Event Sensor Edge Tracking for Accurate Robot Pickup Timing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Accurate estimation of the edge position of a target object is difficult when it is displaced within the sensing range of a camera, leading to inaccurate determination of pickup timing, particularly in image analysis applications like logistics.

Innovation Solution

An information processing device utilizing an event-based vision sensor (EVS) to estimate the movement track of the edge position based on position information from event-caused pixels, improving the accuracy of edge position estimation by enhancing the sampling rate of detection information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If image analysis is applied to a captured image when the target object is displaced within the sensing range, then the robot arm can move toward the target object, but the edge position estimation accuracy deteriorates

Engineering Contradiction:

Improverobot arm movement toward target objectVSAvoidedge position estimation accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system performs preliminary edge position estimation using images captured before the target object enters the sensing range. By estimating the edge position in advance and storing it as reference information, the system can accurately determine pickup timing even when the target object is displaced within the sensing range during robot arm movement.

Inventive Principle:

Principle #10Preliminary action

2Productivity

If the target object is displaced within the sensing range during robot arm movement, then pickup timing can be determined, but the edge position estimation becomes inaccurate due to changing light conditions

Engineering Contradiction:

Improvepickup timing determinationVSAvoidedge position estimation accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system captures images of the target object before it enters the sensing range and estimates the edge position during this stable period. This preliminary estimation is stored as reference information, allowing accurate pickup timing determination even when light conditions change during subsequent robot arm movement and object displacement.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses reference information from preliminary edge position estimation to feedback-correct the pickup timing determination. By comparing the current state with the pre-estimated edge position, the system maintains measurement accuracy despite dynamic changes in light conditions during object displacement.

Inventive Principle:

Principle #23Feedback

3Device complexity

If conventional image sensors are used for edge detection, then the system is simple to implement, but the sampling rate of detection information is insufficient for accurate movement tracking

Engineering Contradiction:

Improvesystem implementation simplicityVSAvoidedge position movement track estimation

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system replaces conventional frame-based image sensing with event-based vision sensing. Event sensors detect changes in light intensity at the pixel level and output event data with high temporal resolution, providing continuous movement track information of the target object edge without requiring complex image processing sequences.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The use of an EVS enables precise estimation of the edge position and determination of pickup timing by referencing the movement track, even in cases of erroneous detection, thereby improving the accuracy of target object pickup.

Implementation Method 1

an event sensor which includes multiple pixels each having a light receiving element and which is configured to be capable of detecting a change of a predetermined amount or more of received light as an event

Methodology Applied

Scientific EffectPhotoelectric Effect: Photoelectric Effect

Data Source

PatentUS20250353184A1Information processing device, information processing method, and program

Publication Date: 2025.11.20 SONY SEMICON SOLUTIONS CORP

AI summary

An information processing device according to the present technology includes a movement track estimation section that estimates a movement track of an edge position of a target object in reference to position information associated with an event-caused pixel detected by an event sensor in a previous period before a reference time point in a state where a positional relation between the event sensor and the target object changes such that the target object is displaced within a sensing range of the event sensor, and an edge position estimation section that estimates an edge position of the target object at the reference time point, as a reference time edge position, in reference to the movement track of the edge position estimated by the movement track estimation section.