Abstract: This application relates to the field of robot control, and provides a motion state control method and apparatus, a device, and a readable storage medium. The method includes the following steps: Step 301: Acquire basic data and motion state data, the basic data being used for representing a structural feature of a wheeled robot, and the motion state data being used for representing a motion feature of the wheeled robot. Step 302: Determine a state matrix of the wheeled robot based on the basic data and the motion state data, the state matrix being related to an interference parameter of the wheeled robot, the interference parameter corresponding to a balance error of the wheeled robot. Step 303: Determine, based on the state matrix, a torque for controlling the wheeled robot. Step 304: Control, by using the torque, the wheeled robot to be in a standstill state.

Abstract: Disclosed is a snow shoveling and snow discharging assembly of a snow sweeping robot. The snow shoveling and snow discharging assembly comprises a snow stirring structure, a snow feeding structure and a snow raising structure. Stirring cutters in the snow stirring mechanism are driven by a stirring cutter shaft to stir bottom area snow into a snow feeding pipe of the snow feeding structure, an air blower in the snow feeding structure blows accumulated snow into a snow raising pipe of the snow raising structure through a connecting pipe, the snow raising pipe can be driven by a steering motor to rotate by a certain angle to control the snow raising direction, and a second electric push rod acts to control pitching of the guide part, so that the height of snow during snow raising is controlled.

Abstract: Disclosed are a method and a device for identifying full-section excavation parameters of large-section tunnel with broken surrounding rock, capable of solving the problem of inaccurate arrangement of blasting hole points in tunnel excavation engineering, and including the following steps: establishing a three-dimensional finite element model based on a blasting section design of a tunnel; performing a simulation with the three-dimensional finite element model based on blasting design parameters to obtain blasting quality parameters; selecting a group closest to a preset quality parameter from multiple groups of the blasting design parameters as target blasting design parameters, wherein the preset quality parameter is an acceptance grade standard of the tunnel; obtaining first thermal imaging information of a first hot spot of a surface to be blasted; calibrating actual hole spacing parameters based on the first thermal imaging information and the target blasting design parameters.

Abstract: Apparatuses, systems, and techniques of using one or more machine learning processes (e.g., neural network(s)) to detect objects from a plurality of image frames. In at least one embodiment, a plurality of image frames are fused into a feature map using one or more neural networks. In at least one embodiment, a plurality of image frames are processed using one or more neural networks to detect objects in a 3D space.

Abstract: A haptic feedback device includes: a first feedback apparatus, including: a fixed platform, a movable platform, a ring disposed on the movable platform, and a power unit disposed on the fixed platform and connected to the movable platform. The power unit is configured to obtain a first control signal generated by a controller and output torsion according to the first control signal. The movable platform is configured to be driven by the torsion to move relative to the fixed platform. The ring is configured to provide feedback force as the movable platform moves, to implement haptic feedback.

Abstract: The present invention discloses an integrated photodiode manufacturing method, a photodiode, and a photoelectric keyboard; the said method comprises the provision of a parallel support, and there is a plurality of pins on the said parallel support; on the parallel support, the infrared light chip and the visible light chip are fixed and installed; the electrodes of the said infrared chip and the said visible light chip are connected to the corresponding said pins respectively to form the electrical circuits independently with each other; the said infrared light chip and the said visible light chip are packaged with the packaging adhesive and/or the fluorescent adhesive to form the photodiode. The said packaging adhesive is transparent or translucent adhesive, and the said fluorescent adhesive is photoluminescence fluorescent material adaptable to the color of the said visible light chip; the packaged photodiode is baked and cured to form the photodiode integrating infrared light and visible light.

Abstract: In various examples, methods and systems are provided for estimating depth values for images (e.g., from a monocular sequence). Disclosed approaches may define a search space of potential pixel matches between two images using one or more depth hypothesis planes based at least on a camera pose associated with one or more cameras used to generate the images. A machine learning model(s) may use this search space to predict likelihoods of correspondence between one or more pixels in the images. The predicted likelihoods may be used to compute depth values for one or more of the images. The predicted depth values may be transmitted and used by a machine to perform one or more operations.

