-
1.发明公开公开(公告)号：US20240338037A1
公开(公告)日：2024-10-10
申请号：US18749205
申请日：2024-06-20
申请人： Kubota Corporation
发明人： Shunsuke MIYASHITA , Yusuke MURATA
IPC分类号： G05D1/646 , G05D1/224 , G05D1/246 , G05D1/248 , G05D1/622 , G05D1/644 , G05D105/15 , G05D107/20 , G05D111/10
CPC分类号： G05D1/646 , G05D1/2246 , G05D1/246 , G05D1/248 , G05D1/622 , G05D1/644 , G05D2105/15 , G05D2107/21 , G05D2111/17
摘要： A path planning system for an agricultural machine to automatically travel inside and outside a field includes a storage to store a map of a region including fields and roads, and a processor to generate a path for the agricultural machine on the map. The map includes attribute information representing, for each of the roads, at least one of whether the road is an agricultural road, whether the road is a road along a specific feature, or whether the road is a road where satellite signals from GNSS satellites are receivable. The processor is configured or programmed to generate at least one of a path including an agricultural road with priority, a path including a road along the specific feature with priority, or a path including, with priority, a road where the satellite signals are receivable, as the path for the agricultural machine based on the attribute information.
-
公开(公告)号：US20240302844A1
公开(公告)日：2024-09-12
申请号：US18425519
申请日：2024-01-29
发明人： Zichong CHEN , Zhuo LV
IPC分类号： G05D1/43 , A01D34/00 , G05D1/246 , A01D101/00 , G05D105/15 , G05D107/20
CPC分类号： G05D1/43 , A01D34/008 , G05D1/246 , A01D2101/00 , G05D2105/15 , G05D2107/23
摘要： A method for selecting a direction, a mower, and an electronic equipment are provided. With the method, a boundary of a target region is identified via a mower. If a distance between the mower and the boundary is determined to be within a first preset range according to the boundary as identified, the mower is controlled to move along the boundary in a movement direction. The movement direction is either a leftward direction along the boundary or a rightward direction along the boundary, which direction has a less angle with respect to an orientation of a head of the mower.
-
公开(公告)号：US20240289909A1
公开(公告)日：2024-08-29
申请号：US18586327
申请日：2024-02-23
CPC分类号： G06Q50/265 , G05D1/246 , G05D1/247 , G05D1/617
摘要： A computer-implemented method and system to enhance safety of one or more workers comprising worker safety management systems, mobile worker safety base stations, robots and one or more wearable devices. The computer-implemented method comprising the steps of: (a) detecting one or more safety issues by the one or more mobile worker safety base stations by using one or more data received from the one or more wearable devices; (b) communicating to the robots by the mobile worker safety base stations, to change their positions with or without using one or more downloaded maps to locate positions where wireless communication links are available and, transmitting signals and/or data based on the received data related to the detected safety issues from the mobile worker safety base stations.
-
4.发明公开公开(公告)号：US20240272642A1
公开(公告)日：2024-08-15
申请号：US18643238
申请日：2024-04-23
申请人： IHI Corporation
发明人： Mai EMOTO
IPC分类号： G05D1/246 , G05D1/646 , G05D107/70 , G05D111/10 , G06Q10/087
CPC分类号： G05D1/246 , G05D1/646 , G06Q10/087 , G05D2107/70 , G05D2111/17
摘要： A self-location estimation device includes a map information acquisition unit, an environmental information acquisition unit, and a self-location estimation unit. The map information acquisition unit is configured to acquire map information in a storage facility generated based on shape information of an object and storage status information of the object in the storage facility. The environmental information acquisition unit is configured to acquire environmental information of surroundings. The self-location estimation unit is configured to estimate a self-location based on the map information acquired by the map information acquisition unit and the environmental information acquired by the environmental information acquisition unit.
-
5.发明公开公开(公告)号：US20240255956A1
公开(公告)日：2024-08-01
申请号：US18562352
申请日：2022-01-27
发明人： HIROSHI MIYAGAWA
摘要： There are provided a device and a method that can quickly correct an approach area defined as a work area of a robot when a new obstacle that is not on a predefined map occurs. There are provided a differential obstacle detector that detects a differential obstacle corresponding to a difference from an obstacle recorded on a predefined map on the basis of information from a sensor that acquires travel environment information of the robot, and an approach area corrector that corrects, in consideration of the differential obstacle, a preset approach area in which a work by the robot is determined to be executable without contact with the obstacle, and generates a corrected approach area, the preset approach area including an area recorded on the predefined map. The approach area corrector determines whether or not a sampling point set inside the preset approach area allows the robot to work without contacting the differential obstacle, and generates the corrected approach area.
