Abstract: Provided is a method for controlling movement of an autonomous mobile machine. The method includes that: a target path and a current state of the autonomous mobile machine are acquired; at least one preview distance is calculated according to a current speed; at least one preview point each corresponding to a respective one of the at least one preview distance is acquired according to the target path and the at least one preview distance; a lateral deviation from each preview point to a current position is calculated; a direction control angle parameter of a current control period is acquired according to the lateral deviation, the current speed and a preset parameter matching table; and the autonomous mobile machine is controlled to move according to the direction control angle parameter. Also provided are an apparatus for controlling movement of an autonomous mobile machine, a machine and a storage medium.

Abstract: The present disclosure relates to an unmanned lane keeping method and device, a computer device, and a storage medium. The method includes that: a vehicle road image collected by a data collector of the vehicle is received; the vehicle road image is transmitted to a preset DNN model of the vehicle for processing to obtain a steering wheel angle corresponding to the vehicle road image, wherein the DNN model of the vehicle is established by deep learning, and is used for characterizing a correspondence between the vehicle road image and the steering wheel angle; and the vehicle is controlled to keep driving in a corresponding lane according to the steering wheel angle.

Abstract: Provided are an automatic parking method and device. The automatic parking method includes: acquiring a global waypoint map of a parking lot where a vehicle is to be parked and position information of available parking spaces, and performing global path planning according to the global waypoint map and the available parking space position information; starting automatic driving according to the global path planning, acquiring vehicle visual information, and performing local path planning and obstacle avoidance processing according to the vehicle visual information; and searching for a parking space when automatically driving to the vicinity of the available parking spaces, and performing parking after finding an available parking space that satisfies a parking condition.

Abstract: Provided are a diagonal parking space detection method and device, and an automatic parking method and system. The diagonal parking space detection method includes: operation S11, determining a target diagonal parking space in multiple diagonal parking spaces arranged along a reference line, wherein the target diagonal parking space is located between a first reference parking space and a second reference parking space; operation S12, detecting a first reference point identifying an intersection point between the first reference parking space and the reference line; operation S13, calculating a slope of the target diagonal parking space; operation S14, detecting a second reference point identifying an intersection point between the second reference parking space and the reference line; and operation S15, calculating a width of the target diagonal parking space.

Abstract: Provide are a method and device for generating a path of an unmanned vehicle on a construction section. The method includes: when detecting a construction section, detected obstacle information is acquired; a current accessible area of the construction section is determined according to the type and position information of the obstacle, and each road point included in the current accessible area is determined; a terminal road point of a target driving path is determined according to the current accessible area; a current location of a vehicle is taken as a start road point, path search is performed in the road points included in the current accessible area according to the start road point and the terminal road point, and passing road points of the target driving path in the construction section are determined; and a target driving path is generated according to the start road point, the passing road points and the terminal road point.

Abstract: Provided are a diagonal parking space detection method and device, and an automatic parking method and system. The diagonal parking space detection method includes: operation S11, determining a target diagonal parking space in multiple diagonal parking spaces arranged along a reference line, wherein the target diagonal parking space is located between a first reference parking space and a second reference parking space; operation S12, detecting a first reference point identifying an intersection point between the first reference parking space and the reference line; operation S13, calculating a slope of the target diagonal parking space; operation S14, detecting a second reference point identifying an intersection point between the second reference parking spacer and the reference line; and operation S15, calculating a width of the target diagonal parking space.

Abstract: Provided is a method for controlling movement of an autonomous mobile machine. The method includes that: a target path and a current state of the autonomous mobile machine are acquired; at least one preview distance is calculated according to a current speed; at least one preview point each corresponding to a respective one of the at least one preview distance is acquired according to the target path and the at least one preview distance; a lateral deviation from each preview point to a current position is calculated; a direction control angle parameter of a current control period is acquired according to the lateral deviation, the current speed and a preset parameter matching table; and the autonomous mobile machine is controlled to move according to the direction control angle parameter. Also provided are an apparatus for controlling movement of an autonomous mobile machine, a machine and a storage medium.

Abstract: The present disclosure relates to an unmanned lane keeping method and device, a computer device, and a storage medium. The method includes that: a vehicle road image collected by a data collector of the vehicle is received; the vehicle road image is transmitted to a preset DNN model of the vehicle for processing to obtain a steering wheel angle corresponding to the vehicle road image, wherein the DNN model of the vehicle is established by deep learning, and is used for characterizing a correspondence between the vehicle road image and the steering wheel angle; and the vehicle is controlled to keep driving in a corresponding lane according to the steering wheel angle.

Abstract: Provided are an automatic parking method and device. The automatic parking method includes: acquiring a global waypoint map of a parking lot where a vehicle is to be parked and position information of available parking spaces, and performing global path planning according to the global waypoint map and the available parking space position information; starting automatic driving according to the global path planning, acquiring vehicle visual information, and performing local path planning and obstacle avoidance processing according to the vehicle visual information; and searching for a parking space when automatically driving to the vicinity of the available parking spaces, and performing parking after finding an available parking space that satisfies a parking condition.

Abstract: Provided are a path planning method and device for an unmanned vehicle, road segments of an origin and destination of a path are acquired; path search is performed to generate an initial path according to an exit endpoint of the road segment where the origin is located, an entrance endpoint of the road segment where the destination is located, and entrance endpoints and exit endpoints of the road segments for connecting the exit endpoint of the road, segment where the origin is located to the entrance endpoint of the road segment where the destination is located; an exit endpoint of a previous road section of the connecting passages in a passable direction is updated according to entrance endpoints of the connecting passages in the initial path; and a final planed path is generated according to different endpoints in the updated initial path.

Abstract: Provide are a method and device for generating a path of an unmanned vehicle on a construction section. The method includes: when detecting a construction section, detected obstacle information is acquired; a current accessible area of the construction section is determined according to the type and position information of the obstacle, and each road point included in the current accessible area is determined; a terminal road point of a target driving path is determined according to the current accessible area; a current location of a vehicle is taken as a start road point, path search is performed in the road points included in the current accessible area according to the start road point and the terminal road point, and passing road points of the target driving path in the construction section are determined; and a target driving path is generated according to the start road point, the passing, road poin is and the terminal road point.

Abstract: A method and a device for measuring various parameters of a membrane electrode assembly (MEA) in a fuel cell. Hydrogen gas and nitrogen gas or air are supplied to the fuel cell to be tested. A voltage of the fuel cell is diminished by connecting to a load until the voltage is zero. The fuel cell is charged at a constant current. A constant current value is measured by a current sensor. A current signal and a voltage signal are collected by a data collector and are converted into digital quantity signals which are transmitted to a data processing unit. Data are automatically processed by programming of the data processing unit. Parameters, including an electrochemical active surface area of a catalyst, a double-layer capacitance, a hydrogen crossover current, and an impedance of the MEA of the fuel cell are acquired by differentiation and integral operations of the voltage data.