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

SourceRabbit released a commercial GCode Sender for GRBL CNC Machines

GRBL is quite popular with the CNC hobby community, open source firmware that turns an Arduino into a CNC controller. It was released in 2015 and in recent years has gained many friends, among them SourceRabbit, a Greek CNC machine tool manufacturer, which aspires to transform GRBL from a hobby tool to an industry standard by offering the first commercial CNC control software for GRBL-compatible CNC machines.

Their new commercial software, GCode Sender 4-Axis, released in April 2021, replaced their old 3-axis software which has been available since 2015. It is compatible with the classic 3-Axis GRBL for AVR processors and the new multi axis Grbl for the Esp32.

We managed to obtain a statement from Nikos Siatras, CEO of SourceRabbit, who told us “From 2015 until the beginning of 2021, many GCode Sender applications were developed to control GRBL CNC machine tools. All of them were open source, free of charge, without any support and often with several bugs that tire even the most patient user. While GRBL is an incredibly good and flexible CNC control firmware, the GCode Senders that existed until today gave the impression that GRBL is purely for hobbyists. Through the development of our own software we are going to change that and we will try to make GRBL a CNC industry standard.”

SourceRabbit plans to implement many new tools and features to the GCode Sender 4-Axis. The software retails for €50.00 + VAT and with the purchase of each license you have free access to all subsequent versions of the software.

Wandelbots – No-Code Robotics – – Kurzinterview

Sebastian von Robots-Blog konnte ein kurzes Interview mit Annelie Harz von Wandelbots führen. Erfahrt im Interview was Wandelbots ist und warum demnächst vielleicht das Programmieren überflüssig wird.

Robots-Blog: Wer bist du und was ist deine Aufgabe bei Wandelbots?

Annelie: Mein Name ist Annelie und ich arbeite als Marketing Managerin bei Wandelbots.

Robots-Blog: Welcher Roboter aus Wissenschaft, Film oder Fernsehen ist dein Lieblingsroboter?

Annelie: Tatsächlich Wall-E. Ein kleiner Roboter, der Gutes tut und einfach nur liebenswert ist.

Robots-Blog: Was ist Wandelbots und woher kommt der Name?

Annelie: Der Name beschreibt den WANDEL der RoBOTik. Denn das ist genau das, was wir tun. Den Umgang mit Robotern, der heute nur einem kleinem Kreis von Experten vorbehalten ist, ermöglichen wir jedem. Unsere langfristige Firmenvision lautet: “Every robot in every company and every home runs on Wandelbots”. Und das verspricht einen großen Wandel in verschiedensten Ebenen – angefangen für uns bei der Industrie.

Robots-Blog: An wen richtet sich euer Produkt und was brauche ich dafür?

Annelie: Unser Produkt richtet sich derzeit an Kunden aus der Industrie. Hierbei kann unsere Software – Wandelbots Teaching – bei der Programmierung verschiedenster Applikationen wie z.B. Schweißen oder Kleben helfen ohne, dass man eine Zeile Code schreiben muss. Sie ist so einfach und intuitiv designed, dass wirklich jeder mit ihr arbeiten kann, um einem Roboter ein gewünschtes Ergebnis beizubringen. Dies funktioniert durch das Zusammenspiel einer App und eines Eingabegerätes, dem TracePen. Dieser hat die Form eines großen Stiftes, mit dem Nutzende dem Roboter am Bauteil beispielhaft einen gewünschten Pfad vorzeichnen können. Aber auch mit Bildungsträgern arbeiten wir zusammen. Sie sind es, die die nächste Generation von Roboterexperten ausbilden. Da darf unser Produkt natürlich nicht fehlen (Annelie grinst) Und langfristig sind wir – das steckt ja schon in unserer Vision – davon überzeugt, dass Roboter auch als kleine Helfer im Privatleben Einzug halten werden.

Robots-Blog: Welches Feature ist besonders erwähnenswert?/Was kann kein anderer?

