Abstract: A slip sensation simulation apparatus includes a base, a first haptic assembly, and a second haptic assembly. The first haptic assembly includes a first synchronous belt, a plurality of first synchronous wheels, and a first motor. The first motor is in a transmission connection with one of the first synchronous wheels, to drive the first synchronous wheels and the first synchronous belt to rotate. The second haptic assembly includes a second synchronous belt, a plurality of second synchronous wheels, and a second motor. The second motor is in a transmission connection with one of the second synchronous wheels, to drive the second synchronous wheels and the second synchronous belt to rotate. The first synchronous belt is located at an inner side of the second synchronous belt. Rotational axial directions of the first and second synchronous belts are different. The first synchronous belt is in contact with the second synchronous belt.

Abstract: A method for controlling a robot to perform a somersault motion enables the robot, when facing an obstacle such as a hole, ditch, or ravine, to cross the obstacle by performing a somersault motion. The robot includes a wheel-leg portion and a base portion connected via a joint. The robot receives a motion instruction and controls a torque of the joint to allow the robot to perform the somersault. During a takeoff phase of the somersault, a center of mass of the wheel-leg portion is lower than a center of mass of the base portion. During a flight phase, the center of mass of the wheel-leg portion is higher than the center of mass of the base portion at some point in time. During the landing phase, the center of mass of the wheel-leg portion is lower than the base portion. This can enable the robot to avoid obstacles.

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: A method for controlling motion of a legged robot includes determining one or more candidate landing points for each foot of the robot. The method further includes determining a first correlation between a center of mass position change parameter, candidate landing points, and foot contact force. The method further includes determining, under a constraint condition set and based on the first correlation, a target center of mass position change parameter, a target step order, and a target landing point for each foot selected among the one or more candidate landing points for the respective foot, the constraint condition set constraining a step order. The method further includes controlling, according to the target center of mass position change parameter, the target step order, and the target landing point for each foot, motion of the legged robot in the preset period.

Abstract: A legged robot motion control method includes: acquiring centroid state data of a spatial path start point and a spatial path end point of a motion path; determining a target landing point of afoot of the legged robot in the motion path based on the spatial path start point and the spatial path end point; determining a change relationship between a centroid position change coefficient and a foot contact force based on the centroid state data; selecting, under constraint of a constraint condition set, a target centroid position change coefficient that meets the change relationship; the constraint condition set including a spatial landing point constraint condition; determining a target motion control parameter according to the target centroid position change coefficient and the target landing point of the foot; and controlling, based on the target motion control parameter, the legged robot to perform motion according to the motion path.

Abstract: A method for controlling motion of a legged robot includes: determining, according to state data of the legged robot at a start moment in a preset period, a candidate landing point of each foot in the preset period; determining, according to the state data at the start moment and the candidate landing point of each foot, a first correlation between a centroid position change parameter, a step duty ratio, a candidate landing point, and a foot contact force; determining, under a constraint of a constraint condition set, a target centroid position change parameter, a target step duty ratio, and a target landing point satisfying the first correlation; and controlling, according to the target centroid position change parameter, the target step duty ratio, and the target landing point, motion of the legged robot in the preset period.

Abstract: A legged robot motion control method, apparatus, and device, and a storage medium. The method includes: acquiring center of mass state data corresponding to a spatial path starting point and spatial path ending point of a motion path; determining a candidate foothold of each foot in the motion path based on the spatial path starting point and the spatial path ending point; determining a variation relationship between a center of mass position variation coefficient and a foot contact force based on the center of mass state data; screening out, under restrictions of a constraint set, a target center of mass position variation coefficient and target foothold that satisfy the variation relationship; determining a target motion control parameter according to the target center of mass position variation coefficient and the target foothold; and controlling a legged robot based on the target motion control parameter to move according to the motion path.

Abstract: This application relates to a planar contour recognition method and apparatus, a computer device, and a storage medium. The method includes obtaining a target frame image collected from a target environment; fitting edge points of an object plane in the target frame image and edge points of a corresponding object plane in a previous frame image to obtain a fitting graph, the previous frame image being collected from the target environment before the target frame image; deleting edge points that do not appear on the object plane of the previous frame image, in the fitting graph; and recognizing a contour constructed by remaining edge points in the fitting graph as a planar contour.

Abstract: The present disclosure provides an image processing method and apparatus, an electronic device, and a computer-readable storage medium. The method includes: obtaining a first three-dimensional image of a target object in a three-dimensional coordinate system; determining a target plane of the target object in the first three-dimensional image, the target plane comprising target three-dimensional points; projecting the target three-dimensional points to a two-dimensional coordinate system defined on the target plane, to obtain target two-dimensional points; determining a target polygon and a minimum circumscribed target graphic of the target polygon according to the target two-dimensional points; and recognizing the minimum circumscribed target graphic as a first target graphic of the target object in the first target three-dimensional image.

Abstract: A scene contour recognition method is provided. In the method, a plurality of scene images of an environment is obtained. Three-dimensional information of a target plane in the plurality of scene images is determined based on depth information for each of the plurality of scene images, The target plane corresponds to a target object in the plurality of scene images. A three-dimensional contour corresponding to the target object is generated by fusing the target plane in each of the plurality of scene images based on the three-dimensional information of the target plane in each of the plurality of scene images. A contour diagram of the target object is generated by projecting the three-dimensional contour onto a two-dimensional plane.

Abstract: This application discloses an image feature recognition method performed at a computing device. The computing device obtains a first neural network model by training parameters in a second neural network model using a first training set and a second training set consecutively, image features of training pictures in the first training set being marked and image features of training pictures in the second training set being not marked. After obtaining a first neural network model, the computing device obtains a recognition request for recognizing an image feature in a target picture. The computing device then recognizes the image feature in the target picture by applying the target picture to the first neural network model. Finally the computing device returns a first recognition result of the first neural network model, the first recognition result indicating an image feature (for example, a pathological feature) recognized in the target picture.

