Pin-Marker Tactile Sensor for Multi-Axis Force Sensing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional tactile sensors in robotics are limited in measuring compressive forces and fail to detect shear movement, torque, and other types of forces, leading to issues in precise robotic assembly and gripper control.

Innovation Solution

A tactile sensor with micro mechanical pins attached to an elastomeric cap that translates patterns of forces into measurable quantities, using fiducial markers and machine vision algorithms to record and amplify deflection motions under pressure, shear, and torque, allowing for sensitive detection of compressive, shear, torque, pinch, and spreading forces.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional pressure sensors are used to measure compressive forces, then compressive force measurement is achieved, but shear movement, torque, and other types of forces cannot be detected

Engineering Contradiction:
Improveforce detection capabilityVSAvoidforce pattern detection accuracy
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The sensor surface is divided into multiple discrete pin locations, each capable of independent deflection and measurement. This segmentation allows different pins to detect different force components (compressive, shear, torque) simultaneously, enabling versatile force pattern detection while maintaining precise measurement at each location through machine vision tracking of individual pin deflections

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The pin-based measurement system serves multiple functions: detecting compressive forces through vertical pin deflection, detecting shear forces through lateral pin displacement, and detecting torque through rotational pin movement. A single sensor platform thus achieves universal force detection capability across multiple force types, resolving the contradiction between adaptability and measurement precision

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

2Measurement precision

If machine vision algorithms with fiducial markers are used to track pin deflection, then sensitivity and accuracy are enhanced, but device complexity increases

Engineering Contradiction:
Improvedeflection detection accuracyVSAvoidsensor system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

Fiducial markers serve as intermediaries between the physical pin deflection and the machine vision measurement system. These markers attach to pin tips and amplify the visual signal of small deflections, enabling high-precision tracking through optical means without requiring complex internal sensor electronics within each pin, thus enhancing measurement precision while managing system complexity

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system creates an optical copy of the pin deflection pattern through machine vision imaging. Instead of embedding complex electronic sensors in each pin, the system captures images of fiducial markers on pin tips and processes these visual copies to determine deflection patterns. This copying approach achieves high measurement precision while avoiding the complexity of multiple embedded electronic sensing elements

Inventive Principle:
Principle #26Copying

3Measurement precision

If micro mechanical pins with lever arms are added to amplify sensitivity, then force detection sensitivity is magnified, but manufacturing complexity increases

Engineering Contradiction:
Improveforce sensitivityVSAvoidsensor fabrication difficulty
Core Design Contradiction:
Measurement precisionVSEase of manufacture

Solution Approach 1:

The pin structure is modified by changing its geometric parameters - adding lever arms that extend from the pin base. This parameter change amplifies the visual displacement of fiducial markers for a given force input, thereby increasing sensitivity. The lever arm length and orientation can be adjusted as design parameters to optimize sensitivity while maintaining manufacturability through standard fabrication techniques

Inventive Principle:
Principle #35Parameter changes

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 solution provides enhanced sensitivity and accuracy in detecting various forces, enabling precise robotic grasping and assembly by converting complex force patterns into measurable data, improving the reliability of robotic operations.

Implementation Method 1

an elastomeric cap including a top surface and an undersurface having pins, ridges, or both... upon exterior forces applied to an outer impact surface of the cap, the micro mechanical pins translate a pattern of forces into measurable quantities

Methodology Applied
Scientific EffectElasticity: Elasticity

Implementation Method 2

Each undersurface pin or ridge includes a mark... the elastically deformable element is attached to a gripper of the robot... the pins translate a pattern of forces into measurable quantities

Methodology Applied
Scientific EffectElasticity: Elasticity

Data Source

PatentEP3903080B1Tactile sensor
Publication Date: 2022.05.11 MITSUBISHI ELECTRIC CORP
  • EP3903080B1 patent drawingFigure 1A
  • EP3903080B1 patent drawingFigure 1B
  • EP3903080B1 patent drawingFigure 1C

AI summary

A tactile sensor including a cap having a top surface and an undersurface. The undersurface includes pins, each pin has a mark. A portion of the undersurface is attachable to a device. A camera positioned in view of the marks, captures images of the marks placed in motion by elastic deformation of the top surface of the cap. A processor receives the captured images and determines a set of relative positions of the marks in the captured images, by identifying measured image coordinates of locations in images of the captured images. Determine a net force tensor acting on the top surface using a stored machine vision algorithm, by matching the set of relative positions of the marks to a stored set of previously learned relative positions of the marks placed in motion. Control the device via a controller in response to the net force tensor determined in the processor.