Robot Auction Scheduling With Automaton-Based Temporal Task Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods lack efficient algorithms for coordinating robots in multi-agent systems to solve tasks with time-dependent specifications in non-deterministic environments, particularly under uncertainties and temporal dependencies.
Innovation Solution
A method using a deterministic finite automaton to assign subtasks to robots through a decentralized auction scheme, where robots determine options based on cost values that consider time and probability, allowing for efficient distribution and adaptation to environmental uncertainties.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional planning methods are used for individual robots, then task completion is achieved, but coordination efficiency and adaptability to uncertainties deteriorate
Solution Approach 1:
The patent segments the task specification into subtasks corresponding to state transitions in a deterministic finite automaton. Each robot independently evaluates and bids on specific subtasks rather than planning entire trajectories, enabling scalable coordination while maintaining adaptability through localized decision-making
Solution Approach 2:
The patent implements continuous feedback loops where robots monitor system state, receive updates from other robots about completed subtasks, and dynamically adjust their plans. This allows the system to adapt to uncertainties and changing environmental conditions while maintaining overall task coordination
2Reliability
If centralized coordination methods are used, then task coordination is achieved, but system complexity and computational burden increase
Solution Approach 1:
Each robot independently evaluates subtasks, determines its own capability and cost, and places bids without requiring centralized arbitration. The auction mechanism itself is simple and rule-based, allowing robots to self-organize and coordinate tasks autonomously, reducing overall system complexity
Solution Approach 2:
The patent creates an equipotential coordination environment where all robots operate under the same auction rules and have equal access to subtask information. This symmetric, rule-based approach simplifies coordination by eliminating the need for hierarchical control structures or complex negotiation protocols
3Adaptability or versatility
If probabilistic planning is used to handle uncertainties, then adaptability improves, but computational complexity and planning time increase
Solution Approach 1:
The patent segments the complex probabilistic planning problem into smaller, independent subtasks corresponding to individual state transitions. Each robot only needs to evaluate probabilities for its own subtasks rather than computing full probabilistic trajectories, dramatically reducing computational complexity while maintaining adaptability
Solution Approach 2:
The patent changes the parameter representation from full probabilistic trajectories to simplified cost values that capture essential uncertainty information. Each robot computes a single cost value per subtask that incorporates probability assessments, transforming complex probabilistic reasoning into tractable parameter optimization
Data Source
AI summary
A method for operating a multi-agent system having a plurality of robots. Each of the robots execute the following method cyclically until a target system state is achieved: starting from an instantaneous system state, determining possible options where progress is made along a path of system states in a predefined, deterministic finite automaton; the options defining actions through which a transition from a current to a subsequent system state can be achieved; determining a cost value for each of the possible options to carry out an action specified by the option; performing an auction, the cost values ascertained for each option being considered by each of the remaining robots; and executing an action, which corresponds to one of the options, as a function of all of the cost values which are determined or received for the respective option.