Abstract: A computing device creates first relation data indicating a relation between an interval duration and a center of mass position of a legged robot. The first relation data comprises a first constant, C. The computing device creates second relation data corresponding to at least one leg of for the legged robot and a force corresponding to the at last one leg with the ground. The second relation data comprises the first constant, C. The computing device creates third relation data according to the second relation data. The device determines a value of the first constant, C, when a target value J is a minimum value, and obtains the first relation data according to the determined value of the first constant, C.

Abstract: This disclosure relates to a spatial calibration method and apparatus of a robot ontology coordinate system based on a visual perception device and a storage medium. The method includes: obtaining first transformation relationships; obtaining second transformation relationships; using a transformation relationship between a visual perception coordinate system and an ontology coordinate system as an unknown variable; and resolving the unknown variable based on an equivalence relationship between a transformation relationship obtained according to the first transformation relationships and the unknown variable and a transformation relationship obtained according to the second transformation relationships and the unknown variable, to obtain the transformation relationship between the visual perception coordinate system and the ontology coordinate system.

Abstract: Embodiments of the present disclosure provide a slip simulation apparatus, a controlled robot, a game handle, a virtual game console, and a control system. The slip simulation apparatus includes a base; at least one motor arranged on the base; a slip simulation controller, configured to: receive slip data, and generate a rotating speed control signal used for controlling the at least one motor; and at least one synchronous wheel, at least one synchronous belt, and at least one limit apparatus associated with the motor, the synchronous wheel being sleeved on the synchronous belt and the limit apparatus, the motor being drivingly connected to the at least one synchronous wheel to drive, according to the rotating speed control signal, the at least one synchronous wheel and the at least one synchronous belt to rotate.

Abstract: An image processing method is provided, including: obtaining a target image; invoking an image recognition model including: a backbone network, a pooling module and a dilated convolution module that are connected to the backbone network and that are parallel to each other, and a fusion module connected to the pooling module and the dilated convolution module; performing feature extraction on the target image by extracting, using the backbone network, a feature map of the target image, separately processing, using the pooling module and the dilated convolution module, the feature map, to obtain a first result outputted by the pooling module and a second result outputted by the dilated convolution module, and fusing the first result and the second result by using the fusion module into a model recognition result of the target image; and determining a semantic segmentation labeled image of the target image based on the model recognition result.

Abstract: A slip sensation simulation apparatus includes a base, a first haptic assembly, and a second haptic assembly. The first haptic assembly includes a first synchronous belt, a plurality of first synchronous wheels, and a first motor. The first motor is in a transmission connection with one of the first synchronous wheels, to drive the first synchronous wheels and the first synchronous belt to rotate. The second haptic assembly includes a second synchronous belt, a plurality of second synchronous wheels, and a second motor. The second motor is in a transmission connection with one of the second synchronous wheels, to drive the second synchronous wheels and the second synchronous belt to rotate. The first synchronous belt is located at an inner side of the second synchronous belt. Rotational axial directions of the first and second synchronous belts are different. The first synchronous belt is in contact with the second synchronous belt.

Abstract: This application provides an image recognition method, a storage medium, and a computer device. The method includes: obtaining a to-be-recognized image; preprocessing the to-be-recognized image, to obtain a preprocessed image; obtaining, through a first submodel in a machine learning model, a first image feature corresponding to the to-be-recognized image, and obtaining, through a second submodel in the machine learning model, a second image feature corresponding to the preprocessed image; and determining, according to the first image feature and the second image feature, a first probability that the to-be-recognized image belongs to a classification category corresponding to the machine learning model. It may be seen that, the solutions provided by this application can improve recognition efficiency and accuracy.

Abstract: An image processing method is provided, including: obtaining a target image; invoking an image recognition model including: a backbone network, a pooling module and a dilated convolution module that are connected to the backbone network and that are parallel to each other, and a fusion module connected to the pooling module and the dilated convolution module; performing feature extraction on the target image by extracting, using the backbone network, a feature map of the target image, separately processing, using the pooling module and the dilated convolution module, the feature map, to obtain a first result outputted by the pooling module and a second result outputted by the dilated convolution module, and fusing the first result and the second result by using the fusion module into a model recognition result of the target image; and determining a semantic segmentation labeled image of the target image based on the model recognition result.

Abstract: This application provides an image recognition method, a storage medium, and a computer device. The method includes: obtaining a to-be-recognized image; preprocessing the to-be-recognized image, to obtain a preprocessed image; obtaining, through a first submodel in a machine learning model, a first image feature corresponding to the to-be-recognized image, and obtaining, through a second submodel in the machine learning model, a second image feature corresponding to the preprocessed image; and determining, according to the first image feature and the second image feature, a first probability that the to-be-recognized image belongs to a classification category corresponding to the machine learning model. It may be seen that, the solutions provided by this application can improve recognition efficiency and accuracy.

Abstract: This application discloses an image feature recognition method performed at a computing device. The computing device obtains a first neural network model by training parameters in a second neural network model using a first training set and a second training set consecutively, image features of training pictures in the first training set being marked and image features of training pictures in the second training set being not marked. After obtaining a first neural network model, the computing device obtains a recognition request for recognizing an image feature in a target picture. The computing device then recognizes the image feature in the target picture by applying the target picture to the first neural network model. Finally the computing device returns a first recognition result of the first neural network model, the first recognition result indicating an image feature (for example, a pathological feature) recognized in the target picture.