22 results about "Motion computation" patented technology

The application discloses a kind of experimental measurement methods of non-spherical particle energy recovery coefficient, it is characterized in that, including the following steps: 1) establish the flat plate model of particle-wall collision working condition;2) establish non-spherical particle model and carry out DEM simulation;3) according to the motion parameter of non-spherical particle after collision, combined with free fall motion, the landing point of particle is calculated, and the random landing point distribution of non-spherical particle after collision with wall is quantified using probability density function;4) design several non-spherical particle models to carry out the above simulation and calculation, obtain the energy recovery coefficient and random landing point distribution of several different non-spherical particles;5) build artificial neural network training model, use Python tool to establish the nonlinear fitting relationship between random landing point distribution and energy recovery coefficient by artificial neural network, construct non-spherical particle energy recovery coefficient prediction model;The application has important significance to the research of particle-wall collision field.

1. Name of the product in this design: Graphical User Interface for Calculating Motion of Electronic Device and its Data Input Area. 2. Purpose of this design: An electronic device. 3. The key design features of this product are the graphical user interface portion for which protection is sought. 4. The picture or photo that best illustrates the key design points: Design 1 front view. 5. Design 1 is designated as the basic design. 6. Purpose of the graphical user interface: Design 1: The main view displays the interface for calculating the motion of the moving part. The left side of the main view of Design 1 displays an input box for user interaction, where users can fill in or select data related to the motion calculation of the mover. The right side of the main view of Design 1 displays the corresponding motion curve of the mover based on the input data. In the main view of Design 1, the single green block represents the content screen, and the X represents a variable character. In the main view of Design 2, the data input area of ​​the motion calculation interface of the part that needs to be protected is displayed. The data input area specifically displays the information involved in the motion calculation of the motion, such as "basic information", "setting parameters", "power configuration" and "actual calculation results" shown. The input boxes shown in the data input area are for user interaction. Users can enter data in the input boxes by filling in or selecting. In the main view of Design 2, the X represents a variable character. 7. Other situations requiring explanation: Design 1 requests protection for the overall appearance design of the product. Design 2 requests protection for a portion of the product's appearance design, wherein the portion covered by the blue semi-transparent layer is the part for which protection is not required.

It is difficult to accurately recognize movements from motion information related to localized body parts. [Solution] The information processing device of the present disclosure includes: a first motion calculation unit that calculates a first motion feature representing the characteristics of a person's movements based on whole-body motion data, which is motion data of the whole body of a person based on training data representing the movements of a person; a second motion calculation unit that calculates a second motion feature representing the characteristics of a person's movements based on local motion data, which is motion data of a local part of a person; and an update unit that updates parameters used by the second motion calculation unit to calculate the second motion feature based on training motion features, which are pre-specified motion characteristics of a person corresponding to training data, the first motion feature, and the second motion feature.

Techniques are discussed herein for restoring autonomous vehicle operations after one or more onboard computer systems have failed. An autonomous vehicle may comprise a primary compute node (PCN), an active motion compute node (MCN) and a backup MCN. In the event of a fault or failure at the active MCN, the backup MCN can take control of the autonomous vehicle, in an operation referred to herein as a "'backup MCN takeover."Subsequent "active MCN takeback" techniques can be applied to restore active MCN control of the autonomous vehicle, and to relinquish backup MCN control of the autonomous vehicle. If an active MCN takeback is successfully completed, the autonomous vehicle can return to an autonomous mission that was in place prior to the fault or failure at the active MCN.

