4 results about "Terminal cost" patented technology

This invention discloses an autonomous unloading method, device, and medium for a loader, belonging to the field of loader unloading technology. The method includes: determining a feasible solution space for unloading trajectory planning based on the spatial constraints of the unloading target area and the kinematic model of the loader's working device; constructing a stage cost function and a terminal cost function for the unloading process based on a dynamic programming algorithm and the feasible solution space, and determining the globally optimal unloading trajectory; determining a mathematical model of the electro-hydraulic servo system based on the electro-hydraulic drive architecture of the proportional servo valve-controlled hydraulic cylinder of the loader's working device; constructing displacement, velocity, and acceleration tracking errors based on the globally optimal unloading trajectory and hydraulic cylinder extension / retraction data from the state acquisition module, determining a trajectory tracking error model; determining a nonlinear integral sliding surface function based on the trajectory tracking error model; and determining a control instruction set based on the nonlinear integral sliding surface function through equivalent control terms and switching control terms with chatter suppression.

The invention provides a terminal strategy optimization heuristic MPC control method and system considering interference, and relates to the technical field of control, and the method comprises the steps: constructing a discrete time nonlinear kinetic model containing time-varying interference; a disturbance predictor is introduced, and disturbance model parameters are obtained through historical disturbance data fitting; using a disturbance predictor to predict disturbance of a future step; obtaining an optimal parameter of the parameterized terminal cost function through supervised learning, and obtaining an optimal terminal cost function; constructing a terminal model predictive control MPC framework, forming a corresponding terminal model predictive control MPC optimization problem, and embedding the optimal terminal cost function into the terminal MPC framework to replace the traditional terminal cost; and solving a constrained terminal MPC optimization problem, and outputting a control law to complete online control. The method can adapt to a time-varying interference scene, reduces interference and control errors caused by various uncertain factors, and improves the stability, accuracy and reliability of online control of the nonlinear unmanned system.

The invention discloses a large model and terminal cost inspired unmanned equipment control method, device and equipment, and relates to the technical field of unmanned equipment motion control. According to the method, a large language model (namely a control strategy large model) is utilized, control track generation driven by task semantics is realized in an unmanned equipment control scene, terminal cost is subjected to micronized expression, disturbance adaptive optimization solution is carried out, a control correction amount is obtained, and the control correction amount and baseline control are superposed and output, so that the control precision is improved. According to the method, semantic planning and real-time constraint optimization collaborative closed-loop control is realized, so that the global decision intelligence and the environmental adaptation robustness are improved while the safety and the real-time performance are ensured.

The application belongs to the technical field of robot control, and discloses a foot-arm multi-task control method and system based on time-varying terminal cost, which comprises the following steps: generating a whole-body reference trajectory of a robot offline, and precomputing a time-varying terminal cost matrix sequence based on the reference trajectory; constructing and solving a nonlinear model predictive control optimization problem based on the time-varying terminal cost matrix sequence, so as to obtain an optimized sequence of system states and control inputs; inputting the optimized sequence as a reference instruction into a hierarchical whole-body controller to optimize multi-task priorities, generating joint control instructions, and outputting the joint control instructions to a robot actuator. The application effectively alleviates the "short-sighted" problem of traditional NMPC in long-term tasks, and significantly improves the operation accuracy of the robot.