39results about How to "Improve the efficiency of performing tasks" patented technology

The present application provides a charging method, an electronic device, and a computer storage medium. The method includes: determining first power information and second power information, where the first power information is used to represent the power required by the electronic device to perform a target task , the second power information is used to represent the remaining power of the electronic device; based on the first power information and the second power information, it is determined whether to control the electronic device to charge.

The invention discloses a method and a device for preventing robot collisions, and relates to the technical field of computers. A specific implementation of the method includes: generating a set of reference points from the starting point to the target point through path planning, and obtaining the identification of the interference area corresponding to the reference point of the set of reference points; according to the identification of the interference area corresponding to the reference point, the set of reference points Carry out splitting, and set the interference area identification for the multiple sub-routes obtained from the splitting; lock the corresponding interference area according to the interference area identification of the sub-routes, and issue routing instructions after the locking is successful, so that the robot enters the interference area; among them, the interference The area is obtained by dividing the reference points according to the distribution of the reference points in the target area. The method divides the interference area in advance, and sets the interference area identification for the sub-routing, so as to lock the corresponding interference area according to the interference area identification of the sub-routing, so as to ensure that only one robot can enter the interference area, and avoid robot collision.

The present invention provides a DQN-based method for autonomously generating a maneuvering strategy of an unmanned aerial vehicle, which respectively establishes a three-degree-of-freedom motion model of the unmanned aerial vehicle, a maneuvering control model of the unmanned aerial vehicle, a three-dimensional model of a reference terrain and a three-dimensional model of a mountain peak; The value of the influence degree of terrain obstacles in the position; build the evaluation network and the target network, and train the evaluation network; use the training result as the UAV flight control outer loop controller to control the two-way overload of the UAV and the speed of the UAV Tilt angle. The invention combines the deep reinforcement learning method with the guidance and control maneuvering strategy of the UAV, conducts learning and training in an offline simulation environment, and then implements practical application after meeting the requirements, which greatly enhances the UAV's ability to perform tasks. Autonomy, which improves the efficiency of UAVs in performing tasks.

The invention provides a DDPG-based autonomous guidance and control method for an unmanned aerial vehicle, which respectively establishes a three-degree-of-freedom motion model of the unmanned aerial vehicle, a maneuvering control model of the unmanned aerial vehicle, a three-dimensional model of a reference terrain and a three-dimensional model of a mountain peak; calculates the current position of the unmanned aerial vehicle The value of the degree of influence of terrain obstacles under the control system; build the evaluation network, the strategy network and the corresponding target network, and train the evaluation network and the strategy network; use the training result as the UAV flight control outer loop controller to control the two UAVs. Tilt angle to overload and drone speed. The invention combines the deep reinforcement learning method with the guidance and control of the unmanned aerial vehicle, conducts learning and training in an offline simulation environment, and then implements practical application after meeting the requirements, which greatly enhances the autonomy of the unmanned aerial vehicle in the process of performing tasks, and improves the the efficiency of the UAV's mission.

The invention discloses an AGV-based control method, which comprises the steps of acquiring task information corresponding to a task request upon receiving the task request; sorting loading points corresponding to each piece of the loading point information to obtain a first sequence of loading task stations corresponding to the loading points; obtaining a second sequence of discharging task stations corresponding to various pieces of discharging point information; and controlling a target AGV corresponding to the task request to execute a loading task corresponding to the loading point information according to the first sequence, and controlling the target AGV to execute a discharging task corresponding to the discharging point information according to the second sequence when the loading task is completed. The invention also discloses an AGV-based control method apparatus and a computer readable storage medium. According to the invention, multiple tasks can be performed by the same AGV, the utilization rate of the AGV is further increased and the execution task efficiency of the AGV is improved.