Abstract: This application relates to the field of robot control, and provides a motion state control method and apparatus, a device, and a readable storage medium. The method includes the following steps: Step 301: Acquire basic data and motion state data, the basic data being used for representing a structural feature of a wheeled robot, and the motion state data being used for representing a motion feature of the wheeled robot. Step 302: Determine a state matrix of the wheeled robot based on the basic data and the motion state data, the state matrix being related to an interference parameter of the wheeled robot, the interference parameter corresponding to a balance error of the wheeled robot. Step 303: Determine, based on the state matrix, a torque for controlling the wheeled robot. Step 304: Control, by using the torque, the wheeled robot to be in a standstill state.

Abstract: Embodiments of the present disclosure disclose a method and apparatus for verifying a vehicle function, an electronic device, and a storage medium, wherein the method includes: acquiring operation scenario data respectively corresponding to each of one or operation scenarios; determining, based on the operation scenario data respectively corresponding to each of the operation scenarios, first perception result information corresponding to a preset vehicle function of an ego vehicle in each of the operation scenarios; performing perception failure simulation processing on the first perception result information based on a perception failure simulation rule to obtain second perception result information corresponding to each of the operation scenarios; and verifying the preset vehicle function based on the second perception result information to obtain a verification result.

Abstract: A method includes: obtaining current motion state data of the wheel-legged robot, the current motion state data representing motion features of the wheel-legged robot, inputting the current motion state data into a nonlinear controller to obtain a target joint angular acceleration reference value of a target robot joint of the wheel-legged robot, and inputting the target joint angular acceleration reference value into a whole-body dynamics controller to output a joint torque for controlling the wheel-legged robot to perform a control task.

Abstract: The invention belongs to the technical field of waste cloth recovering and reusing, and particularly relates to waste-cloth-containing recovered fiber coating slurry and coating, and a preparation method thereof. 0.5-8 parts by weight of recovered fiber of waste cloth, 95-110 parts by weight of waterborne polyurethane, and 4-6 parts by weight of curing agent are prepared into recovered fiber coating slurry. The recovered fiber coating slurry is printed on a base cloth or a base plate, and dried to obtain a recovered fiber coating having a thickness of 0.1-1.0 mm. According to the technical solution provided by the invention, the field of physical method recycling of waste cloth is expanded to coating. Because the particle size of recovered fiber of the waste cloth is fine, the recovered fiber coating obtained by mixing waterborne polyurethane with a curing agent in a proper proportion has excellent abrasion resistance and mechanical properties.

Abstract: A mechanical leg comprises a frame, a retractable member, a wheel, an extension and retraction driving member, a travel driving member, an auxiliary leg, and an auxiliary wheel. The extension and retraction driving member is located on a side of the frame. The retractable member is connected to the extension and retraction driving member. The wheel is connected to the retractable member. The wheel is further connected to the travel driving member. A first end of the auxiliary leg is connected to the auxiliary wheel, and a second end of the auxiliary leg is located on the frame. The retractable member extends under the driving of the extension and retraction driving member to drive the wheel to jump. The wheel is driven by the travel driving member to move. When the auxiliary wheel contacts the ground, the mechanical leg moves with the rolling of the wheel and the auxiliary wheel.

Abstract: Disclosed are a method and a device for identifying full-section excavation parameters of large-section tunnel with broken surrounding rock, which is capable of solving the problem of inaccurate arrangement of blasting hole points in tunnel excavation engineering, including following steps: establishing a three-dimensional finite element model based on a blasting section design of a tunnel; performing a simulation with the three-dimensional finite element model based on blasting design parameters to obtain blasting quality parameters; selecting a group closest to a preset quality parameter from multiple groups of the blasting design parameters as target blasting design parameters, wherein the preset quality parameter is an acceptance grade standard of the tunnel; obtaining first thermal imaging information of a first hot spot of a surface to be blasted; calibrating actual hole spacing parameters based on the first thermal imaging information and the target blasting design parameters.

