Better gripping with intelligent picking robots

Researchers from Germany and Canada work on new AI methods for picking robots.

 ISLANDIA, NY, July 7, 2021 — Production, warehouse, shipping – where goods are produced, stored, sorted or packed, picking also takes place. This means that several individual goods are removed from storage units such as boxes or cartons and reassembled. With the FLAIROP (Federated Learning for Robot Picking) project Festo and researchers from the Karlsruhe Institute of Technology (KIT), together with partners from Canada, want to make picking robots smarter using distributed AI methods. To do this, they are investigating how to use training data from multiple stations, from multiple plants, or even companies without requiring participants to hand over sensitive company data. 

“We are investigating how the most versatile training data possible from multiple locations can be used to develop more robust and efficient solutions using artificial intelligence algorithms than with data from just one robot,“ says Jonathan Auberle from the Institute of Material Handling and Logistics (IFL) at KIT. In the process, items are further processed by autonomous robots at several picking stations by means of gripping and transferring. At the various stations, the robots are trained with very different articles. At the end, they should be able to grasp articles from other stations that they have not yet learned about. „Through the approach of federated learning, we balance data diversity and data security in an industrial environment,“ says the expert.

Powerful algorithms for industry and logistics 4.0

Until now, federated learning has been used predominantly in the medical sector for image analysis, where the protection of patient data is a particularly high priority. Consequently, there is no exchange of training data such as images or grasp points for training the artificial neural network. Only pieces of stored knowledge – the local weights of the neural network that tell how strongly one neuron is connected to another – are transferred to a central server. There, the weights from all stations are collected and optimized using various criteria. Then the improved version is played back to the local stations and the process repeats. The goal is to develop new, more powerful algorithms for the robust use of artificial intelligence for industry and Logistics 4.0 while complying with data protection guidelines.

“In the FLAIROP research project, we are developing new ways for robots to learn from each other without sharing sensitive data and company secrets. This brings two major benefits: we protect our customers‘ data, and we gain speed because the robots can take over many tasks more quickly. In this way, the collaborative robots can, for example, support production workers with repetitive, heavy, and tiring tasks”, explains Jan Seyler, Head of Advanced Develop. Analytics and Control at Festo SE & Co. KG During the project, a total of four autonomous picking stations will be set up for training the robots: Two at the KIT Institute for Material Handling and Logistics (IFL) and two at the Festo SE company based in Esslingen am Neckar.

Start-up DarwinAI and University of Waterloo from Canada are further partners

“DarwinAI is thrilled to provide our Explainable (XAI) platform to the FLAIROP project and pleased to work with such esteemed Canadian and German academic organizations and our industry partner, Festo. We hope that our XAI technology will enable high-value human-in-the-loop processes for this exciting project, which represents an important facet of our offering alongside our novel approach to Federated Learning.  Having our roots in academic research, we are enthusiastic about this collaboration and the industrial benefits of our new approach for a range of manufacturing customers”, says Sheldon Fernandez, CEO, DarwinAI.

“The University of Waterloo is ecstatic to be working with Karlsruhe Institute of Technology and a global industrial automation leader like Festo to bring the next generation of trustworthy artificial intelligence to manufacturing.  By harnessing DarwinAI’s Explainable AI (XAI) and Federated Learning, we can enable AI solutions to help support factory workers in their daily production tasks to maximize efficiency, productivity, and safety”, says Dr. Alexander Wong, Co-director of the Vision and Image Processing Research Group, University of Waterloo, and Chief Scientist at DarwinAI.

About FLAIROP

The FLAIROP (Federated Learning for Robot Picking) project is a partnership between Canadian and German organizations. The Canadian project partners focus on object recognition through Deep Learning, Explainable AI, and optimization, while the German partners contribute their expertise in robotics, autonomous grasping through Deep Learning, and data security.

  • KIT-IFL: consortium leadership, development grasp determination, development automatic learning data generation.
  • KIT-AIFB: Development of Federated Learning Framework
  • Festo SE & Co. KG: development of picking stations, piloting in real warehouse logistics
  • University of Waterloo (Canada): Development object recognition
  • Darwin AI (Canada): Local and Global Network Optimization, Automated Generation of Network Structures

Visit www.festo.com/us for more information on Festo products and services.

About Festo

Festo is a leading manufacturer of pneumatic and electromechanical systems, components, and controls for process and industrial automation. For more than 40 years, Festo Corporation has continuously elevated the state of manufacturing with innovations and optimized motion control solutions that deliver higher performing, more profitable automated manufacturing and processing equipment.

Connect with Festo: Facebook, LinkedIn, Twitter and YouTube

Artificial feathers give flight to robotic birds

Festo presents its new bionic project “BionicSwift”


Thanks to radio-based indoor GPS with ultra-wideband technology (UWB) the BionicSwifts can fly safely and in a coordinated pattern in a defined airspace. To execute these flight manoeuvres as true to life as possible, the wings are modelled on the plumage of real birds. The agility of the artificial birds is not just due to their lightweight design and aerodynamic kinematics, but also to the use of function integration.


