Multi-Robot Task Allocation With Dynamic Runtime Plan Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current multi-robot coordination systems face challenges in making effective dynamic decisions in operating environments, such as warehouses, and are unable to efficiently update plans and task allocation strategies at runtime.
Innovation Solution
A platform that dynamically generates solutions for updating plans and task allocation strategies on heterogeneous autonomous mobile devices by continuously monitoring events, analyzing existing strategies, and deploying new compatible plans and task allocation strategies based on various factors, including new capabilities and historical data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multi-robot coordination systems are designed to handle complex tasks, then the system can perform diverse operations, but the system complexity increases and becomes difficult to maintain
Solution Approach 1:
The system segments coordination logic into individual robot-level decision-making modules. Each robot independently evaluates tasks and allocates resources without requiring centralized control for every decision, reducing overall system complexity while maintaining task diversity capability
Solution Approach 2:
A universal task evaluation framework is implemented that can handle multiple task types through a common decision-making architecture. The system uses standardized interfaces and protocols that work across different robot types and task domains, reducing complexity through reuse rather than custom solutions
2Productivity
If the system makes dynamic runtime decisions, then operational effectiveness improves, but the ability to update plans and strategies efficiently deteriorates
Solution Approach 1:
The system implements dynamic plan structures that can be modified at runtime without complete re-planning. Task allocation strategies are designed to be adaptive, allowing individual task parameters to be adjusted while maintaining overall plan integrity, enabling fast updates without sacrificing operational effectiveness
Solution Approach 2:
The system pre-evaluates multiple task allocation strategies and maintains ready-to-execute plan variants. When runtime changes occur, the system can switch to pre-prepared alternative plans rather than generating new plans from scratch, significantly reducing plan update time
3Reliability
If the system continuously monitors and analyzes existing plans, then optimal performance is achieved, but computational resources and processing time increase
Solution Approach 1:
The system implements partial monitoring that focuses computational resources on critical plan elements and robots currently executing tasks. Instead of continuously analyzing all plans and all robots, the system monitors only those elements that are actively changing or approaching decision points, reducing computational overhead while maintaining performance optimality
Solution Approach 2:
The system uses event-driven feedback mechanisms where monitoring is triggered by specific conditions such as task completion, robot status changes, or performance threshold breaches. This asynchronous monitoring approach reduces continuous computational burden while ensuring plans remain optimized through timely updates
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system and a method to dynamically update plans and task allocation strategies on at least one or more of cloud and plurality of heterogeneous autonomous mobile devices (e.g. robot) has been described. The system or a platform continuously monitors various events internally and externally. The platform analyzes notification or a trigger on whether the existing plans and task allocation strategies need to be updated or replaced. The platform generates solutions depending on various factors and identifies relevant plans and task allocation strategies that may need to be updated. Based on the solutions that are generated, the existing plans and allocated task allocation strategies may be updated or replaced. Once the updation of plans and task allocation strategies are performed, the platform deploys the updated plans and tasks allocation strategies on at least one or more of the cloud and plurality of heterogeneous autonomous mobile devices.