Robot Mission Behavior Trees for Extensible Autonomy Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomy systems for robots are limited in extensibility and adaptability, as they are typically configured to address only one aspect of robot operations, restricting their ability to support the addition of new modules and rapid adaptation to new platforms.
Innovation Solution
A behavior tree framework is used to model and execute missions, decoupling mission planning from execution and enabling flexible, adaptable autonomy through a switch node, trigger node, and action nodes, with a leaf node library for handling contingency events.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If existing autonomy systems are configured to address only one aspect of robot operations, then the system design can be simplified and focused, but the extensibility and adaptability to new modules and platforms are limited
Solution Approach 1:
The autonomy system is segmented into distinct behavioral modules (e.g., navigation, manipulation, sensing) that can be independently developed, tested, and combined. Each module is encapsulated as a reusable component that can be integrated into different mission configurations without redesigning the entire system.
Solution Approach 2:
The system employs universal interface standards and common communication protocols that allow different behavioral modules to work together across multiple robot platforms. This enables the same autonomy framework to support diverse modules and adapt to new platforms through parameterization rather than structural modification.
2Device complexity
If existing autonomy systems are configured to address only one aspect of robot operations, then the system design can be simplified and focused, but the adaptability to new platforms through parameterization is limited
Solution Approach 1:
The system uses parameterized configurations where platform-specific characteristics (dimensions, capabilities, sensor locations) are defined through adjustable parameters rather than hard-coded structures. This allows the same autonomy software to adapt to different robot platforms by simply changing parameter values, maintaining low design complexity while achieving high adaptability.
3Adaptability or versatility
If a behavior tree framework is used to decouple mission planning from execution, then the system becomes more extensible and adaptable, but the system complexity increases
Solution Approach 1:
The behavior tree is segmented into hierarchical levels (mission-level, task-level, action-level) that separate high-level planning from low-level execution. This segmentation allows independent development and modification of planning and execution components without increasing overall system complexity, as each level operates with well-defined interfaces.
Solution Approach 2:
The behavior tree acts as an intermediary layer between mission planning and execution, translating high-level mission objectives into actionable tasks. This mediator decouples the planning and execution processes, allowing each to be optimized independently while maintaining clear communication through standardized interfaces.
Data Source
AI summary
A method is provided for causing one or more robots to execute a mission. The method includes determining a behavior tree in which the mission is modeled, and causing the one or more robots to execute the mission using the behavior tree and a leaf node library. The behavior tree is expressed as a directed tree of nodes including a switch node, a trigger node representing a selected task, and action nodes representing others of the tasks. The switch node is connected to the trigger node and the action nodes in a parent-child relationship in which the trigger node and the action nodes are children of the switch node. The trigger node is a first of the children that, when ticked by the switch node, returns an identifier of one of the action nodes to trigger the switch node to next tick the one of the action nodes.