Robot Autonomy Authoring With SLAM-Based Action Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for mapping environments and setting mission parameters for robots require separate steps of mapping and authoring behavior steps, which are time-consuming and prone to errors due to the complexity of interpreting topographical maps.
Innovation Solution
An online authoring system that allows users to simultaneously map an environment and record actions using simultaneous localization and mapping (SLAM), generating a behavior tree by selecting actions from a playbook and combining prebuilt behavior tree portions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If separate steps of mapping and authoring behavior steps are used, then mapping accuracy can be maintained, but time consumption increases and error probability increases
Solution Approach 1:
The patent combines the mapping process and behavior authoring process into a single integrated online authoring system. While the robot performs SLAM mapping of the environment, the system simultaneously captures sensor data, identifies target locations, and records user-defined actions to create behavior trees. This merging of previously separate operations eliminates the need for sequential processing, thereby reducing time consumption while maintaining mapping accuracy through continuous SLAM operations.
Solution Approach 2:
The system performs preliminary action by pre-recording user actions and defining behavior rules during the mapping process itself, before actual mission execution. The online authoring system captures sensor data and user inputs in real-time, pre-processing behavioral information alongside environmental mapping. This preliminary capture of action data during mapping eliminates the need for subsequent separate authoring steps, reducing overall time while preserving mapping precision.
2Ease of operation
If separate steps of mapping and authoring behavior steps are used, then detailed behavior control can be achieved, but error probability increases due to complexity of interpreting topographical maps
Solution Approach 1:
The patent introduces an intermediary online authoring system that mediates between the raw sensor data/topographical map and the final behavior execution. Instead of requiring users to directly interpret complex topographical maps and manually author behaviors, the system captures sensor data during mapping, automatically processes this data to identify target locations, and provides a simplified interface for users to record actions. This intermediary processing layer reduces errors by eliminating complex manual interpretation steps while preserving detailed behavior control capabilities.
Solution Approach 2:
The system creates a copy of the environmental information in the form of recorded sensor data and generated behavior trees during the mapping process. Rather than requiring users to work directly with the complex topographical map structure, the online authoring system generates simplified behavioral representations (behavior trees) that copy essential navigation and action information. This copying process transforms complex spatial data into easier-to-interpret behavioral instructions, reducing errors while maintaining control precision.
3Productivity
If simultaneous mapping and behavior tree generation is performed, then time efficiency improves, but system complexity increases
Solution Approach 1:
The online authoring system performs multiple functions simultaneously: it conducts SLAM mapping, captures sensor data, identifies target locations, records user actions, and generates behavior trees all within a single integrated system. This multi-functionality consolidates what would otherwise require multiple separate systems or sequential processes into one unified platform, achieving time efficiency through parallel operations while managing complexity through integrated architecture rather than multiple independent components.
Solution Approach 2:
While performing simultaneous operations, the system segments the complex task into distinct functional modules: SLAM mapping module, sensor data capture module, target location identification module, action recording module, and behavior tree generation module. Each module handles a specific aspect of the simultaneous process, allowing the system to achieve high productivity through parallel processing while managing complexity through modular design. The segmentation enables independent optimization of each function while maintaining overall system integration.
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.