Tactile Sensing Unit for Thin Object Grasp Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Robotic systems face challenges in determining whether a robotic arm end effector has successfully grasped very thin objects or features, as the difference in finger position can be subtle, making it difficult to distinguish between a missed grasp and a successful grasp.

Innovation Solution

The implementation of a tactile sensing unit with multiple sensors, including magnetic, optical, electromechanical, pressure, and deformation sensors, which provide output values indicative of engagement, and a multi-factor model to process these values for accurate determination of grasp success.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional single sensor or simple position detection is used, then the device complexity is low, but the measurement precision is insufficient to distinguish successful grasp from missed grasp of very thin objects

Engineering Contradiction:
Improvegrasp detection precisionVSAvoidsensing system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The tactile sensing unit is divided into multiple independent sensors (first sensor, second sensor, third sensor, fourth sensor) distributed across different fingers and locations. Each sensor independently measures specific parameters (normal force, shear force, torque), and their combined outputs enable precise grasp detection through multi-factor analysis

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Multiple sensor types (force sensors, torque sensors, deformation sensors) are integrated into a unified tactile sensing unit on the end effector. The system merges mechanical sensing with computational analysis through a multi-factor model that processes combined sensor outputs to determine grasp success

Inventive Principle:
Principle #5Merging (Combining)

2Reliability

If multiple sensors and multi-factor model are implemented, then the measurement precision improves, but the device complexity increases

Engineering Contradiction:
Improvegrasp detection reliabilityVSAvoidsensing and processing system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system continuously monitors sensor outputs during the grasping process and uses a multi-factor model to provide real-time feedback on grasp success. The processor analyzes the combination of normal forces, shear forces, and torques to determine whether the object has been successfully grasped, enabling adaptive control

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The tactile sensing unit serves multiple functions: measuring normal forces, measuring shear forces, measuring torques, and providing comprehensive grasp detection. This multi-functional design consolidates what would otherwise require separate sensing systems into a single integrated unit

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

Data Source

PatentUS11969880B2Detecting robot grasp of very thin object or feature
Publication Date: 2024.04.30 DEXTERITY INC
  • US11969880B2 patent drawing
  • US11969880B2 patent drawing
  • US11969880B2 patent drawing

AI summary

A value associated with a plurality of measurement objects that are embedded in a material associated with an intermediate layer of a plurality of layers associated with a tactile sensing unit is sensed. The value associated with the plurality of measurement objects is sensed by a sensor that is included a layer below the intermediate layer of the tactile sensing unit. An output of the sensor is used to make a determination associated with engagement of a robotic arm end effector with an item.