Summary
Creating new healthcare products requires testing huge numbers of samples. Today manual procedures dominate, since regulations require understanding of the execution of each process step and systematic checking to verify task completion– what in this domain is called traceability.
The objective of TraceBot is to bring verifiable actions to robot manipulation by reasoning over sensor-actor trails in a traceability framework based on digital-twin technology. This entails extending current robot motion planners by the automatic execution of self-checking procedures and creating a semantic trace of the actions performed for reasoning about the correct (in the sense of domain regulations) execution of the production steps. The goal is to create robotic systems able to understand what they perceive and do, to ensure that any manipulation action is verified, so leading to the Audit Trail required in the regulated environment. To achieve this ambitious goal, we will develop: appropriate tactile fingers/grippers for handling medical products; a set of manipulation skills to execute the regulatory checking action for every assembly step, leading to the audit trail; an intuitive programming method for a quick adaptation to novel products and tasks; reasoning for safe and failure-resistant operation of the robot system to meet the need of safety-critical automation.
To maximise impact, TraceBot has adopted sterility testing as use case, a key process in the distribution of medical products. The industries are highly competitive and innovative, being a major sector for the EU, turning over €1000bn/year and providing 10 million jobs. Automation is needed to reduce cost, to improve the quality of production and working conditions. The capability to verify and trace robot actions would overcome a barrier in medical industries. We will demonstrate that our traceability framework achieves it on a complete set of steps for sterility testing and show rapid adaption to another test set.
The objective of TraceBot is to bring verifiable actions to robot manipulation by reasoning over sensor-actor trails in a traceability framework based on digital-twin technology. This entails extending current robot motion planners by the automatic execution of self-checking procedures and creating a semantic trace of the actions performed for reasoning about the correct (in the sense of domain regulations) execution of the production steps. The goal is to create robotic systems able to understand what they perceive and do, to ensure that any manipulation action is verified, so leading to the Audit Trail required in the regulated environment. To achieve this ambitious goal, we will develop: appropriate tactile fingers/grippers for handling medical products; a set of manipulation skills to execute the regulatory checking action for every assembly step, leading to the audit trail; an intuitive programming method for a quick adaptation to novel products and tasks; reasoning for safe and failure-resistant operation of the robot system to meet the need of safety-critical automation.
To maximise impact, TraceBot has adopted sterility testing as use case, a key process in the distribution of medical products. The industries are highly competitive and innovative, being a major sector for the EU, turning over €1000bn/year and providing 10 million jobs. Automation is needed to reduce cost, to improve the quality of production and working conditions. The capability to verify and trace robot actions would overcome a barrier in medical industries. We will demonstrate that our traceability framework achieves it on a complete set of steps for sterility testing and show rapid adaption to another test set.
Unfold all
/
Fold all
More information & hyperlinks
| Web resources: | https://cordis.europa.eu/project/id/101017089 |
| Start date: | 01-01-2021 |
| End date: | 31-03-2025 |
| Total budget - Public funding: | 6 999 905,00 Euro - 6 999 905,00 Euro |
Cordis data
Original description
Creating new healthcare products requires testing huge numbers of samples. Today manual procedures dominate, since regulations require understanding of the execution of each process step and systematic checking to verify task completion– what in this domain is called traceability.The objective of TraceBot is to bring verifiable actions to robot manipulation by reasoning over sensor-actor trails in a traceability framework based on digital-twin technology. This entails extending current robot motion planners by the automatic execution of self-checking procedures and creating a semantic trace of the actions performed for reasoning about the correct (in the sense of domain regulations) execution of the production steps. The goal is to create robotic systems able to understand what they perceive and do, to ensure that any manipulation action is verified, so leading to the Audit Trail required in the regulated environment. To achieve this ambitious goal, we will develop: appropriate tactile fingers/grippers for handling medical products; a set of manipulation skills to execute the regulatory checking action for every assembly step, leading to the audit trail; an intuitive programming method for a quick adaptation to novel products and tasks; reasoning for safe and failure-resistant operation of the robot system to meet the need of safety-critical automation.
To maximise impact, TraceBot has adopted sterility testing as use case, a key process in the distribution of medical products. The industries are highly competitive and innovative, being a major sector for the EU, turning over €1000bn/year and providing 10 million jobs. Automation is needed to reduce cost, to improve the quality of production and working conditions. The capability to verify and trace robot actions would overcome a barrier in medical industries. We will demonstrate that our traceability framework achieves it on a complete set of steps for sterility testing and show rapid adaption to another test set.
Status
SIGNEDCall topic
ICT-46-2020Update Date
27-10-2022
Images
No images available.
Geographical location(s)
Structured mapping
Unfold all
/
Fold all
