Manipulator Path Planning With Space Compression and Curve Smoothing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing manipulator path planning methods face challenges such as high computational cost in high-dimensional spaces, low convergence speed, high memory requirements, and the generation of non-smooth paths, particularly in complex spaces for guided measurement tasks.
Innovation Solution
A manipulator execution path planning method that involves determining a measurement space, identifying obstructed and free spaces, constructing a space compression model, and using reinforcement learning to find the shortest path, followed by high-order curve fitting for smoothing and inverse kinematics for joint angle calculation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If graph search method is used for path planning, then path optimization in two-dimensional space is achieved, but calculation cost is exponentially increased in high-dimensional space
Solution Approach 1:
The patent segments the high-dimensional measurement space into multiple subspaces by selecting key dimensions for compression. This allows the path planning algorithm to operate efficiently in reduced-dimensional subspaces while still achieving comprehensive path optimization, thereby resolving the contradiction between path optimization quality and computational efficiency in high-dimensional spaces.
Solution Approach 2:
The patent applies dimensionality reduction by compressing the measurement space from high-dimensional to lower-dimensional subspaces. This transformation maintains the essential path planning information while reducing the computational burden, enabling efficient path optimization without exponential calculation costs associated with full high-dimensional search.
2Manufacturing precision
If intelligent optimization method is used for path planning, then learning-based optimization is achieved, but convergence speed is reduced and memory requirements are increased
Solution Approach 1:
The patent performs preliminary space compression and dimensionality reduction before applying path planning algorithms. By pre-processing the measurement space to eliminate redundant dimensions, the subsequent optimization process operates on a reduced problem size, significantly improving convergence speed while maintaining optimization quality and reducing memory requirements.
Solution Approach 2:
The patent extracts and removes redundant dimensions from the high-dimensional measurement space, keeping only the essential dimensions needed for path planning. This extraction process eliminates unnecessary computational overhead, allowing the intelligent optimization method to converge faster with reduced memory usage while maintaining path optimization effectiveness.
3Adaptability or versatility
If sampling-based planning method is used for path planning, then suitability for high-degree-of-freedom problems is achieved, but path smoothness and sampling uniformity are compromised
Solution Approach 1:
The patent applies high-order curve fitting to smooth the sampled path points, transforming the non-smooth piecewise linear paths into smooth curved trajectories. This curvature application maintains the adaptability of sampling-based methods for high-degree-of-freedom problems while significantly improving path smoothness and quality for guided measurement tasks.
Solution Approach 2:
The patent changes the parameter representation of the path by applying high-order polynomial fitting to the sampled points. This parameter transformation converts the discrete, non-uniform sampling results into a continuous, smooth path representation, improving path quality while preserving the versatility of sampling-based planning for complex high-dimensional spaces.
Data Source
AI summary
A manipulator execution path planning method for a complex space guided measurement task, includes: determining a measurement space of a manipulator and a starting point and a target point of a path; determining an obstructed space and a free space of the measurement space and a proportion of the obstructed space in the measurement space using a collision algorithm, and classifying and constructing a space compression model according to the proportion of the obstructed space in the measurement space to compress the measurement space and remove an invalid space; finding candidate paths for connecting the starting point and the target point by constructing an adjacent node tree connected topology network; finding a required path in the candidate paths, and performing high-order curve fitting to obtain a final path; discretizing the final path, and solving joint angles of the manipulator to obtain a joint track.