Abstract: An electrical connector includes: an insulating housing comprising a base portion and a tongue portion; plural terminals located at the tongue portion; and an outer shell surrounding the insulating housing and comprising a first shell and a second shell discrete from each other, the first shell comprises an upper plate, two first side plates, and a rear plate spaced from the two first side plates, the second shell comprises a lower plate and two second side plates, the first shell and the second shell are assembled together to commonly surround the insulating housing for defining a mating cavity around the tongue portion, the upper plate and the lower plate are parallel to the tongue portion and located at two opposite sides of the tongue portion, and each of the second side plates spans forward to reach a corresponding first side plate and spans backward to reach the rear plate.

Abstract: This application provides a capacitance detection circuit for detecting capacitance of a capacitor element within a capacitor array. The circuit includes a capacitance detection module for detecting a first capacitance of a first capacitor set, a second capacitance of a second capacitor set, and a third capacitance of the third capacitor set, the first capacitor set comprising the capacitor element and a row capacitor element in the same row of the capacitor array as the capacitor element, the second capacitor set comprising the capacitor element and a column capacitor element in the same column of the capacitor array as the capacitor element, the third capacitor set comprising the row capacitor element and the column capacitor element; and a processing module, configured to obtain the capacitance of the capacitor element according to the first capacitance, the second capacitance and the third capacitance.

Abstract: In various examples, systems and methods are disclosed relating to real-time multiview map generation using neural networks. A system can receive sensors images of an environment, such as images from one or more camera, RADAR, LIDAR, and/or ultrasound sensors. The system can process the sensor images using one or more neural networks, such as neural networks implementing attention structures, to detect features in the environment such as lane lines, lane dividers, wait lines, or boundaries. The system can represent the features in various views, including top-down/bird's eye view representations. The system can provide the representations for operations including map generation, map updating, perception, and object detection.

Abstract: Disclosed are smart glasses and a manufacturing method therefor. The smart glasses comprise a first assembly comprising a front crossbeam portion, a camera assembly and an optical mechanical assembly; and a second assembly comprising a rear crossbeam portion, a first temple and a second temple, wherein the first assembly is inserted into the second assembly. The first temple is provided with a first cavity; and the second temple is provided with a second cavity. A hollow passage for communicating the first cavity with the second cavity is enclosed by the front crossbeam portion and the rear crossbeam portion, the camera assembly is at least partially arranged in the first cavity, and the optical-mechanical assembly is at least partially arranged in the second cavity. The disclosed smart glasses have improved performance with enhanced convenience of assembly and ease of operation.

Abstract: A deep neural network(s) (DNN) may be used to perform panoptic segmentation by performing pixel-level class and instance segmentation of a scene using a single pass of the DNN. Generally, one or more images and/or other sensor data may be stitched together, stacked, and/or combined, and fed into a DNN that includes a common trunk and several heads that predict different outputs. The DNN may include a class confidence head that predicts a confidence map representing pixels that belong to particular classes, an instance regression head that predicts object instance data for detected objects, an instance clustering head that predicts a confidence map of pixels that belong to particular instances, and/or a depth head that predicts range values. These outputs may be decoded to identify bounding shapes, class labels, instance labels, and/or range values for detected objects, and used to enable safe path planning and control of an autonomous vehicle.

Abstract: A deep neural network(s) (DNN) may be used to detect objects from sensor data of a three dimensional (3D) environment. For example, a multi-view perception DNN may include multiple constituent DNNs or stages chained together that sequentially process different views of the 3D environment. An example DNN may include a first stage that performs class segmentation in a first view (e.g., perspective view) and a second stage that performs class segmentation and/or regresses instance geometry in a second view (e.g., top-down). The DNN outputs may be processed to generate 2D and/or 3D bounding boxes and class labels for detected objects in the 3D environment. As such, the techniques described herein may be used to detect and classify animate objects and/or parts of an environment, and these detections and classifications may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.