Robot Autonomy Authoring With Online Mapping and Behavior Trees
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for robot autonomy applications require separate processes for environmental mapping and behavior authoring, which are time-consuming and prone to errors due to the need for accurate interpretation of environmental maps.
Innovation Solution
An online authoring system that allows simultaneous environmental mapping and action recording, using sensor data to generate an environmental map and a behavior tree that navigates the robot to target locations and performs specified actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If separate processes are used for environmental mapping and behavior authoring, then each process can be performed independently, but the overall time consumption increases and error probability increases due to the need for accurate interpretation of environmental maps
Solution Approach 1:
The patent combines environmental mapping and behavior authoring into a single integrated online authoring process. The system simultaneously performs SLAM to generate environmental maps while recording user actions and automatically generating behavior trees, eliminating the need for separate offline processing steps and reducing both time consumption and error probability.
Solution Approach 2:
The system automatically generates behavior trees from recorded user actions without requiring manual interpretation of environmental maps. The automated behavior tree generation engine converts recorded actions into executable navigation and task sequences, reducing human error and time investment in the authoring process.
2Measurement precision
If manual interpretation of environmental maps is required for behavior authoring, then precise control can be achieved, but the complexity of the authoring process increases and time consumption increases
Solution Approach 1:
The system automatically generates behavior trees from recorded user actions without requiring manual interpretation of environmental maps. The automated behavior tree generation engine converts recorded actions into executable navigation and task sequences, reducing human error and time investment in the authoring process.
Solution Approach 2:
The patent introduces an automated behavior tree generation engine as an intermediary between user actions and robot execution. This engine automatically translates recorded actions into structured behavior trees with proper navigation and task sequences, eliminating the need for users to manually interpret complex environmental maps while maintaining precision.
3Adaptability or versatility
If offline behavior authoring is performed after environmental mapping, then comprehensive behavior planning can be achieved, but the overall mission preparation time increases
Solution Approach 1:
The patent combines environmental mapping and behavior authoring into a single integrated online authoring process. The system simultaneously performs SLAM to generate environmental maps while recording user actions and automatically generating behavior trees, eliminating the need for separate offline processing steps and reducing both time consumption and error probability.
Solution Approach 2:
The system performs behavior authoring continuously during the environmental mapping process rather than requiring a separate offline phase. Users can record actions and generate behavior trees in real-time as the robot explores the environment, maintaining continuous productive work throughout the mapping process.
Data Source
AI summary
A method for online authoring of robot autonomy applications includes receiving sensor data of an environment about a robot while the robot traverses through the environment. The method also includes generating an environmental map representative of the environment about the robot based on the received sensor data. While generating the environmental map, the method includes localizing a current position of the robot within the environmental map and, at each corresponding target location of one or more target locations within the environment, recording a respective action for the robot to perform. The method also includes generating a behavior tree for navigating the robot to each corresponding target location and controlling the robot to perform the respective action at each corresponding target location within the environment during a future mission when the current position of the robot within the environmental map reaches the corresponding target location.


