Robot Target Selection Display With Score-Based User Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous robots may act against the user's intention due to misinterpretation of instructions or surroundings, making it difficult for users to predict their behavior.
Innovation Solution
A system that includes an interface to receive recognition information from the autonomous robot, displaying candidate target objects with associated scores, and allowing user input to guide the robot's behavior through an overhead space diagram and object images, enabling user feedback and score adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If the autonomous robot autonomously selects target objects based on its own judgment, then the robot can operate independently without user intervention, but the robot may act against the user's intention due to misinterpretation of instructions or surroundings
Solution Approach 1:
The system displays candidate target objects with scores to the user, who then provides feedback by selecting the actual target object. This feedback loop allows the robot to learn from user corrections and improve its target selection accuracy over time, resolving the contradiction between autonomous operation and behavior predictability.
Solution Approach 2:
The robot performs preliminary actions by identifying and ranking candidate target objects before final selection. By presenting these candidates with scores to the user for approval, the system ensures user intention alignment while maintaining efficient autonomous operation.
2Speed
If the autonomous robot autonomously selects target objects without user feedback, then the operation speed is fast, but the accuracy of target selection may be low due to misinterpretation
Solution Approach 1:
The robot performs partial user interaction by displaying only the top candidate target objects with scores rather than requiring full manual selection. This partial feedback mechanism maintains high operation speed while improving target identification accuracy through user confirmation of the most likely candidates.
3Loss of information
If the system displays detailed information about candidate target objects to improve user prediction, then the user can better understand robot behavior, but the interface complexity increases
Solution Approach 1:
The system applies different levels of information display to different candidate target objects based on their scores. High-scoring candidates receive more detailed presentation, while lower-scoring ones receive minimal display. This local differentiation maintains information transparency while reducing overall interface complexity.
Data Source
AI summary
A control system, method and computer program product cooperate to assist control for an autonomous robot. An interface receives recognition information from an autonomous robot, the recognition information including candidate target objects to interact with the autonomous robot. A display control unit causes a display image to be displayed on a display of candidate target objects, wherein at least two of the candidate target objects are displayed with an associated indication of a target object score.


