Nonlinear model predictive control method applied to visual servo
A nonlinear model and predictive control technology, applied in the field of navigation and control, can solve problems such as correcting navigation deviations, achieve the effects of improving convergence speed, facilitating the solution of optimal solutions, and controlling efficiency advantages
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0068] like figure 1 A nonlinear model predictive control method applied to visual servoing is shown, including the following steps:
[0069] 1) When the four-Mecanum wheel unmanned vehicle passes through the AprilTag code, the pose of the unmanned vehicle is determined according to the image captured by the bottom camera. The specific process is as follows:
[0070] like figure 2 As shown, the AprilTag code is a visual benchmark library that is widely used in robotic systems due to its ability to store information and easy identification. When the four-Mecanum wheel unmanned vehicle moves to the vicinity of the AprilTag code, the camera located at the bottom of the unmanned vehicle can capture the AprilTag code, and then use the findcounters function in the Opencv image processing library to obtain the boundary of the AprilTag code, and then calculate the average of the boundaries. Get the midpoint of the AprilTag and use it as the coordinates of the bottom camera in the A...
Embodiment 2
[0106] The present invention is also applicable to the visual servoing of the differential wheel unmanned vehicle. Unlike the four Mecanum wheel unmanned vehicle, which can move in any direction, the two power wheels of the differential wheel unmanned vehicle are generally located on the left and right sides of the unmanned vehicle site. side, respectively apply different rotational speeds to the two wheels to achieve the steering of the ground. like Figure 4 As shown, the clockwise rotation is set to a square, and its kinematic model is as follows:
[0107]
[0108] where θ is the heading angle of the unmanned vehicle, is the derivative of the position and attitude of the unmanned vehicle, v is the straight speed of the unmanned vehicle with differential wheels, and ω is the angular velocity of the unmanned vehicle with differential wheels. The distance difference between the unmanned vehicle in the world coordinate system and the target point defined by the four-Mecan...
Embodiment 3
[0114] In some industrial scenarios, the unmanned vehicle needs to move from one target point to another. For this reason, we design the current map to consist of multiple nodes, and each node has a corresponding AprilTag code to record its location information. , when the unmanned vehicle starts from the starting node and passes through each node, the under-vehicle camera can obtain its own position information, judge the direction of the next node in the established route, and use the AprilTag code to realize the steering and node of the unmanned vehicle. movement between.
[0115] Image 6 It shows the distribution of AprilTag codes in a 4×4 meter map, where the distance between the codes is 2 meters, and the unmanned vehicle needs to move from the starting node 3 to the target node 7. In this process, when the unmanned vehicle detects the AprilTag code, in addition to using the visual servoing and nonlinear model predictive control algorithm to control the unmanned vehicl...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