The Festo Bionic Learning Network has a long tradition of being inspired by natural flight. The creation of the BionicSwift represents the next chapter for Festo in the development of bionic flying objects. As in its biological model, the use of lightweight structures is at the heart of the artificial bird. Because in both engineering and in nature, the less weight there is to move, the less material is required, and the less energy is consumed. That is why the BionicSwift weighs just 42 grams despite having a body length of 44.5 centimetres and a wingspan of 68 centimetres. This makes it extremely agile, nimble and capable of flying loops and making tight turns. By interacting with a radio-based indoor navigation system, the robotic birds are able to move autonomously in a coordinated pattern in a defined airspace.

Aerodynamic feathers

To be able to replicate natural flight as closely as possible, the wings of the BionicSwifts are modelled on bird feathers. The individual lamellae are made from an ultra-lightweight, flexible but very robust foam, and overlap each other. Connected to a carbon quill, they are attached to the actual hand and arm wings as in the natural model. The individual lamellae fan out during the wing upstroke, allowing air to flow through the wing. This means the birds require less power to propel the wing upwards. The lamellae then close during the downstroke to provide the flying robot with a more powerful flight. This close replication of bird wings gives the BionicSwift a better flight profile than previous beating wing drives.

Function integration in the tightest of spaces

The agility of the artificial bird is not just due to its lightweight design and aerodynamic kinematics, but also to the use of function integration. The bird’s body contains the compact construction for the wingflapping mechanism, the communication technology, the control components for wing flapping and the elevator, the tail. A brushless motor, two servo motors, the battery, the gear unit and various circuit boards are installed in the smallest of spaces. Through the intelligent interaction of the motors and mechanical systems, the frequency of the wing beats and the elevator for the various manoeuvres can be precisely adjusted.

GPS coordination of the flight manoeuvre

The coordinated and safe flight of the robotic birds is made possible by radio-based indoor GPS with ultra-wideband technology (UWB). Several radio modules are mounted in the space, forming fixed anchors that locate each other and define the controlled airspace. Each bird is equipped with a radio marker that sends signals to the bases, which can then locate the bird’s exact position and send the data collected to a central master computer, which functions as a navigation system. The system can use preprogrammed paths to plan and determine routes and flight paths for the birds. If the birds deviate from this flight path, for example due to a sudden change in ambient conditions such as wind or thermals, they immediate correct their flight path by intervening autonomously – without any human pilots. Radio-based communication means that position sensing is possible, even if there are obstacles and visual contact is partially lost. The use of UWB as radio technology guarantees safe and interference-free operation.

New inspiration for intralogistics

The intelligent networking of flight objects and GPS routing makes a 3D navigation system that could be used in the networked factory of the future. For example, by precisely locating the flow of materials and goods, process workflows can be improved and bottlenecks can be predicted. In addition, autonomous flying robots could be used for transporting materials, with their flight corridors a way of optimising the use of space within a factory.

About Festo:

Festo is a global player and an independent family-owned company with headquarters in Esslingen am Neckar, Germany. The company supplies pneumatic and electrical automation technology to 300,000 customers of factory and process automation in over 35 industries. The products and services are available in 176 countries. With about 21,000 employees in over 250 branch offices in 61 countries worldwide, Festo achieved a turnover of around €3.07 billion in 2019. Each year around 8% of this turnover is invested in research and development.

In this learning company, 1.5% of turnover is invested in basic and further training. Yet training services are not only provided for Festo’s own staff – Festo Didactic SE also supplies basic and further training programmes in the field of automation technology for customers, students and trainees.

Bionic Flower: a bionically inspired robot flower

Another step for the integral didactic concept of Bionics4Education

Festo Didactic presents a new product for the bionics didactic concept of Bionics4Education. What is new: the orientation towards the maker movement approach and the 4Cs. The aim is inspiring learners, finding new ways and solutions, dealing creatively with provided materials, and sharing these experiences with others to prepare them for the digital world of tomorrow.

Inspired by the plant world

The Bionic Flower is a construction kit inspired by the plant world. Festo Didactic developed the Bionic Flower following the models of mimosa plants and water lilies in cooperation with SkySpirit. The Bionic Flower opens and closes its petals as a reaction to external influences such as touch, proximity or light. These mechanisms can be discovered in a playful way by pupils in the classroom using sensors and control technology integrated in the Bionic Flower. The design, as well as the transfer of principles from the plant world, rounds off the teaching of curriculum topics in STEM education (Science, Technology, Engineering, and Maths). The topic of biodiversity can also be discussed in class.

