Virtual Robot Teaching for Adaptive Mobile Manipulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional robotic systems struggle to perform tasks when the starting point and/or orientations/locations of objects do not align with the programmed or taught task, limiting their adaptability in diverse and unstructured environments.
Innovation Solution
A method and system that use virtual reality to teach robotic devices parameterized behaviors, allowing them to map task images to teaching images and update parameters based on relative transforms, enabling the robotic device to perform tasks regardless of changes in starting position or orientation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If conventional robotic systems are programmed or taught to carry out a task, then the task can be executed with high precision, but the system cannot adapt when starting points or object orientations do not align with the programmed task
Solution Approach 1:
The system changes parameters by computing relative transforms between the actual task image and the taught task image. These transforms adjust the parameters of parameterized behaviors (such as position, orientation, and transformation matrices) to accommodate different starting points and object orientations while maintaining task execution precision
Solution Approach 2:
The system achieves universality by creating a mapping mechanism that works across multiple starting positions and object orientations. The relative transform computation and parameter updating enable the same taught task to be executed universally from any starting position or object orientation, making the robotic system multi-functional rather than task-specific
2Reliability
If robots are programmed for specific tasks with fixed orientations, then task execution is reliable, but the system fails when encountering unique or unstructured environments
Solution Approach 1:
The system uses feedback by capturing the actual task image, comparing it with the taught task image, and computing the relative transform between them. This feedback loop allows the system to detect deviations from the taught task conditions and automatically adjust behavior parameters to maintain reliable task execution in unstructured environments
Solution Approach 2:
The system applies dynamics by making the behavior parameters adjustable and adaptive rather than fixed. The parameterized behaviors can be dynamically updated based on the computed relative transform, allowing the robot to adapt its execution strategy in real-time to match the actual environmental conditions while maintaining task reliability
Data Source
AI summary
A method for controlling a robotic device is presented. The method includes positioning the robotic device within a task environment. The method also includes mapping descriptors of a task image of a scene in the task environment to a teaching image of a teaching environment. The method further includes defining a relative transform between the task image and the teaching image based on the mapping. Furthermore, the method includes updating parameters of a set of parameterized behaviors based on the relative transform to perform a task corresponding to the teaching image.