Robot Path Planning With Weighted Obstacle Distance Costs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robot path planning methods require expanding obstacles to ensure safety, leading to oversized obstacle distances and sub-optimal path planning.
Innovation Solution
A deterministic method for robot path planning that computes a minimum distance to obstacles without expanding them, using a weighting parameter to balance joint angle costs and obstacle-distance costs in the cost function.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If obstacles are expanded to ensure safety distance, then robot safety is improved, but obstacle size becomes oversized and path optimality deteriorates
Solution Approach 1:
The cost function is designed in advance to incorporate both joint angle costs and obstacle-distance costs with weighted parameters. By pre-defining the cost function structure with appropriate weighting, the system achieves safety without requiring obstacle expansion, thus avoiding the sub-optimal paths caused by oversized obstacles.
Solution Approach 2:
The patent introduces weighting parameters (λ1 and λ2) that balance the joint angle cost and obstacle-distance cost in the total cost function. By adjusting these parameters, the system can dynamically control the trade-off between safety margins and path optimality, eliminating the need for fixed obstacle expansion while maintaining robot safety.
2Stability of the object's composition
If deterministic methods are used to minimize cost function, then path fixedness is improved, but computational complexity increases
Solution Approach 1:
The cost function is segmented into distinct components: joint angle cost (weighted by λ1) and obstacle-distance cost (weighted by λ2). This segmentation allows the deterministic optimization to process manageable sub-components separately, reducing overall computational complexity while maintaining path fixedness through systematic minimization of the total cost.
Data Source
AI summary
The present teaching relates to a method and system for path planning. A target is tracked via one or more sensors. Information of a desired pose of an end-effector with respect to the target and a current pose of the end-effector is obtained. Also, a minimum distance permitted between an arm including the end-effector and each of at least one obstacle identified between the current pose of the end-effector and the target is obtained. A weighting factor previously learned is retrieved and a cost based on a cost function is computed in accordance with a weighted smallest distance between the arm including the end-effector and the at least one obstacle, wherein the smallest distance is weighted by the weighting factor. A trajectory is computed from the current pose to the desired pose by minimizing the cost function.