Robot Autonomy Authoring With SLAM-Based Action Recording
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for robot autonomy require separate steps for mapping environments and authoring behavior, which are time-consuming and require accurate interpretation of topographical maps, making it difficult for users to quickly and efficiently set mission parameters.
Innovation Solution
An online authoring system that allows users to simultaneously create environmental maps and record actions while navigating the robot, using sensor data to generate behavior trees and automate action recording, enabling simultaneous localization and mapping (SLAM) and behavior authorization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If separate steps are used for mapping environments and authoring behavior, then mapping precision and behavior accuracy are improved, but the time required and operational complexity increase significantly
Solution Approach 1:
The patent combines environmental mapping and behavior authoring into a single integrated online process. The robot performs SLAM (simultaneous localization and mapping) while the user simultaneously records actions at detected locations, merging two previously separate offline processes into one concurrent operation, thereby reducing total time without sacrificing precision
Solution Approach 2:
The system performs preliminary environmental mapping and location detection automatically as the robot traverses the environment, preparing the spatial framework in advance. This allows the user to immediately record actions at pre-identified locations without waiting for separate mapping completion, reducing overall task time while maintaining accurate mapping
2Measurement precision
If separate steps are used for mapping environments and authoring behavior, then accurate interpretation of topographical maps is improved, but device complexity and ease of operation deteriorate
Solution Approach 1:
The patent merges environmental mapping and behavior authoring into a unified online system where both processes occur simultaneously. The system integrates SLAM algorithms with action recording functionality, allowing users to interact with the environment directly rather than interpreting separate topographical maps, thereby reducing operational complexity while maintaining accuracy
Solution Approach 2:
The robot autonomously performs environmental mapping and location detection without requiring user intervention for map interpretation. The system automatically identifies locations and presents them to the user for action recording, eliminating the need for users to manually interpret complex topographical maps and reducing operational complexity
3Reliability
If manual behavior tree creation is used, then behavior accuracy is improved, but productivity and time efficiency decrease
Solution Approach 1:
The system automatically records user actions and generates behavior trees without requiring manual creation. As the user interacts with the environment during robot traversal, the system captures these interactions and automatically structures them into behavior trees, maintaining accuracy while dramatically improving productivity by eliminating time-consuming manual authoring
Solution Approach 2:
The system performs preliminary action recording during the environmental traversal phase, capturing all necessary behavioral data before final behavior tree generation. This preliminary capture of action data allows for automatic, accurate behavior tree creation that maintains the reliability of manual authoring while achieving the speed of automated processing
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.