Method for projecting light distributions (10) for a vehicle (12, 12a) using a light distribution system (14), wherein the light distribution system (14) comprises at least one sensor unit (16) for determining position data (18) of the vehicle (12, 12a), a computing unit (20), and at least one light projector (22), wherein the computing unit (20) converts target light distributions (24) stored in the computing unit (20) into projection data (26) related to the light projector (22), and the light projector (22) uses the projection data (26) to project the light distributions (10) onto at least one projection surface (32) in the environment, wherein the position data (18) of the vehicle (12, 12a) determined by the at least one sensor unit (16) are12a) are transmitted to a correction calculation module (28) of the computing unit (20), and the correction calculation module (28) uses the position data (18) to calculate corrected projection data (30) from the projection data (26), and the corrected projection data (30) are forwarded to the light projector (22) for the projection of corrected light distributions (10), characterized in that several sensor units (16), comprising inertial sensors and a camera system, are combined with the vehicle data, such as speed and steering angle, to further increase the accuracy of the correction by skillfully predicting the possible vehicle movements determined as position data (18), wherein the inertial sensors are acceleration sensors and yaw rate sensors which determine the vehicle movements as position data (18), wherein the sensor units (16) transmit position data (18) of the vehicle (12,12a) provide for use in the correction calculation module (28), wherein the vehicle movements are calculated as position data (18) in the correction calculation module (28) using algorithms based on the data determined by the camera system, wherein the projection data (26) are calculated by the computing unit (20) in parallel with the determination of the projection data (30) corrected by the correction calculation module (28), based on the specified target light distribution (24) and the position of the projection surface (32) detected by the light distribution system (14), wherein the corrected projection data (30) are recalculated every 10 to 40 milliseconds, and the correction calculation module (28) always refers back to the most recently determined projection data (26), whereby irregularities of the projection surface (32) are taken into account and thus a pre-distortion is implemented in the projection data (26) and in the corrected projection data (30).

The embodiment of the invention provides a universal motion processor for controlling motion of a physical entity. The core structure of the processor comprises at least one programmable motion calculation core used for processing calculation tasks related to dynamics and motion optimization of the physical entity; the at least one model interface is used for receiving model data describing the mechanical structure of the physical entity; and the at least one instruction interface is used for receiving motion task instructions. Wherein the motion computing core is configured to process a motion task instruction received through the instruction interface based on model data received through the model interface to generate a control signal for driving the physical entity. Based on the scheme, the invention provides a special hardware core to ensure the calculation performance and real-time performance of motion control, and meanwhile, through a standardized interface design, the system can adapt to different physical entities, thereby fundamentally solving the contradiction between'special 'and'universal'.

To prevent the control device from exceeding its allowable computational load and to suppress a decrease in control accuracy. [Solution] The drive control device includes: an motion generation unit that generates a target motion of the front work device using parameters based on the detection result of the attitude sensor and work design information; an actuator control unit that calculates the target operating speed of the actuator based on the target motion generated by the motion generation unit and generates and outputs a control signal to control the operation of the actuator at the calculated target operating speed; a computation load estimation unit that estimates the computation load of the drive control device based on the calculation time of the target motion in the motion generation unit, the calculation time of the target operating speed in the actuator control unit, and the load of the overall control device; and a parameter adjustment unit that adjusts the parameters to reduce the computation load of the motion generation unit if it is determined that the computation load estimated by the computation load estimation unit is higher than a predetermined reference value.

Method for operating a human-machine interface (10) comprising the steps: - Applying a large number of accelerometers (12) to the skin (16) of a user by means of a holding device (14) - Calculating a user-requested input command from the user's muscle movements detected by the accelerometers (12), by the following procedure steps: ◯ Determining a common movement of the accelerometers (12) caused by a movement of the entire body part (18) of the user to which the accelerometers (12) are attached, ◯ Removing the accelerations of the accelerometers (12) caused by this movement of the accelerometers (12), so that only their relative accelerations to each other remain and are taken into account for further processing.

This invention relates to a processing method for improving auxiliary clamping efficiency in a laser processing CNC system, comprising the following steps: raising the Z-axis; when the Z-axis moves to the position of the outer circle of the tube, the auxiliary clamping begins to release; the X-axis, Y-axis, Z-axis, and B-axis begin to move towards the starting point of the next cutting segment; calculating the maximum remaining angle of the B-axis; when the B-axis moves to a certain position from the endpoint, the auxiliary clamping begins to clamp; the Z-axis descends to the processing position, ready for the next processing. The processing method, device, processor, and computer-readable storage medium of this invention in a laser processing CNC system for improving auxiliary clamping efficiency reduce the waiting time of the auxiliary clamping and shorten the overall processing time. This invention provides a method for solving the maximum remaining angle of the B-axis in the method for improving auxiliary clamping efficiency, simplifying the process and improving the efficiency of the calculation.

