Person-Absence Detection Using Human-Specific Sensor Features

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing security systems struggle to reliably distinguish between humans and automated guided vehicles (AGVs), leading to conservative safety measures that reduce machine productivity and hinder effective human-machine collaboration, as they are based on generalized movement detection without object type identification.

Innovation Solution

A device comprising a data acquisition unit, feature extraction unit, and deductive decision module that uses deductive reasoning to determine the absence of persons by extracting human-specific features from sensor data, initiating safety measures only when the presence of a person cannot be ruled out, thereby leveraging multiple sensors' strengths and compensating for their weaknesses.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If generalized movement detection methods are used to detect persons in monitored areas, then detection coverage is improved, but the ability to distinguish between persons and automated guided vehicles deteriorates

Engineering Contradiction:
Improveperson detection reliabilityVSAvoidobject type identification precision
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The detection process is segmented into multiple independent analysis stages: initial movement detection, feature extraction (shape, size, movement patterns), classification (person vs. AGV), and safety decision-making. This segmentation allows each stage to focus on specific aspects, improving overall detection reliability while maintaining precision through specialized analysis at each step.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system transitions from 2D movement detection to 3D spatial analysis by incorporating depth information and volumetric characteristics. This dimensional enhancement enables the system to distinguish between persons and AGVs based on their different spatial footprints, shapes, and movement trajectories in three-dimensional space, resolving the identification precision issue.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Reliability

If rigid safety concepts with strict safety zones are applied, then operator safety is improved, but machine productivity deteriorates due to frequent interruptions

Engineering Contradiction:
Improveoperator safetyVSAvoidmachine productivity
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The safety system transitions from static, rigid safety zones to dynamic safety boundaries that adapt in real-time based on detected object type. When AGVs are detected, the system maintains permissive operation within defined zones. When persons are detected, safety interventions are triggered. This dynamic adaptation preserves operator safety while eliminating unnecessary interruptions caused by false detections, thereby maintaining machine productivity.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the parameter of safety zone enforcement based on object classification. Instead of applying a fixed safety protocol, the system adjusts safety parameters (such as zone activation, warning levels, and intervention thresholds) according to whether the detected object is a person or an AGV, optimizing both safety and productivity.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If multi-sensor systems are integrated for person detection, then detection accuracy is improved, but system complexity increases

Engineering Contradiction:
Improveperson detection accuracyVSAvoidsystem integration complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

Multiple sensor types (cameras, radar, ultrasonic sensors, light fields) are merged into a unified detection system with a single classification output. The system combines data from different sensors to detect movement, extract features, and classify objects, achieving high detection accuracy while managing complexity through integrated processing architecture.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system employs multi-functional sensor units that can perform multiple detection tasks (movement detection, positioning, identification) and work with various object types (persons, AGVs, other vehicles). This universality reduces the need for separate specialized systems, thereby improving detection accuracy without proportionally increasing system complexity.

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

Data Source

PatentEP4697283A1Device for the safe detection of the absence of persons in a surveillance area
Publication Date: 2026.02.18 PILZ GMBH & CO KG
  • EP4697283A1 patent drawingFigure 1
  • EP4697283A1 patent drawingFigure 2
  • EP4697283A1 patent drawingFigure 3

AI summary

Device (100) for the reliable detection of the absence of persons in a monitored area of ​​a technical installation, comprising: a data acquisition unit (102) configured to record sensor data relating to an environment of the technical installation, provided by at least one sensor, a feature extraction unit (104) configured to extract human-specific features from the sensor data, and a deductive decision module (106) configured to initiate a safety-related action if, based on a deductive conclusion derived from the extracted human-specific features, the presence of a person cannot be excluded.