Robot Target Selection Display for Predictable Autonomous Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous robots may act against user intentions due to misinterpretation of instructions or surroundings, making it difficult for users to predict their behavior.
Innovation Solution
A control system that includes an interface to receive recognition information from the robot, displaying candidate target objects with associated scores on a display, allowing users to provide feedback and select preferred actions, thereby enhancing prediction and control of the robot's behavior.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If the autonomous robot acts autonomously according to user instructions, then the robot can perform tasks independently, but the user cannot predict the robot's behavior accurately
Solution Approach 1:
The system displays candidate target objects with scores to the user, who then provides feedback by selecting the actual target. This feedback loop allows the robot to learn from user corrections and improve its target recognition accuracy over time, resolving the contradiction between autonomous operation and behavior predictability.
Solution Approach 2:
The robot performs preliminary recognition of candidate target objects and presents them to the user before final selection. This preliminary action allows the user to predict and correct the robot's behavior in advance, maintaining autonomous operation while improving predictability.
2Productivity
If the robot selects target objects autonomously based on its judgment, then task execution speed increases, but accuracy of task completion decreases
Solution Approach 1:
The system calculates scores for multiple candidate target objects and displays them to the user for verification. The user's selection provides feedback that confirms or corrects the robot's autonomous judgment, ensuring both speed and accuracy in target identification.
Solution Approach 2:
Instead of selecting a single target autonomously, the robot performs excessive recognition of multiple candidate targets and presents them to the user. This partial automation approach ensures higher accuracy while maintaining reasonable execution speed.
3Ease of operation
If the robot interprets user instructions autonomously, then ease of operation increases, but reliability of task completion decreases
Solution Approach 1:
The system displays recognized candidate targets with confidence scores to the user, who then provides feedback by selecting the correct target. This feedback mechanism ensures that autonomous interpretation of simple instructions leads to reliable task completion.
Solution Approach 2:
The display interface acts as an intermediary between the user's simple instruction and the robot's autonomous execution. It shows candidate targets and their scores, allowing the user to verify and correct the robot's interpretation before execution, thereby improving reliability.
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, said 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.