The objective is to provide a method for calculating forward motion that can quickly determine the position and orientation of the mechanical interface of a 6-degree-of-freedom parallel link robot. [Solution] A method for calculating forward motion for calculating the position and orientation of a mechanical interface of a 6-degree-of-freedom parallel link robot, wherein the parallel link robot has first to sixth movable bodies that move on straight lines parallel to each other, first to sixth rods whose base ends are connected to each of the first to sixth movable bodies via ball joints and which have the same rod length, and the mechanical interface connected to the tip of each of the first to sixth rods via ball joints.

The invention discloses a large model application platform construction method oriented to aircraft task intellectualization. The construction method of the platform comprises the following steps: deploying a large language model for local quantification of an aircraft orbital motion calculation vertical field task as a core processing engine; an aircraft orbital motion calculation type task planning workflow constructed based on an open source framework is established, and a complex orbital motion calculation type task is decomposed into fine grit; building an aircraft orbit task real-time correction workflow for monitoring a task execution state and dynamically adjusting a plan; a set of model context protocol tool set required by aircraft orbital motion calculation is assembled, calculation, model, perception and action tools are integrated, and the capability boundary of a special large model is greatly expanded. Besides, an aircraft orbit calculation type task execution specification manual knowledge base and a retrieval auxiliary workflow thereof are also constructed, and an accurate vertical field specification basis is provided for task execution through vectorization storage and semantic retrieval.

1. Name of the product in this design: Graphical User Interface for Calculating Motion of Electronic Device and its Data Input Area. 2. Purpose of this design: An electronic device. 3. The key design features of this product are the graphical user interface portion for which protection is sought. 4. The picture or photo that best illustrates the key design points: Design 1 front view. 5. Design 1 is designated as the basic design. 6. Purpose of the graphical user interface: Design 1: The main view displays the interface for calculating the motion of the moving part. The data input area on the right side of the main view of Design 1 displays an input box for user interaction. Users can enter data related to the motion calculation of the mover by filling in or selecting data in the input box. The visualization display area on the left side of the main view of Design 1 displays the corresponding motion curve of the mover based on the input data. In the main view of Design 2 and Design 3, the data input area of ​​the mover motion calculation interface, which needs to be protected, is displayed in the local area. The data input area specifically displays the information involved in the mover motion calculation, such as "Basic Information", "Setting Parameters", "Power Configuration", "Control Thrust Requirements", and "Actual Calculation Results". The input boxes shown in the data input area are for user interaction, and users can enter data in the input boxes by filling in or selecting. In the interface, X represents a variable character. 7. Other situations requiring explanation: Design 1 requests protection for the overall appearance design of the product. Designs 2 and 3 request protection for partial appearance designs of the product, where the portion covered by the blue semi-transparent layer is the part for which protection is not required.

The application discloses a visible light video multi-target tracking method and system based on DeepSORT, and the method comprises the following steps: inputting a visible light video, detecting a target by using YOLOv5, and obtaining target information; introducing a camera motion compensation method to correct the position information of the target, and using a Kalman filtering algorithm to predict the trajectory of all targets, and determining whether the trajectory is in a confirmed state or an unconfirmed state; combining the target with the confirmed state trajectory to calculate a cost matrix based on appearance and motion for cascade matching; using a GIoU matching algorithm and an IoU matching algorithm to sequentially match mismatched trajectories and mismatched targets respectively; using the Kalman filtering algorithm in combination with an adaptive noise scale to update the state of the matched trajectory, and outputting the target information after the state update. Through the technical scheme of the application, the multi-target tracking accuracy is improved, the interference of uncertainty on the tracking system is reduced, the robustness of the target tracking system is improved, and the false matching is reduced.

Techniques are discussed herein for the use of multiple different autonomous safety operation modes. The different safety operation modes can be used by a backup motion compute node (MCN) of an autonomous vehicle, so that the backup MCN is prepared to perform safety operations according to an applicable safety operation mode. In a first safety operation mode, the autonomous vehicle can respond to emergencies or fault conditions by following generated safety operation trajectories. The generated safety operation trajectories can include, e.g., moderate braking and active steering. In contrast, in a second safety operation mode, the autonomous vehicle can respond to emergencies or fault conditions by following preset steering and braking settings.

