Adaptive Goal Function for Robot Path Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing Rapidly-exploring Random Tree (RRT) algorithm for robot path planning can get stuck in local minima due to an inaccurate goal function, leading to inefficient path generation and increased time in finding an optimal motion path to avoid obstacles.
Innovation Solution
The method involves determining if local minima occur during tree expansion, changing the goal function by adjusting the directional vector between the obstacle and the goal point or the end effector, and selecting a node closest to the new goal point to escape local minima, thereby improving path planning efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the RRT algorithm uses a fixed goal function for tree expansion, then the path planning follows a consistent direction, but the algorithm gets stuck in local minima and cannot find the optimal path
Solution Approach 1:
The patent applies dynamics by making the goal function adaptive rather than fixed. The goal function dynamically changes based on the robot's current state and environmental conditions, allowing the RRT algorithm to escape local minima by adjusting the expansion direction in real-time during path planning
Solution Approach 2:
The patent changes parameters of the goal function including directional vectors and weighting factors based on the robot's position and obstacles. By modifying these parameters dynamically, the algorithm can adapt to different situations and avoid getting trapped in local minima, thereby improving both success rate and efficiency
2Productivity
If the goal function is adjusted to escape local minima, then the path planning efficiency improves, but the complexity of the algorithm increases
Solution Approach 1:
The patent modifies parameters of the existing RRT algorithm rather than fundamentally changing its structure. By adjusting goal function parameters like directional vectors and weights, the patent improves efficiency while maintaining the core algorithmic framework, thus limiting the increase in complexity
Data Source
AI summary
If a manipulator of a robot falls in local minima when expanding a node to generate a path, the manipulator may efficiently escape from local minima by any one of a random escaping method and a goal function changing method or a combination thereof to generate the path. When the solution of inverse kinematics is not obtained due to local minima or when the solution of inverse kinematics is not obtained due to an inaccurate goal function, an optimal motion path to avoid an obstacle may be efficiently searched for. The speed to obtain the solution may be increased and thus the time consumed to search for the optimal motion path may be shortened.