System and method of replanning for coverage of environments with unknown obstacles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing coverage planning approaches for semi-autonomous cleaning devices are inefficient when dealing with unknown static obstacles, as they either require recomputing entire paths, leading to increased coverage time, or result in unnecessary detours when using greedy detour replanning.
Innovation Solution
The OARP-Replan method, which performs near-optimal replanning of coverage paths by solving linear relaxations of mixed-integer linear programs to identify sections of the interrupted path that can be optimally replanned within a given time budget, minimizing deviations from the initial path.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If the robot recomputes the entire coverage path when encountering unknown obstacles, then the coverage path can be optimized, but the coverage time increases due to computational expense and robot stoppages
Solution Approach 1:
The patent segments the coverage path into multiple independent sections or ranks. When an obstacle is detected, only the affected section is replanned rather than the entire path. This segmentation allows the robot to maintain already-completed sections while locally optimizing the blocked section, reducing overall replanning time and computational expense.
Solution Approach 2:
The patent pre-computes multiple alternative coverage paths or ranks before execution. When an obstacle is encountered, the system can switch to a pre-computed alternative path without requiring extensive online computation. This preliminary preparation enables faster response to obstacles while maintaining path optimality.
2Productivity
If the robot uses greedy detour replanning to avoid obstacles, then the replanning is computationally efficient, but unnecessary detours increase the coverage path length
Solution Approach 1:
The patent implements a dynamic replanning strategy that adapts the replanning approach based on the situation. When computational resources allow, the system performs more thorough optimization to minimize detours. When time is critical or obstacles are minor, it uses faster greedy approaches. This dynamic adjustment balances path length and computational efficiency.
Solution Approach 2:
The patent changes the optimization parameters and constraints based on the specific obstacle situation. For small obstacles, it uses parameters that allow quick local adjustments. For large obstacles blocking significant portions of the path, it switches to parameters that optimize for minimal detour distance. This parameter adaptation enables the system to minimize unnecessary path length while maintaining computational efficiency.
Data Source
AI summary
A system and method to replan coverage paths for a robot operating in an environment with initially unknown static obstacles. Existing coverage approaches reduce coverage time by covering along the minimum number of coverage lines (straight-line paths). However, recomputing such paths online can be computationally expensive resulting in robot stoppages that increase coverage time. An alternative is greedy detour replanning, i.e., replanning with minimum deviation from the initial path, which is efficient to compute but may result in unnecessary detours. In this work, an anytime coverage replanning approach named OARP-Replan is proposed that performs near-optimal replans to an interrupted coverage path within a given time budget. This is accomplished by solving linear relaxations of mixed-integer linear programs (MILPs) to identify sections of the interrupted path that can be optimally replanned within the time budget.