12 results about "Motion optimization" patented technology

The invention relates to the technical field of robot control. A humanoid robot gait generation system based on hierarchical control is characterized by comprising a multi-layer control system operating at different refresh frequencies, and the multi-layer control system comprises a high-layer gait and trajectory planning layer operating at a low frequency and used for generating a macroscopic motion instruction; the middle-layer whole-body motion optimization layer runs at medium frequency, serves as a bridge of high-layer planning and bottom-layer control and is used for converting expected plantar and trunk tracks into reference motion of all joints of the whole body; the bottom joint servo control layer runs at the highest frequency and is responsible for accurately tracking a joint-level instruction output by the whole-body motion optimization layer; the state sensing and feedback closed-loop layer is used for feeding back state information, obtained in real time, of the body state of the robot to all the layers, providing a basis for track re-planning of a high layer and providing a real-time state initial value for optimization of a middle layer; and a feedback signal is provided for servo control of a bottom layer.

The invention relates to the technical field of load motion platform control, in particular to a vibration control method and device of a load motion platform, equipment and a storage medium. The method comprises the following steps: collecting state parameters of a load motion platform to obtain a multi-dimensional state parameter set, and executing parameter fusion processing to obtain a fusion state vector; updating the model parameter set according to the fusion state vector, and obtaining predicted deformation based on the fusion state vector and the elastic deformation parameter; determining a load change trend in combination with historical load data and the fusion state vector, and determining an optimization curve parameter in combination with a load characteristic parameter; generating a first acceleration and deceleration curve in combination with the basic curve parameter and the optimized curve parameter; determining a speed correction amount according to the predicted deformation amount, superposing the speed correction amount to the first acceleration and deceleration curve, and rejecting a target resonant frequency component through a vibration transmission parameter to generate a second acceleration and deceleration curve; and generating a motion optimization instruction based on the second acceleration and deceleration curve to execute motion control. The platform control stability can be improved.

The application provides a logistics warehouse picking training and motion optimization method and system based on virtual reality, and relates to the technical field of intelligent warehousing. The method constructs a virtual warehouse environment linked with a database in real time and generates a picking task guide; collects depth images, inertial measurement data and physiological signals, and fuses to generate whole body posture data of a trainee; identifies non-standard actions based on the posture data and calculates work efficiency; combines the carrying weight, physiological state and motion data to perform ergonomics scoring, fatigue accumulation analysis and injury risk prediction; dynamically adjusts the task difficulty and controls the training process according to the training state; and finally generates a training evaluation report through motion data comparison. The application can improve the quality of logistics picking training and reduce the risk of work injury.

A deformation-viewpoint dynamic coupling robot viewpoint intelligent planning method and system, the method comprising: constructing a deformation-view mapping model and training; constructing a space-time graph convolution network and training; constructing a multi-objective hierarchical decoupling optimization network, inputting the multi-modal information in the actual into the trained deformation-view mapping model, generating a coverage prediction value, generating a compensated view according to the deformation compensation layer; the motion optimization layer uses a deep reinforcement learning strategy network and combines an adaptive importance sampling strategy to screen the compensated view and generate a screened candidate viewpoint set; generating a space-time safety corridor according to the trained space-time graph convolution network, scoring the collision risk of the screened candidate viewpoint set according to the safety constraint layer, constructing a multi-objective fitness function and solving, obtaining the optimal viewpoint set. The present application is suitable for high-precision visual detection scene, which significantly improves the real-time performance and robustness of robot viewpoint planning.

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'.

This invention relates to the field of program-controlled robot motion technology, specifically to a motion optimization method, system, and device for amphibious robots. The invention first acquires motion sample information of the amphibious robot in each motion scenario. Then, based on the distribution characteristics and control effect parameters of control parameter combinations at all historical motion moments, it filters out all reference control parameter combinations, thereby determining the distribution reference range of road condition data corresponding to each reference control parameter combination. Finally, based on the distribution reference range of the amphibious robot's current road condition data, it determines the control parameters of the amphibious robot and performs motion control. This invention, based on the effective reference provided by the amphibious robot's historical motion data and control strategies, can adaptively match control strategies based on the current motion situation, avoiding rule base conflicts in different scenarios and improving the motion control effect of the amphibious robot.

The application discloses a kind of double-arm motion planning methods based on speed constraint space, belong to robot technical field.Method includes: first give the starting point and target point of double-arm carrying object;Then the speed constraint space of object is calculated to carry out uniform sampling, obtain the sampling speed set of object;Then distance deviation, pose deviation, joint torque and task operability are used as index to establish evaluation function, the sampling speed is scored by evaluation function, selects the highest score sampling speed as the speed of object next time;Finally, the optimal sampling speed of object each time is constantly selected until the complete trajectory from starting point to target point is obtained.The application realizes the motion optimization of double-arm coordination under the kinematic and dynamic constraint conditions, improves the task operability of double-arm, reduces the joint torque of robot arm, guarantees the stability and safety of double-arm carrying process.