Bionic work didactically prepared

One Bionic Flower can be used by up to three students at a recommended age of 10 and over. The petals contain the first bionic topic: the folding technique. The petals gain the necessary mechanical stiffness by folding. The mechanism for opening and closing the petals is electrically actuated with a stepper motor which opens and closes the petals one after the other. The movement and the light effects are controlled via Wi-Fi-enabled smartphones, tablets or PCs. If required, the microcontroller can be programmed with the graphic coding interface „Open Roberta“. Experienced students can also program their Bionic Flower in C++. The code is open source. This enables teachers to teach technical content via a new, interdisciplinary educational path. Accompanying teaching material, as well as the assembly manual, can be downloaded free of charge from our website www.bionics4education.com.

An expanded approach to promoting valuable skills

Students learn different aspects of STEM with the Bionic Flower – in a digital, creative and interdisciplinary way. The Bionic Flower combines bionics and technical education and is thus based on the competencies of the 4Cs: collaboration, communication, critical thinking and creativity to empower learners for the digital world of tomorrow.
In addition, soft skills such as working in a team are reinforced.

New in the concept: the maker movement approach

The maker movement is based on the DIY (do it yourself) culture and the idea of finding new ways and solutions, dealing creatively with materials, and sharing these experiences with others. The Bionic Flower takes this approach and combines Maker Education and STEM Education. In addition to assembling the Bionic Flower, learners can customize and expand on the Bionic Flower by using 3D printers, other materials, hardware and software.

Festo and MassRobotics to Create Innovations in Robotics and Automation Through New Partnership

STUTTGART, GERMANY (PRWEB) APRIL 23, 2020

Festo has entered into a strategic partnership with MassRobotics, based in Boston, to further global market growth and innovation initiatives dedicated to the development of the next generation of robotics.

MassRobotics, the independent, nonprofit group serving as an innovation hub for robotics and smart connected devices, works to foster a collaborative space in which to inspire the next generation of robotics and automation innovators and builders. The organization’s unique “escalator” model allows startups to establish, grow, offer meaningful employment, and provide ongoing value for MassRobotics’ partner organizations.

MassRobotics also creates a supportive learning environment to engage youth and next generation engineers and entrepreneurs by offering Science, Technology, Engineering and Mathematics (STEM) workshops, competitions, and technical internships. MassRobotics supports the Ventilator Project, founded by entrepreneurs located at MassRobotics. The Ventilator Project aims to solve the ventilator shortage crisis with an innovative low-cost ventilator designed by members; the team is currently seeking FDA approval for the device.

“We are pleased to announce our partnership with MassRobotics,” said Alfons Riek, Vice President Technology and Innovation, Festo. “Combining Festo’s in-depth know-how in manufacturing applications and automation technology with the MassRobotics community will enable Festo to engage with robotics and automation startups. We will collaborate with entrepreneurs and academia alike in bringing innovative new automation and robotic concepts and solutions to market.”

“The Boston area with its high density of robotic expertise is very interesting for us, and we expect many interesting opportunities for our robot development throughout the partnership with MassRobotics,” said Christian Tarragona, Vice President Festo Robotics.

Carlos Miranda, CEO, Festo North America, added, “Festo and other MassRobotics members will explore the evolution of automated manufacturing solutions to autonomous ones. Through technology challenge engagements, members will co-develop and commercialize advanced products and systems.”

Festo is one of the world’s leading automation companies, and, in addition to technology, the company offers automation learning systems through its Didactic Division. It promotes public and private alliances that implement apprenticeship programs. Festo invests heavily in research and development. The Bionic Learning Network, for example, creates novel solutions based on designs found in nature. The network emphasizes Festo partnerships with academia and technology businesses.

“MassRobotics and Festo share a vision of developing the future of robotic solutions dedicated to the emerging needs of the manufacturing sector,” said Fady Saad, Cofounder and Vice President of Strategic Partnerships, MassRobotics. “Having an automation company with the expertise, resources, and leading-edge development capabilities of Festo will further the mission of MassRobotics and create excitement about our collaborative efforts.”

###

About Festo    
Festo is a leading manufacturer of pneumatic and electromechanical systems, components, and controls for process and industrial automation. For more than 40 years, Festo Corporation has continuously elevated the state of manufacturing with innovations and optimized motion control solutions that deliver higher performing, more profitable automated manufacturing and processing equipment. Connect with Festo: Facebook, LinkedIn, Twitter and YouTube

About MassRobotics
MassRobotics is the collective work of a group of Boston-area engineers, rocket scientists and entrepreneurs. With a shared vision to create an innovation hub and startup cluster focused on the needs of the robotics community, MassRobotics was born. MassRobotics’ mission is to help create and scale the next generation of successful robotics and connected device companies by providing entrepreneurs and innovative robotics/automation startups with the workspace and resources they need to develop, prototype, test and commercialize their products and solutions. http://www.massrobotics.org

NI WorldClass 2012 – Video

Back from NI Worldclass 2012, here is the official video. Thanks to NI and all the nice people I have met there! It was great fun and an „once in a lifetime“ experience!

The robot shown in the video is a Robotino from Festo Didactic.

Don’t forget to apply for WorldClass 2013! You should not miss that!