggering criteria, conditions of a triggering event underlying the fulfilment. Moreover, the buffer segment length adjusting system determines (1003) at least a first current ADS-related operational condition. Furthermore, the buffer segment length adjusting system sets (1005) a respective start time point and end time point of - e.g. an event segment length of - said event recording buffer based on the triggering event conditions and the at least first current ADS-related operational condition.
The disclosure also relates to a buffer segment length adjusting system in accordance with the foregoing, a vehicle comprising such a buffer segment length adjusting system, and a respective corresponding computer program product and non-volatile computer readable storage medium.

6. 发明公开

EP4206606A1 HYPOTHESIS INFERENCE FOR VEHICLES 审中-实审
公开(公告)号：EP4206606A1
公开(公告)日：2023-07-05
申请号：EP21218005.3
申请日：2021-12-28
申请人： Zenseact AB
发明人： FU, Junsheng , BEAUVISAGE, Axel
IPC分类号： G01C21/00 , B60W60/00 , G01C21/16 , G01C21/30 , G01C21/36 , G05D1/00 , G05D1/02 , G06N20/00 , G06V20/56
摘要： The present disclosure relates to a method, system, a vehicle and a computer-readable storage medium for determining a state of a vehicle on a road portion having two or more lanes. The vehicle comprises an Automated Driving System, ADS, feature. The method comprises obtaining map data associated with the road portion and further obtaining positioning data indicating a position of the vehicle on the road and obtaining sensor data from a sensor system of the vehicle. The method further comprises initializing a filter per lane of the road portion based on the obtained map data, the obtained positioning data, and the obtained sensor data, wherein each filter indicates an estimated state of the vehicle on the road portion. Further, the method comprises selecting one of the initialized filters by means of a trained machine-learning algorithm configured to use the obtained map data, the obtained positioning data, the obtained sensor data, and each estimated state as indicated by each filter as input and to output a single selected initialized filter indicative of a current state of the vehicle on the road portion. In various aspects and embodiments the method further comprises controlling the ADS feature of the vehicle based on the selected initialized filter.

7. 发明公开

EP4148607A1 ADS FEATURE VERIFICATION 审中-实审
公开(公告)号：EP4148607A1
公开(公告)日：2023-03-15
申请号：EP21196364.0
申请日：2021-09-13
申请人： Zenseact AB
发明人： LUVÖ, Thomas
IPC分类号： G06F21/64
摘要： The present disclosure relates to a method performed by a distributed verification system (1) for supporting verification of ADS features within specific ODDs. The distributed verification system identifies (1001) at one or more ADS-equipped vehicles (2) connected via a peer-to-peer blockchain network (3), a respective at least first verification instruction (4) pertinent an at least first specified ODD of a specified ADS feature; collects (1002) at at least a first vehicle (20) of the one or more vehicles, verification data from execution by the at least first vehicle of the at least first ADS verification instruction while the specified ADS feature is active within and/or in association with the at least first specified ODD; generates (1003) at the at least first vehicle, a verification result transaction (5) to be added to a distributed ledger of the network, which verification result transaction comprises verification information derived from the verification data along with information of circumstances and/or configuration of the at least first vehicle associated with the verification data; and when consensus of the verification result transaction is reached on the network, adds (1004) the verification result transaction to the distributed ledger.
The disclosure also relates to a distributed verification system in accordance with the foregoing, at least a first node ― for instance a network-connected ADS-equipped vehicle and/or a network-connected simulation node (6) ― comprising such a distributed verification system, and a respective corresponding computer program product and nonvolatile computer readable storage medium.

8. 发明公开

EP4063222A1 PRECAUTIONARY VEHICLE PATH PLANNING 审中-公开
公开(公告)号：EP4063222A1
公开(公告)日：2022-09-28
申请号：EP21164687.2
申请日：2021-03-24
申请人： Zenseact AB
发明人： Fei, Zhennan , Rodrigues de Campos, Gabriel
IPC分类号： B60W60/00 , B60W50/00 , B60W50/14 , B60W40/02
摘要： The present disclosure relates to a method performed by a path-adapting system (1) for precautionary path planning of a host vehicle (2). The path-adapting system determines (1001) conditions of a liquid and/or solid loose material in the air and/or on the road surface in vicinity of the host vehicle based on collected input data. The path-adapting system further determines (1002) movement attributes in relation to the host vehicle, of at least a first object (3) in host vehicle surroundings captured with support from one or more surrounding detecting sensors (23) onboard the host vehicle. Moreover, the path-adapting system determines (1003) based on said conditions and said movement attributes, at least a first estimated upcoming host vehicle position (4) occurring at an estimated upcoming at least first time instance (Te) at which the at least first detected object is estimated to direct said material onto the host vehicle and/or the host vehicle is estimated to direct said material onto the at least first detected object. Furthermore, the path-adapting system determines (1005) a driving path (6) intended for the host vehicle, altering for the at least first time instance the at least first estimated upcoming host vehicle position to a modified host vehicle position (7) mitigating said estimated directing of the material.
The disclosure also relates to a path-adapting system in accordance with the foregoing, a vehicle comprising such a path-adapting system, and a respective corresponding computer program product and non-volatile computer readable storage medium.

9. 发明公开

EP3995341A1 TRANSITIONING OF VEHICLE SPEED CONTROL FROM AN ADAS OR AD SYSTEM TO A DRIVER 审中-公开
公开(公告)号：EP3995341A1
公开(公告)日：2022-05-11
申请号：EP20206436.6
申请日：2020-11-09
申请人： Zenseact AB
发明人： FU, Junsheng , XU, Sheng
IPC分类号： B60K37/06
摘要： The present disclosure relates to a method performed by a deviation assessment system (1) of a vehicle (2) for supporting transitioning of speed control from an ADAS or AD system (21) of the vehicle, to a vehicle driver. The deviation assessment system derives (1001) a current system-initiated value of a speed-affecting system parameter pertinent speed control by the ADAS or AD system. The deviation assessment system further derives (1002) a value of a corresponding speed-affecting intervention parameter pertinent a driver-initiated speed-affecting intervention of the speed control. Moreover, the deviation assessment system presents (1003) on a vehicle display (23) a graphical representation (4) indicative of a discrepancy between the system-initiated value and the driver-initiated value.
The disclosure also relates to a deviation assessment system in accordance with the foregoing, a vehicle comprising such a deviation assessment system, and a respective corresponding computer program product and non-volatile computer readable storage medium.

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