Remote Assistance System for Visually Impaired Users

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing solutions for providing remote assistance to visually or audibly impaired individuals are limited in their ability to offer real-time, independent navigation and task guidance, often relying on human assistants and lacking in integration with advanced technologies like AI and IoT devices.

Innovation Solution

A system comprising a client device with AI capabilities, capable of streaming live video and sensor data to a remote server or live agent, utilizing engines for navigation, identification, and emergency assistance, and providing feedback through audible or haptic means, with features like privacy and local modes for enhanced user control.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If real-time video streaming and AI processing are implemented, then navigation and task guidance accuracy is improved, but device complexity and energy consumption increase

Engineering Contradiction:
Improvenavigation accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system divides functionality between the client device (wearing device with camera and sensors) and the remote server (AI processing). The client captures video and sensor data, while the server performs AI-based scene understanding, object detection, and generates guidance instructions. This segmentation allows high navigation accuracy through advanced AI processing without overloading the client device.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

A remote server acts as an intermediary between the client device and the user. The server receives video and sensor data, processes it through AI engines, and returns guidance instructions. This intermediary enables complex AI processing to be performed remotely, improving navigation accuracy while keeping the client device relatively simple.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Speed

If continuous video streaming is used, then real-time guidance feedback is improved, but network dependency and data usage increase

Engineering Contradiction:
Improvefeedback speedVSAvoidnetwork dependency
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

The system establishes a network connection and begins video streaming before guidance is needed. The client device continuously sends video frames and sensor data to the server, so that when guidance is required, the server already has current information and can provide immediate feedback without waiting for data transmission.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The video streaming operates continuously during guidance sessions, maintaining an ongoing flow of data from the client to the server. This continuous action ensures that the server always has up-to-date information about the user's environment and position, enabling real-time feedback while efficiently utilizing the network connection.

Inventive Principle:
Principle #20Continuity of useful action

3Measurement precision

If multiple sensors and cameras are integrated, then environmental awareness and guidance accuracy are improved, but power consumption increases

Engineering Contradiction:
Improveenvironmental detection accuracyVSAvoidpower consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system combines data from multiple sensors (camera, microphone, accelerometer, GPS) and processes it together through AI algorithms. By merging sensor inputs, the system achieves comprehensive environmental awareness and accurate navigation guidance. The coordinated use of multiple sensors provides redundant information that improves detection accuracy without requiring each sensor to operate at maximum power independently.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3189655B1Computer-implemented method and system for providing remote assistance for visually-impaired users
Publication Date: 2020.02.05 AIRA TECH CORP
  • EP3189655B1 patent drawingFigure 1
  • EP3189655B1 patent drawingFigure 2
  • EP3189655B1 patent drawingFigure 3

AI summary

Techniques and systems are provided for assisting a user through a guidance mode activity. Such a user may be visually or otherwise impaired, or a user requiring help for other reasons. In some embodiments, a client device, held or worn by the user, may comprise a video capture device and several sensors, and may send video data and sensor data to a server. The server may comprise a processor and artificial intelligence. The server may send the video data and sensor data to an agent device. The agent device may provide content for display on an agent interface. An agent may view the agent interface, and assist the user in real time through audio instructions or other feedback.