Companion Robot Tracking with Leg Imaging and Inertial Backup

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing follower robots face frequent 'unhooking' issues due to unexpected masking of the operator, especially in crowded or cluttered environments, leading to loss of tracking reference and emergency stops, which is inappropriate for autonomous systems.

Innovation Solution

A companion robot system that uses image analysis of the operator's legs and inertial unit data to maintain tracking, even in transient masking situations, employing a multi-band Wifi router for communication quality optimization and ad-hoc networking between a wearable box and the robot, without requiring human intervention for movement commands.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the robot uses image analysis to track the operator, then tracking precision is improved, but reliability deteriorates due to frequent disconnection in crowded environments

Engineering Contradiction:
Improvetracking precisionVSAvoidtracking continuity
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The tracking system is segmented into multiple independent components: image analysis module for visual tracking, inertial unit for motion sensing, and wireless communication module for data transmission. This segmentation allows the system to switch between different tracking methods when one becomes unreliable, maintaining continuous operation in crowded environments where occlusion occurs

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The inertial measurement unit acts as an intermediary backup system that provides continuous tracking data through wireless communication when image analysis fails due to occlusion. The system uses proximity sensors and inertial data as intermediate references to maintain tracking continuity without requiring direct visual contact with the operator

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of operation

If the robot implements autonomous following without remote control, then ease of operation is improved, but reliability worsens due to emergency stops from unexpected masking

Engineering Contradiction:
Improveautonomous operationVSAvoidoperation continuity
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system performs preliminary actions by continuously monitoring multiple data sources (image analysis, inertial unit data, proximity sensors) and preparing backup tracking methods before occlusion occurs. The robot proactively switches to alternative tracking methods when degradation is detected, preventing emergency stops and maintaining autonomous operation

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The tracking system dynamically adjusts its methodology based on environmental conditions. When the operator is visible, image analysis is used for precise tracking. When occlusion is detected through wireless communication data or sensor input, the system dynamically switches to inertial unit-based tracking, maintaining autonomous following without interruption

Inventive Principle:
Principle #15Dynamics

3Reliability

If the robot uses multiple sensors for tracking, then reliability is improved, but device complexity increases

Engineering Contradiction:
Improvetracking robustnessVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The inertial measurement unit serves multiple functions: it provides backup tracking data when image analysis fails, communicates operator position wirelessly to the robot, and can independently track operator movement through its own sensors. This multi-functionality reduces the need for separate dedicated components, managing system complexity while maintaining reliability

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP3906452B1Companion robot system comprising an autonomously guided machine
Publication Date: 2023.03.01 BALYO
  • EP3906452B1 patent drawingFigure 1

AI summary

The invention concerns a companion robot system comprising an autonomously guided machine having at least one means for imaging the front of the robot and a computer controlled by a program for processing the acquired images and analysing leg movements in order to calculate the guidance instructions in real time. The system further comprises a unit for detecting movements of the operator, intended to be worn by the operator to be monitored, the equipment comprising an inertial unit and a communication module for transmitting data generated by said inertial unit to a communication module of said autonomously guided machine and to the computer.