Abstract: A traction saddle disposed on a tractor for connection with a traction pin of a trailer, is provided. The traction saddle includes a base, a gear set, and a damper. A gear carrier of the gear set fixes axial centers of the planetary gears of the gear set, the planetary gears are meshed with an inner ring gear of the gear set, and the inner ring gear is fixed to the base. The gear carrier is used for fixing the traction pin to rotate with the traction pin. The planetary gears are meshed with one end of a sun gear of the gear set to drive the sun gear to rotate, and the damper is connected to the other end of the sun gear to apply resistance to rotation of the sun gear. In addition, a traction pin, a tractor, a trailer, and a truck are also provided.

Abstract: The present disclosure discloses a method, apparatus, medium, and device for vehicle automatic navigation control.

Abstract: The disclosure provides a sensor case, a sensor system, and a vehicle, the sensor case including: a backing plate; a first base plate mounted to the backing plate, the first base plate having a first opening configured for the first sensor to pass through; and a protecting component magnetically coupled to the backing plate, the protecting component including a first cover plate positioned above the first base plate and a first gap being defined between the first cover plate and the first base plate. The sensor case of the disclosure can provide waterproof and rainproof functions of a sensor, and has a simple structure, stable performance, convenient opening and closing, and improved cleaning efficiency of the sensor.

Abstract: The present disclosure provides an on-board synchronization device. The on-board synchronization device includes: a first circuit and at least one second circuit. The first circuit is configured to receive an initial signal containing Universal Time Coordinated (UTC), generate a first signal containing the UTC, and output the first signal to at least one on-board device, such that the at least one on-board device synchronizes its built-in clock with the UTC based on the first signal. The second circuit is configured to receive a Pulse Per Second (PPS) signal, generate a periodic second signal with a same phase as the PPS signal, and output the second signal or the PPS signal to the at least one on-board device, such that the at least one on-board device performs a predetermined action based on the second signal or the PPS signal.

Abstract: The present application discloses a method, system and related device of implementing vehicle automatic payment. The method includes: controlling, by a vehicle controller, a vehicle to drive automatically and stop at a payment position; obtaining, by a payment terminal, vehicle identification information of the vehicle, and determining payment amount corresponding to the vehicle identification information; sending, by the payment terminal, leaving indication information to the vehicle controller after determining that the vehicle controller pays the payment amount; and controlling, by the vehicle controller, the vehicle to start and leave the payment position when receiving the leaving indication information.

Abstract: The present disclosure provides an intelligent port control system and related systems and apparatuses.

Abstract: The present disclosure provides a method and an apparatus for training a neural network and a computer server. The method includes: selecting automatically input data for which processing by the neural network fails, to obtain a set of data to be annotated; annotating the set of data to be annotated to obtain a new set of annotated data; acquiring a set of newly added annotated data containing the new set of annotated data, and determining a union of the set of newly added annotated data and a set of training sample data for training the neural network in a previous period as a set of training sample data for a current period; and training the neural network iteratively based on the set of training sample data for the current period, to obtain a neural network trained in the current period.

Abstract: The present disclosure provides a system, method and associated apparatus for autonomous vehicle transportation. The system includes: an operation system configured to generate a transportation plan for a vehicle and transmit the transportation plan to a vehicle controller of the vehicle; and the vehicle controller configured to control, in accordance with the transportation plan, the vehicle to autonomously move to a position of a checkpoint at an entrance to a target highway port, and interact with a checkpoint controller corresponding to the position of the checkpoint for autonomously passing the checkpoint; and control the vehicle to autonomously move from the position of the checkpoint to a specified loading/unloading position in the target highway port, and interact with a loading/unloading control apparatus for autonomous loading/unloading at the loading/unloading position.

Abstract: The present application discloses a method, system and related device of implementing vehicle automatic inspection and repair. The method includes: obtaining, by a vehicle controller, vehicle self-inspection data, and controlling a vehicle to drive and stop at an inspection and repair position when determining the vehicle malfunctions according to the vehicle self-inspection data; sending, by the vehicle controller, vehicle diagnostic information to an inspection and repair apparatus; and determining, by the inspection and repair apparatus, a corresponding repair advice according to the vehicle diagnostic information, and sending the repair advice to the vehicle controller.

Abstract: The present disclosure provides a method and an apparatus for determining an attitude angle of a camera, capable of improving the accuracy of the attitude angle of the camera, and in turn the accuracy of the attitude of the camera that is obtained based on the attitude angle of the camera. The present disclosure can also improve the accuracy of object distance measurement and vehicle positioning based on the attitude angle of the camera. In the method for determining an attitude angle of a camera, the camera is fixed to one and the same rigid object in a vehicle along with an Inertial Measurement Unit (IMU).

Abstract: The invention discloses a method, system and related device of implementing vehicle automatic loading and unloading, so as to achieve the automatic loading and unloading of the unmanned vehicle. The method includes: controlling, by a vehicle controller, a vehicle to drive automatically and stop at a loading and unloading position; obtaining, by a loading and unloading control apparatus corresponding to the loading and unloading position, vehicle identification information of the vehicle; verifying the vehicle identification information and controlling a loading and unloading machine to load and unload when the verification succeeds; sending a loading and unloading completion indication to the vehicle controller after the loading and unloading is completed; and controlling, by the vehicle controller, the vehicle to leave the loading and unloading position when receiving the loading and unloading completion indication.