-
6.发明公开公开(公告)号：US20240219920A1
公开(公告)日：2024-07-04
申请号：US18570264
申请日：2022-10-18
申请人： ESSETEL. CO.,LTD
发明人： Joong Hee RYU , Sung Eun JIN , Young Il KIM
IPC分类号： G05D1/246 , G01S13/89 , G05D105/80 , G05D107/10 , G05D109/20 , G05D111/30
CPC分类号： G05D1/246 , G01S13/89 , G05D2105/87 , G05D2107/10 , G05D2109/20 , G05D2111/30
摘要： A method of operating a user terminal operating by at least one processor, wherein a bus information providing app executed according to a user input displays an information registration menu screen.
When an information registration signal is input, it is confirmed whether the information registration menu screen includes a bus stop surrounding image and additional information about the bus stop surrounding image, and bus stop surrounding information including the input bus stop surrounding image, the additional information, and location information of the user terminal is transmitted to a bus information system.-
公开(公告)号：US20240209579A1
公开(公告)日：2024-06-27
申请号：US18537801
申请日：2023-12-13
申请人： Rajeev Thakur
发明人： Rajeev Thakur
CPC分类号： E01H5/098 , E01H10/007 , G05D1/222 , G05D1/246 , G05D1/648 , A01D34/008
摘要： This invention relates to an autonomous snow removal machine for residential use. The machine is created by converting a manually operated snowblower to electric operation using motors, sensors, and a small computer. Key functions like wheel movement, chute control, and auger engagement are now powered by electric motors, while the auger rotation remains driven by the original gas engine or electric motor. Onboard sensors provide data to the control computer, enabling autonomous snow clearing within a defined area. The user interacts with the machine through a smartphone application to define the clearing zone and initiate the autonomous process. The machine can be operated manually when required by disengaging the clutch mechanism at the wheels and other electric motors.
-
公开(公告)号：US20240362924A1
公开(公告)日：2024-10-31
申请号：US18645882
申请日：2024-04-25
发明人： Gireesh NANDIRAJU , Ayush AGRAWAL , Ahana DATTA , Snehasis BANERJEE , Mohan SRIDHARAN , Madhava KRISHNA , Brojeshwar BHOWMICK
IPC分类号： G06V20/58 , G05D1/246 , G05D1/633 , G05D1/644 , G05D101/00 , G05D101/15 , G06T7/246 , G06V10/82
CPC分类号： G06V20/58 , G05D1/246 , G05D1/633 , G05D1/644 , G06T7/246 , G06V10/82 , G05D2101/15 , G05D2101/22 , G06T2207/20084 , G06T2207/30261
摘要： This disclosure relates generally to method and system for multi-object tracking and navigation without pre-sequencing. Multi-object navigation is an embodied Al task where object navigation only searches for an instance of at least one target object where a robot localizes an instance to locate target objects associated with an environment. The method of the present disclosure employs a deep reinforcement learning (DRL) based framework for sequence agnostic multi-object navigation. The robot receives from an actor critic network a deterministic local policy to compute a low-level navigational action to navigate along a shortest path calculated from a current location of the robot to the long-term goal to reach the target object. Here, a deep reinforcement learning network is trained to assign the robot with a computed reward function when the navigational action is performed by the robot to reach an instance of the plurality of target objects.
-
公开(公告)号：US20240353839A1
公开(公告)日：2024-10-24
申请号：US18662273
申请日：2024-05-13
申请人： TuSimple, Inc.
摘要： A system and method for implementing a neural network based vehicle dynamics model are disclosed. A particular embodiment includes: training a machine learning system with a training dataset corresponding to a desired autonomous vehicle simulation environment; receiving vehicle control command data and vehicle status data, the vehicle control command data not including vehicle component types or characteristics of a specific vehicle; by use of the trained machine learning system, the vehicle control command data, and vehicle status data, generating simulated vehicle dynamics data including predicted vehicle acceleration data; providing the simulated vehicle dynamics data to an autonomous vehicle simulation system implementing the autonomous vehicle simulation environment; and using data produced by the autonomous vehicle simulation system to modify the vehicle status data for a subsequent iteration.
-
公开(公告)号：US20240351207A1
公开(公告)日：2024-10-24
申请号：US18758950
申请日：2024-06-28
申请人： Intel Corporation
CPC分类号： B25J9/1664 , B25J5/007 , B25J9/1694 , G05D1/246
摘要： An apparatus, including: an interface operable to receive sensor data and generate a map representation of an environment of a robot; processing circuitry operable to: plan a sequence of states to direct the robot to a task goal of the robot based on the map representation and a kinematic state of the robot for a plurality of degrees of freedom; determine a time-dependent trajectory of the robot to the task goal based on the sequence of states by dynamically enabling or disabling one or more of the plurality of degrees of freedom; and generate a movement instruction to control movement of the robot based on the time-dependent trajectory.
-
-
-
-
-
-
-
-
-
搜索结果
65 条记录 (耗时 0.017 秒)
