Object Determination via Iterative Characteristic Inquiry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face difficulties interacting with machines, such as robots, when they are not familiar with the technology, leading to cumbersome interactions and potential abandonment of the technology due to the need for extensive situational description and refinement, especially for non-experts using natural language.
Innovation Solution
A device equipped with user interface, memory, and processing circuitry that interacts with users to determine if a target object is known, and if not, uses characteristic-based inquiries to narrow down potential objects, allowing users to identify objects using natural language characteristics like color, size, and shape, reducing the number of potential targets through iterative questioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If users interact with machines using natural language, then ease of operation improves, but the machine requires extensive situational description and refinement to understand the user's intent
Solution Approach 1:
The machine performs preliminary actions by proactively sensing and identifying potential target objects in the environment before the user completes their request. The system uses sensors to detect objects, pre-processes this information, and prepares candidate objects for matching against the user's natural language input, thereby eliminating the need for users to provide extensive descriptions
Solution Approach 2:
The system implements feedback by presenting the user with a list of candidate objects that match their natural language input, allowing them to confirm or correct the identification. This feedback loop enables the machine to refine its understanding based on user responses, reducing the time needed for iterative refinement while maintaining ease of operation
2Measurement precision
If the machine asks for extensive situational description, then measurement precision of object identification improves, but ease of operation deteriorates
Solution Approach 1:
The machine performs preliminary object identification using sensors and environmental context before the user interaction is complete. By pre-identifying potential target objects and their characteristics, the system reduces the burden on users to provide detailed descriptions while maintaining high identification precision through automated sensing and analysis
Solution Approach 2:
The system performs self-service by automatically sensing, identifying, and filtering potential target objects without requiring user input for basic object characteristics. The machine independently gathers environmental information, processes it to identify candidate objects, and presents these to the user for confirmation, thereby achieving high precision with minimal user effort
Data Source
AI summary
This disclosure pertains to machine object determination based on human interaction. In general, a device such as a robot may be capable of interacting with a person (e.g., user) to select an object. The user may identify the target object for the device, which may determine whether the target object is known. If the device determines that target object is known, the device may confirm the target object to the user. If the device determines that the target object is not known, the device may then determine a group of characteristics for use in determining the object from potential target objects, and may select a characteristic that most substantially reduces a number of potential target objects. After the characteristic is determined, the device may formulate an inquiry to the user utilizing the characteristic. Characteristics may be selected until the device determines the target object and confirms it to the user.