Robot high-performance track automatic generation method combined with multistage optimization model

Abstract

The invention relates to a Robot high-performance track automatic generation method combined with a multistage optimization model. The method comprises the following steps: S1, determining coordinates of track key points and a track curve model between two adjacent track key points; s2, building a performance index library, and constructing a multi-stage optimization model; s3, obtaining a weight factor of the performance index, and determining an optimization objective function; s4, based on the optimization objective function, adopting an improved genetic particle swarm hybrid optimization algorithm to optimize the motion time of each section of trajectory; and S5, determining trajectory curve model parameters based on the trajectory curve model and the motion time of each section of trajectory, and obtaining each section of trajectory curve. Compared with the prior art, the track generation method can meet the user-defined performance requirement of a user, and absolute smoothness and continuity of the track are guaranteed.

Description

technical field [0001] The invention relates to a robot trajectory planning method, in particular to a robot high-performance trajectory automatic generation method combined with a multi-level optimization model. Background technique [0002] As an important part of robot motion control, trajectory planning determines the performance of the robot in actual production and application. Especially for industrial robots, a high-performance trajectory can not only ensure the smooth and efficient movement of the robot, but also meet user needs. Improving product quality is also important. In addition, with the continuous promotion of robot applications, it is of great significance to provide an automatic generation method for high-performance trajectories according to the performance requirements of users in different scenarios. [0003] At present, there are two general robot trajectory planning methods, one is conventional trajectory planning, it is mainly based on the preset t...

AI Technical Summary

Problems solved by technology

This method is currently widely used because it is intuitive and simple, but it has several key shortcomings: First, in actual production and use, for multi-point planning, it will cause cumbersome parameter setting, poor user interaction, and cannot consider global performance. , resulting in low efficiency; the other is artificially setting the motion parameters, which cannot give full play to the motion performance of the robot, let alone guarantee the comprehensive performance requirements of the trajectory, which obviously does not match the different trajectory performance that may be required by different tasks today.

Another method is to combine the optimized iterative algorithm to automatically generate trajectories from the perspective of performance index optimization. Compared with conventional planning, this method has lower real-time performance, but it can effectively avoid cumbersome parameter setting and performance quantification problems. In today's intelligent However, there are two problems in the current research and application of this method: one is that most of the current methods are only aimed at specific optimization goals, and cannot be customized by users according to their own task requirements, and they lack certain adjustment and adaptation. The other is that the generality and efficiency of the algorithm are insufficient, and the convergence speed and iteration time need to be further improved

Images