Abstract: A system, a method and a device for planning a driving path for a vehicle are described. In one example aspect, the device is configured to: analyze sense data to obtain positioning data of vehicles; assign vehicle transportation tasks to an unmanned vehicle and a manned vehicle in the predetermined area in accordance with a predetermined transportation task, each vehicle transportation task including a transportation start point and a transportation end point; plan driving paths for the unmanned vehicle and the manned vehicle based on the assigned vehicle transportation tasks, the vehicle positioning data and map data; transmit the assigned transportation task and the planned driving path for the unmanned vehicle to the unmanned vehicle; and transmit the assigned transportation task and the planned driving path for the manned vehicle to a mobile device corresponding to the manned vehicle.

Abstract: The present document describes a vehicle-side image capturing system and method that is capable of improving qualities of images captured at vehicle-side. The system includes: a controller, a plurality of cameras, a light sensor and an encoder each connected to the controller. The controller is configured to: receive an illumination intensity of a current environment from the light sensor, select one of the plurality of cameras that is adapted to the illumination intensity as a target camera, activate when the target camera is different from a currently operating camera, deactivate the currently operating camera then configure the target camera as an operating camera for image capturing, and receive images captured by the operating camera and transmit the received images to the encoder. The encoder is configured to encode the received images and transmit the encoded images.

Abstract: A vehicle control method for platooning vehicles includes determining, for a first following vehicle, a predicted movement state information, and a lead vehicle predicted movement state information of a lead vehicle corresponding to a number of time points in the future. In the vehicle control method, when there is an adjacent second following vehicle, second following vehicle predicted movement state information corresponding to the number of time points is determined, and also includes determining optimized control quantities corresponding to respective ones of the number of time points, including determining an overall constraint model based on constraints between the first following vehicle and the lead vehicle, and constraints between the first following vehicle and the second following vehicle; determining the optimized control quantities; and performing longitudinal control in accordance with the optimized control quantities.

Abstract: The application discloses a method, system and related device of implementing vehicle automatically weighing, so as to achieve the automatically weighing of the unmanned vehicle. The method includes: controlling, by a vehicle controller, a vehicle to drive automatically and stop at a weighing position; weighing, by a weighbridge sensor, the vehicle when sensing the vehicle stopping at the weighing position, and sending weighing end information to the vehicle controller; and controlling, by the vehicle controller, the vehicle to start and leave the weighing position when receiving the weighing end information.

Abstract: The present disclosure provides a method and an apparatus for sampling training data and a computer server. The method includes: inputting a video to a target detection model to obtain a detection result for each frame of image; inputting the detection results for all frames of images in the video to a target tracking model, to obtain a tracking result for each frame of image; and for each frame of image in the video: matching the detection result and the tracking result for the frame of image, and when the detection result and the tracking result for the frame of image are inconsistent with each other, determining the frame of image as a sample image to be marked, for which processing by the target detection model is not optimal.

Abstract: The present disclosure provides a cooling system. The cooling system includes: a first set of fans mounted on an inward-facing side of an air inlet on an outer shell of a case; a second set of fans mounted on an inward-facing side of an air outlet on the outer shell of the case, for generating, in cooperation with the first set of fans, a high-pressure airflow from the air inlet to the air outlet; a first heat sink connected to heat generating component in the case, for absorbing heat from the heat generating component and transferring the absorbed heat to a second heat sink; and the second heat sink mounted on an inward-facing side of the second set of fans and cooled by the high-pressure airflow.

Abstract: The present disclosure provides a method and an apparatus for creating an occupancy grid map, as well as a processing apparatus. The method includes: creating a current occupancy grid map based on a location of the vehicle and a previous occupancy grid map; and determining a current probability that each grid in the current occupancy grid map belongs to each of occupancy categories based on last environment perception information received from the sensors and updating an occupancy category to which each grid in the current occupancy grid map belongs based on the current probability that the grid belongs to each of the occupancy categories, in accordance with an asynchronous updating policy.

Abstract: A method and device for training a neural network are disclosed. The method comprises: selecting, by a training device, a teacher network performing the same functions of a student network; and iteratively training the student network and obtaining a target network, through aligning distributions of features between a first middle layer and a second middle layer corresponding to the same training sample data, so as to transfer knowledge of features of a middle layer of the teacher network to the student network.

Abstract: The embodiments of this application provide a method and device for optimizing neural network. The method includes: binarizing and bit-packing input data of a convolution layer along a channel direction, and obtaining compressed input data; binarizing and bit-packing respectively each convolution kernel of the convolution layer along the channel direction, and obtaining each corresponding compressed convolution kernel; dividing the compressed input data sequentially in a convolutional computation order into blocks of the compressed input data with the same size of each compressed convolution kernel, wherein the data input to one time convolutional computation form a data block; and, taking a convolutional computation on each block of the compressed input data and each compressed convolution kernel sequentially, obtaining each convolutional result data, and obtaining multiple output data of the convolution layer according to each convolutional result data.