Robot Mission Task Graphs for Contingency-Adaptive Execution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomy systems for robots are limited in extensibility as they are typically configured to address only one aspect of robot operation, such as mission planning or execution, lacking the ability to handle multiple aspects simultaneously and adapt to contingency events effectively.
Innovation Solution
A system that uses a task graph to decouple mission planning from execution, allowing robots to execute maneuvers through a task library, which includes nominal and alternate tasks, and can adapt to contingency events by transitioning between task nodes based on detected events, ensuring continuous mission feasibility.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If existing autonomy systems are configured to address only one aspect of robot operation (mission planning or execution), then the system design can be focused and simplified, but the extensibility and ability to handle multiple aspects simultaneously are limited
Solution Approach 1:
The autonomy system is segmented into distinct modules: a mission planning module that generates task graphs, a task library containing reusable task definitions, and an execution module that processes tasks. This segmentation allows each module to be developed and optimized independently while maintaining overall system extensibility through the standardized task graph interface.
Solution Approach 2:
The task graph structure serves as a universal interface that can represent multiple aspects of robot operation including navigation, manipulation, sensor operations, and contingency handling. By using a standardized task graph format with configurable parameters, the system can address diverse operational requirements through a single unified framework rather than separate specialized systems.
2Adaptability or versatility
If a robot system uses a unified autonomy framework to handle multiple aspects of operation, then extensibility and adaptability improve, but the complexity of system design and implementation increases
Solution Approach 1:
The system performs preliminary action by pre-defining a comprehensive task library containing reusable task definitions for common robot operations including nominal tasks and contingency response tasks. These tasks are prepared in advance with all necessary parameters and logic, allowing the execution module to handle contingency events by selecting and configuring pre-existing tasks rather than creating new logic during execution.
Solution Approach 2:
The task graph serves as an intermediary structure that bridges mission planning and execution. It translates high-level mission objectives into structured task sequences that can be processed by the execution module. This intermediary representation simplifies the interface between planning and execution while maintaining the ability to handle complex operational requirements through standardized task definitions.
3Productivity
If mission planning and execution are coupled in existing systems, then the system architecture is simpler, but the ability to separate predictive decision-making from real-time execution is reduced
Solution Approach 1:
The system extracts the predictive decision-making component into a separate mission planning module that generates task graphs before execution. This extracted planning component operates independently from the real-time execution module, allowing predictive decisions about task sequences and parameters to be made in advance while the execution module focuses on efficient real-time task processing and contingency response.
Solution Approach 2:
The decoupled architecture maintains continuity of useful action by ensuring that the task graph produced by the planning module can be continuously processed by the execution module without interruption. The standardized task graph format ensures seamless transition from planning to execution, and the execution module can continuously process tasks while independently handling real-time contingencies without requiring re-planning.
Data Source
AI summary
A method and corresponding apparatus and computer-readable storage medium are provided for causing one or more robots to execute a mission. The method includes identifying the mission including a nominal sequence of selected tasks that are executable to cause the one or more robots to execute maneuvers to achieve a mission objective. The method includes determining a task graph in which the mission is modeled. The task graph is expressed as a directed graph and includes selected task nodes representing the selected tasks that are connected by edges representing transitions between the selected tasks. The method also includes causing the one or more robots to execute the mission using the task graph and a task library of tasks including a selected task executable to cause the one or more robots to execute a maneuver.