The invention discloses a linear encoder precision compensation system and method based on error table compensation, and the system comprises a module pedestal, the module pedestal is provided with a multi-read-head linear magnetic encoder and a rotor sliding along the module pedestal, the rotor is provided with a magnetic scale cooperating with the multi-read-head linear magnetic encoder, and the magnetic scale is provided with a plurality of error tables. A high-precision reference measurement system is arranged on the module base and the rotor in a matched manner; the calibration data acquisition unit is used for synchronously acquiring position output information of the multi-read-head linear magnetic encoder and the high-precision reference measurement system; and the calibration module is used for controlling the rotor to move, calculating a position error and generating a static error compensation table. The system is high in cost benefit, the precision of magnetic drive module products produced in a large scale can be permanently improved only by adding a set of reusable reference measurement system in a factory leaving link, and the situation that each module is equipped with an expensive high-precision grating ruler is avoided.

In various examples, a technique for hybrid imitation learning includes generating, via execution of a first machine learning model, a first plurality of actions based on a first plurality of states associated with a virtual character and computing a first set of rewards based on the first plurality of actions and a reference motion for the virtual character. The technique also includes generating, via execution of the first machine learning model, a second plurality of actions based on a second plurality of states associated with the virtual character and a training target goal and computing a second set of rewards based on discriminator output generated by a second machine learning model from the second plurality of actions. The technique further includes updating one or more parameters of the first machine learning model based on the first and second sets of rewards to produce a trained machine learning model.

A surgical table (1) comprises a base (2), components (7), and a controller (9). The controller (9) is configured to store a geometric collision model including object model datasets of the components (7), of the base (2), and of a supporting surface (6) and motion compute datasets of the base (2) and of the components (7). The controller (9) is configured to execute an anti-collision algorithm defining ranges of motion of the base (2) and of the components (7) based on a specific geometric collision model, and to control a drive (8, 8', 8") to move the base (2) and the components (7) within the defined ranges of motion such that a collision is prevented. The controller (9) is configured to store a defined initial geometric collision model of a configuration and to adapt the initial geometric collision model to an actual geometric collision model according to an actual configuration.

To generate more accurate depth estimation models from images. [Solution] This is a program that causes a computer to perform a depth calculation step, a motion calculation step, a correspondence calculation step, and a learning step. The learning step updates the parameters of the first and second estimated models to optimize a first loss function that includes a term showing the difference between correspondence information and correspondence training data, which is training data for the correspondence between the first and second pixels; a second loss function that includes a term for depth; and a third loss function that includes a term showing the difference in pixel values ​​between the first and second pixels whose correspondence is indicated by the correspondence information. The program then generates the first and second estimated models represented by the updated parameters.

Techniques are discussed herein for restoring autonomous vehicle operations after one or more onboard computer systems have failed. An autonomous vehicle may comprise a primary compute node (PCN), an active motion compute node (MCN) and a backup MCN. During a first “nominal” mode, the active MCN can supply first vehicle pose information for use by the PCN. If the active MCN experiences a fault, the autonomous vehicle can enter a second “emergency” mode in which the backup MCN supplies second vehicle pose information for use by the PCN. As part of its restoration operations, the active MCN can use a snapshot of the second vehicle pose information as a starting point to resume computing the first vehicle pose information.

Techniques are discussed herein for the use of multiple different autonomous safety operation modes. The different safety operation modes can be used by a backup motion compute node (MCN) of an autonomous vehicle, so that the backup MCN is prepared to perform safety operations according to an applicable safety7 operation mode. In a first safety operation mode, the autonomous vehicle can respond to emergencies or fault conditions by following generated safety operation trajectories. The generated safety operation trajectories can include, e.g., moderate braking and active steering. In contrast, in a second safety operation mode, the autonomous vehicle can respond to emergencies or fault conditions by following preset steering and braking settings.