Pixelbliss - Fotolia
Armar-6 shows how helper robots can work in Ocado warehouses
Collaborative robot is the result of the five-year SecondHands project with academia to develop a robot that can support human workers
The European Union’s SecondHands Horizon 2020 robotics project has been completed, resulting in Armar-6, a humanoid robot that can help workers with maintenance tasks. It was developed by Ocado Technology and its academic partners across Europe in a five-year project.
Launched in 2015, the mission was to develop a collaborative robot, or “cobot” assistant, to improve the safety of people working in industrial environments by proactively offering assistance to humans in maintenance tasks. Along with Ocado Technology, the consortium developing the robot included the Ecole Polytechnique Fédérale de Lausanne (EPFL), Karlsruhe Institute of Technology (KIT), Sapienza University of Rome and University College London (UCL).
The original project goals included the ability for the robot to hold, lift, reach or pass objects. According to Ocado Technology, the overall goal was to develop a robot that could take on responsibility for tasks such as heavy lifting and support roles, enabling people to concentrate on the “skilled” part of a job.
The underlying robot platform, the Armar-6, was developed at the KIT specifically for the project requirements with respect to human-robot interaction. The robot is the sixth generation and youngest member of the Armar family of humanoid robots.
Tamim Asfour, a professor at KIT, said: “Robots with sophisticated manipulation, interaction and learning abilities, such as Armar-6, will provide a second pair of hands to people in need of help at home and at work. The achievements in the project are important steps towards building humanoid robots with embodied intelligence.”
The robot can respond to natural language commands, as well as inferring when a person needs help and proactively offering it, as well as lift, hold and pass objects of a wide range of shapes and sizes using dexterous manipulation. The project team behind Armar-6 said it can also learn how to assist with a variety of maintenance tasks in a range of environments.
Aude Billard, a professor at EPFL, said: “The breakthroughs demonstrated in ‘hand-over’ scenario, ‘guard removal and insertion’, ‘guard co-manipulation’ and ‘obstacle avoidance’ will play a crucial role in having reliable robots that can be used in everyday scenarios.”
Ocado Technology believes collaborative robots such as Armar-6 will be key for solving many societal challenges – both as assistive robots in industry, and out in the wider world. Graham Deacon, robotics research fellow at Ocado Technology, said: “Humanoid robots are key for improving flexibility and safety in industrial contexts in a way that is genuinely useful.
“The same technologies that enable the Armar-6 to communicate and interact with humans, like natural language comprehension, soft manipulation and 3D spatial awareness, also mean the robot could be developed further to help in other situations, such as in helping to reduce contamination, or in assisted living.”
Read more about robot innovations
- In 1620, the Mayflower set sail to the New World. We speak to the tech lead of an autonomous ship that has been built to make the same voyage.
- The future of AI in the workplace relies on the successful integration of humans and bots. Retail use cases for cobots point to customer engagement and labour tasks.
The robot has been tested working alongside Ocado Technology employees in one of Ocado’s highly automated warehouses. Lourdes Agapito, a professor at UCL, said: “It was really valuable to be able to test in the Ocado warehouse as a real-world environment. The dynamic, constantly changing conditions tested our vision, robotics and language processing algorithms to go beyond the current state of the art.”
Fiora Pirri, a professor at Sapienza University, added: “These artificial intelligence innovations have been made possible thanks to the close collaboration of all the partners. The challenging real-world environment of the Ocado customer fulfilment centre allowed us to develop a reasoning system and perception algorithms to provide support in industrial maintenance tasks.”