The CoLLaboratE project aims to revolutionize the way humans and robots cooperate

Automation & RoboticsTechnical ArticlesSouth-East European INDUSTRIAL Мarket - issue 4/2019 • 07.11.2019

The CoLLaboratE project, implemented by 14 partners, including universities, research institutes, SMEs and industries, has received funding from the European Union’s Horizon 2020 research and innovation programme. CoLLaboratE aims to revolutionize the way industrial robots learn to cooperate with human workers for performing new manufacturing tasks, with a special focus on the challenging area of assembly operations. The envisioned system for collaborative assembly will be capable of allocating human and robotic resources for executing the production plan sharing the tasks according to the capabilities of the available actors. The proposed solution will be evaluated in four different pilot sites, which will be implemented as collaborative factory floors of the industrial partners in Italy, Slovenia, Turkey and Romania.

According to the project summary, traditional manufacturing systems lack the necessary flexibility and reconfigurability that can allow short production cycles and fast deployment of the updated system. “Although the use of automation technologies based on industrial robots can increase the adaptability of a production line, the desired flexibility cannot be achieved until abilities for genuine collaboration of the robots with the human workers are developed”, the initiative goals overview further explains.

 

Key collaboration skills

Key collaboration skills are aimed to be established through the project implementation. Among them are: adaptive robot control in collaborative tasks with physically coupled actors; collaborative behaviour primitives; human touch recognition and classification; detection of human intentions for AGVs and professional gesture recognition.
The project also aims to develop instruments for smart learning of collaborative assembly tasks through: learning from human demonstration (visual and/or kinaesthetic); autonomous assembly policy learning and policy improvement; and multimodal learning of assembly tasks.

Another priority field is the human monitoring and safety. It is planned to be achieved through: dynamic active constraints construction and enforcements for human safety during HRC and monitoring the ergonomic performance of the operator.

The CoLLaboratE project also includes developing human-robot collaboration planning system and reconfigurability solution. This will be performed by: efficient production planning optimising the utilisation of human and robotic resources and fast adaptation of co-production cell through reconfigurable hardware design.
The CoLLaboratE project will build upon state-of-the-art methods for teaching the robot assembly tasks using human demonstration, extending them to facilitate genuine human-robot collaboration. To this end, a framework for equipping the robots and AGV mobile platforms with basic collaboration skills, such as load sharing, human touch recognition and human intention detection will also be developed, coupled with deep reinforcement learning algorithms for increasing adaptability. Special attention will be paid to providing effective safety strategies allowing the use of a fenceless approach within the production cell. As a result, closer collaboration will be achievable and efficient production plans making optimal use of the available resources will be designed and executed, the project documentation also says.

 

Audience, scientific and technical objectives

The target users for the CoLLaboratE system are manufacturing industries in need of flexible and affordable automation systems to boost their global competitiveness. “Successful completion of CoLLaboratE will allow SMEs and large manufacturing companies in Europe to easily program assembly tasks and flexibly adapt to changes in the production pipeline. Such ease of use and rapid integration time of robotic assembly systems is expected to pave the way for step change in the adoption of not only collaborative robots, but a complete collaborative environment provided by the CoLLaboratE solution”, the initiative overview further explains.

In order for CoLLaboratE to successfully realize its vision several prerequisites are set in the form of major scientific and technological objectives throughout the project duration. These are summarized in the following points:

  • to equip the robotic agents with basic collaboration skills easily adaptable to specific tasks;
  • to develop a framework that enables non-experts teaching human-robot collaborative tasks from demonstration;
  • the development of technologies that will enable autonomous assembly policy learning and policy improvement;
  • to develop advanced safety strategies allowing effective human robot cooperation with no barriers and ergonomic performance monitoring;
  • to develop techniques for controlling the production line while making optimal use of the resources by generating efficient production plans, employing reconfigurable hardware design, and utilizing AGVs with increased autonomy;
  • to investigate the impact of Human-Robot Collaboration to the workers’ job satisfaction, as well as test easily applicable interventions in order to increase trust, satisfaction and performance;
  • to validate CoLLaboratE system’s ability to facilitate genuine collaboration between robots and humans.

 

A several practical use cases are planned within the project implementation. These include: performing car starter assembly, windshield visual quality check, performing LCD TV assembly and aerospace structure riveting. There will be presented the following challenges: demonstrating the task to the robot (visually, kinesthetically) until the robot has learned to execute it autonomously; teaching the robot to assist the worker in handling large, heavy and fragile parts; setting up collaboration for parallel operations of a human and a robot on the same assembly; and reducing physical effort and avoiding non-ergonomic positions with human-robot collaboration in difficult-to-automate procedures.

 

CoLLaboratE in the workshop for the future of industrial collaborative robots

The CoLLaboratE project was invited by the European Commission to participate in the “Workshop on the Future of Industrial collaborative Robotics”. Fotis Dimeas from AUTH represented the project and presented an overview of its vision. He then had the chance to discuss with the participants the challenges in physical human-robot interaction for industrial applications.

This workshop was part of a study of EC to assess the impacts of H2020 projects in Robotics. The results were reported this September at the European Research and Innovation Days. Besides CoLLaboratE, the following sister projects participated that share some common objectives: Coroma, Sharework, Sherlock, Thomas, Rossini, HR-Recycler, Symbiotic.

 

CoLLaboratE in the European Robotics Forum 2019

CoLLaboratE project presented the workshop “Collaborative robots for industrial and professional service tasks” on 20 March, Bucharest, Romania during the European Robotics Forum 2019.

The workshop was aimed to bring together different fields of science to aid in the application area of collaborative robot programming. The focus was on challenges faced by human-robot collaboration in both manufacturing and service industries. “Along these lines, the CoLLaboratE project aims to revolutionize the way industrial robots learn to cooperate with human workers for performing new manufacturing tasks, with a special focus on the challenging area of assembly operations”, the participants explained.
The following topics were discussed during the workshop: enabling technologies for teaching collaborative robots; challenges in human robot collaborative use-cases; self-learning and adaptation capabilities of robots in collaborative scenarios; role assignment in human-robot collaboration.

Top