Service Robot User Identification via Visual Service Tokens

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing robots lack the ability to identify users who have requested services and provide tailored services to them, relying solely on pre-set routes and server commands without user recognition.

Innovation Solution

A robot equipped with an input interface, camera, and processor that uses an object recognition model based on an artificial neural network to identify users through video analysis and perform tasks corresponding to service requests.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If the robot moves according to a set route or control server settings, then the robot can provide guide service, but the robot cannot identify users who have requested service or provide tailored services to them

Engineering Contradiction:
Improveservice customization capabilityVSAvoidsystem structure
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system is divided into multiple functional modules: a user identification module that analyzes video to detect service identifiers, a service information acquisition module that retrieves data based on identified identifiers, and a task execution module that performs customized services. This segmentation allows the robot to add user identification capabilities without completely redesigning the system architecture.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a service identifier as an intermediary element that bridges the user and the robot. The identifier (such as a QR code or RFID tag) carries service information that the robot can read and process, enabling customized service delivery without requiring complex direct user-robot communication systems.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If the robot uses video analysis with object recognition model to identify users, then user identification accuracy is enhanced, but processing time and computational resources increase

Engineering Contradiction:
Improveuser identification accuracyVSAvoididentification processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The object recognition model is pre-trained with service identifier data before deployment. When a user presents a service identifier, the model can quickly match it against stored patterns without requiring extensive real-time processing. This preliminary preparation significantly reduces identification time while maintaining high accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The video analysis focuses specifically on detecting service identifiers rather than performing comprehensive user authentication. The system processes only the necessary visual information (the identifier itself) rather than analyzing all user characteristics, reducing computational overhead while achieving the required identification accuracy.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS12050464B2Robot paired with user to perform specific task
Publication Date: 2024.07.30 LG ELECTRONICS INC
  • US12050464B2 patent drawing
  • US12050464B2 patent drawing
  • US12050464B2 patent drawing

AI summary

A robot including an input interface configured to receive a service identifier in response to a service request; a camera configured to capture a video of a user who has presented the service identifier; a transceiver configured to receive service information associated with the service identifier; and a processor configured to identify the user who has presented the service identifier from the video using an artificial neural network based learning model; and in response to successfully identifying the user, perform a task corresponding to the service request for the user based on the service information.