Annelie: Unser Produkt arbeitet roboterhersteller-unabhängig. In der Robotik hat jeder Hersteller über die Jahre seine eigene proprietäre Programmiersprache entwickelt. Das macht die Kommunikation zwischen Mensch und Maschinen sehr schwierig. Wir wollen hingegen ein Tool schaffen, mit dem jeder Mensch mit jedem Roboter arbeiten kann – ganz unabhängig von Programmiersprache und Hersteller. Robotik soll dem Anwender unseres Produktes Spaß machen. Dank der hohen Usability und der Bedienung unserer App via iPad ist das heute schon möglich. Und über die nächste Zeit kommen applikationsspezifische Editionen in unsere Plattform – aktuell arbeiten wir beispielsweise an einer Appversion für das Roboterschweißen.

Robots-Blog: Muss ich dann überhaupt noch Programmieren lernen?

Annelie: Nein. Wie eben erklärt muss man mit dieser sogenannten No-Code Technologie nicht mehr programmieren lernen. Es ist einfach, intuitiv und nutzerfreundlich, selbst für Laien. Selbstverständlich muss man aber, vor allem aus Sicherheitsgründen, immer ein gewisses Grundverständnis über Robotik verfügen. Die Gefährdungen durch Roboter sollte man nie unterschätzen, deswegen arbeitet unser Produkt immer nach den jeweiligen herstellerspezifischen Sicherheitsvorgaben.

Robots-Blog: Welche Roboter werden unterstützt? Ich habe einen Rotrics DexArm und einen igus Robolink DP-5; kann ich diese auch verwenden?

Annelie: Wir wollen kurz nach dem Markteintritt natürlich erst einmal die Robotik in der Industrie, beispielsweise der Automobilbranche, flexibler und einfacher machen. Dafür integrieren wir die größten Robotermarken nach und nach in unsere Plattform. Kleinere Robotermarken, die eine oder mehrere Nischen abdecken, werden wir mit Sicherheit auch noch integrieren. Oder – noch besser – dank unseres Software Development Kits für die Roboterintegration können das Roboterhersteller demnächst sogar selbst.

Robots-Blog: Was kostet euer Produkt?

Annelie: Unser Produkt wird über ein Lizenzmodell als Subscription angeboten, wie es im Software as a Service Business üblich ist oder auch klassisch zum Kauf. Die aktuellen Preise für die unterschiedlichen Editionen könnt Ihr auf unserer Website finden (und dort bestimmt noch spannende weitere Inhalte finden)

Der neue Bildungsroboter MAKEBLOCK mBot2 lässt sich dank KI sogar über die Mimik steuern und gibt Gefühle wieder

Der mBot2 Programmierroboter löst nach 8 Jahren den weltweit erfolgreichen mBot1 ab und begeistert mit topaktueller Sensorik, neuen Motoren und einem brandneuen KI-Steuerboard im vertrauten Design. Für Kinder, Lehrer und Tüftler, die spielend mehr über Informatik, MINT, IoT, AI und blockbasiertes Coding lernen wollen 

Ubstadt-Weiher, 29.04.2021 – In den vergangenen acht Jahren hat der Bildungsroboter mBot von MAKEBLOCK weltweit Millionen von Kindern, Schülern, Lehrern und angehenden Programmieren nicht nur komplexe MINT (Mathematik, Informatik, Naturwissenschaft, Technik)-Zusammenhänge spielerisch vermittelt, sondern auch nach Abschluss erfolgreicher Missionen ein Lächeln ins Gesicht gezaubert. Und die Erfolgsgeschichte geht mit dem neuen mBot2 weiter: Unter der behutsam modifizierten Hülle, die jetzt aus robustem Aluminium besteht, ist geballte modernste Technologie verpackt, die unzählige neue Programmierungs- und Anwendungsmöglichkeiten ermöglicht. Am auffälligsten sind auf den ersten Blick die Ultraschallsensoren der nächsten Generation, die einem in strahlendem Blau anblicken. Wer kann diesem verführerischen Blick schon widerstehen? Die blauen „Augen“ sind aber nicht nur für die präzise Entfernungsmessung geeignet, sie vermitteln mit Hilfe der steuerbaren Ambient-Beleuchtung auch Emotionen. Der mBot2 sucht geradezu den Blickkontakt zu den kleinen Programmierern, denn durch die KI-Bilderkennung lässt sich z.B. die Geschwindigkeit über den Gesichtsausdruck steuern.