This disclosure provides a motion optimization obstacle avoidance control method and system for vehicle-like robots, relating to the field of robot path planning and obstacle avoidance technology. The method includes: defining the state space of the vehicle-like robot; planning the global path of the vehicle-like robot; fitting the sparse state sequence using Hermite curves to obtain a time-space continuous trajectory; establishing a collision model between the vehicle-like robot and obstacles; transforming the geometric separation conditions between the robot and obstacles into a set of continuously differentiable nonlinear algebraic constraints based on duality theory; using the time-space continuous trajectory as a reference trajectory; and constructing a trajectory optimization objective function. This function can solve for the motion control quantities of the vehicle-like robot while satisfying its dynamic constraints, input constraints, and acceleration smoothing constraints, thus achieving obstacle avoidance planning and control of polygonal obstacles. This disclosure enables real-time, full-size robot planning and obstacle avoidance control.

The invention discloses a fixed base mechanical arm point-to-point trajectory optimization method based on a near-end strategy optimization algorithm, solves the problem that a high-dimensional continuous action space exists when deep reinforcement learning is directly used for a fixed base mechanical arm tail end position to reach a task, and belongs to the field of robot operation control and mechanical arm autonomous motion optimization. The method comprises the steps that a mechanical arm kinematics model is established, and constraint conditions are defined; modeling a tail end point-to-point arrival task as a sequential decision process, constructing a state vector as the input of a strategy network, and taking a tail end displacement increment direction vector as the action output of the strategy network; mapping the tail end displacement increment direction vector into a joint increment through differential inverse kinematics, and performing constraint processing according to a constraint condition to generate an executable joint control instruction; and training the strategy network by adopting a near-end strategy optimization algorithm, obtaining a single-step reward through a multi-target reward function, and evaluating the performance output by the action of the strategy network according to the single-step reward until convergence.

The invention provides a fiber winding multi-target coordinated motion optimization method for a composite shell robot, relates to the field of fiber winding optimization, and solves the technical problem that multi-target performance in a whole winding path cannot be integrally optimized due to the fact that a greedy or single-target optimization strategy is mostly adopted when redundant variables are processed in the prior art. The method comprises the steps that a target winding track and position information of a plurality of doffing points in the target winding track are generated under the boundary limiting condition according to geometric structure parameters and a non-geodesic equation of a shell core model, and a plurality of sub-models are constructed in three-dimensional software based on a fiber winding robot and the shell core model, and constructing a kinematic model according to the position relationship and the spatial constraint relationship among the plurality of sub-models, and performing spatial rotation and translation transformation on the target winding trajectory according to the position information of the plurality of doffing points to obtain a task trajectory point of an end effector of the winding robot. The device is used for the fiber winding process of the large-size composite material shell robot.

This invention discloses a pose-coupled path planning method for unmanned aerial vehicles (UAVs) based on dual quaternions. The method uses dual quaternions to uniformly represent the spatial position and three-dimensional attitude of the UAV, achieving pose-coupled modeling. The flight path is discretized into a series of path nodes, and the pose parameter of each node is parameterized as a motion vector. A dual quaternion optimization model is constructed. Through predefined motion operators and unit dual quaternion operators, a mapping is established between the dual quaternion space and the motion vector space, thereby transforming the dual quaternion optimization model into a motion optimization model in the motion vector space. The motion optimization model is iteratively solved in the motion vector space, updating the path node sequence to obtain the optimal path that satisfies all constraints. The optimized path nodes are then smoothed to generate the flight trajectory. This invention significantly improves path planning efficiency and path quality.

The invention discloses a deformation-visual angle dynamic coupling robot viewpoint intelligent planning method and system. The method comprises the steps that a deformation-visual angle mapping model is constructed and trained; constructing a space-time diagram convolutional network and training the space-time diagram convolutional network; constructing a multi-target layered decoupling optimization network, inputting actual multi-modal information into the trained deformation-visual angle mapping model, generating a coverage prediction value, and generating a compensated visual angle according to a deformation compensation layer; the motion optimization layer uses a deep reinforcement learning strategy network and combines an adaptive importance sampling strategy to screen the compensated visual angles, and generates a screened candidate viewpoint set; and generating a space-time safety corridor according to the trained space-time diagram convolutional network, carrying out collision risk scoring on the screened candidate viewpoint set according to a safety constraint layer, constructing a multi-target fitness function, and solving the multi-target fitness function to obtain an optimal viewpoint set. The method is suitable for a high-precision visual detection scene, and the real-time performance and robustness of robot viewpoint planning are remarkably improved.