Weiterlesen

GinoBot by Engino – Base model with Gripper

Today I built the base model with a gripper and sent my feedback to the developers. It’s already really great product but there are always things to tweak or make better. Do not miss to support it on Kickstarter!

Weiterlesen

Rotrics DexArm knows how to visit its favourite website

Rotrics DexArm Robotarm visiting its favourite website robots-blog.com. Having a robot arm is fun! Find the latest News on robots, drones, AI, robotic toys and gadgets at robots-blog.com

https://www.mybotshop.de/Rotrics-DexArm

GinoBot, Inspiring Inventors of the Future with STEM Disciplines, Launches on Kickstarter

The all-in-one smart toy incorporates science, technology, engineering and mathematics disciplines with playtime, in a hands-on way. 

Astoria, New York – (May 3, 2021) Keeping children entertained and engaged in today’s tech-driven world is now easier with GinoBot. The tool that implements a fun, hands-on experiencewith unlimited expansion potential for learning STEM disciplines, computational thinking, and digital literacy is launching on Kickstarter today.


GinoBot seamlessly blends playtime with advanced learning to sharpen a child’s mind for the future. From plug-and-play robot to high-end coding and electronics, the progression of skills with GinoBot is unlimited. Children ages 6+ can build simple or complex models with GinoBot’s scalable, and compatible design.
It features KEIRO software for block-based programming, which is compatible with a PC (Windows, Linux, MAC OS) and smart devices (Google Play, Apple Store). GinoBot has Bluetooth and WiFi connectivity, as well as a micro USB connector. It can also connect with 3rd party hardware like Arduino, Microbit and Raspberry Pi, among others.

Science, technology, engineering and math, or STEM toys are the future. GinoBot is a solution for children to learn 21st century skills that lets them playfully learn how to code, design, build, and rebuild models quickly, no matter their age or learning style. 

“Children are our future and we believe they are all gifted with the power to perform astonishing technological feats,” said Costas Sisamos, founder and CEO of Engino. “As STEM learning principles become more prominent in our children’s curriculum, GinoBot is a great learning tool that will keep young minds hungry to explore, design and create enabling them to experience the limitless thrill of scientific discovery.” 

GinoBot is a great way to invest in your child’s imagination and expand their creativity. To pre-order, visit pr.go2.fund/ginobot.

About Engino 

Engino is a toy manufacturer that specializes in construction toys and smart educational toys, and have been at the vanguard of the STEM education movement for the past 15 years. A few years ago, Engino joined the robotics market and started developing programmable robots. These robots are supported with an extensive curriculum so children can learn the digital-side of thinking and how to do programming, coding, and more. For more information, visit https://www.engino.com/.

New MAKEBLOCK mBot2 educational robot can even be controlled by facial expressions

The mBot2 programming robot replaces the globally successful mBot1 after 8 years and inspires with cutting-edge sensor technology, new motors and a brand-new AI control board in a familiar design. For kids, teachers and tinkerers who want to learn more about computer science, STEM, IoT, AI and block-based coding while playing.

Ubstadt-Weiher, 29.04.2021 – Over the past eight years, MAKEBLOCK’s educational robot mBot has not only playfully taught millions of children, students, teachers and budding programmers worldwide about complex STEM (mathematics, computer science, natural science, technology) subjects, but also put a smile on their faces after completing successful missions. And the success story continues with the new mBot2: under the carefully modified shell, which is now made of robust aluminum, is packed concentrated state-of-the-art technology that enables countless new programming and application possibilities.

The most striking feature at first glance is the next-generation ultrasonic sensors, which look at you in brilliant blue. Who can resist that seductive look? But the blue „eyes“ are not just for precise distance measurement, they also convey emotion with the help of controllable ambient lighting. The mBot2 is virtually looking for eye contact with the little programmers, because the AI image recognition allows, for example, the speed to be controlled via facial expression.

Weiterlesen

MindCuber-RI uses LEGO Mindstorms Robot Inventor 51515 to solve Rubik’s Cube

MindCuber-RI is a robot that can solve the well-known Rubik’s Cube® puzzle. It is designed by David Gilday and Mike Dobson.


It is built using elements from a single LEGO® MINDSTORMS® Robot Inventor set 51515.

MindCuber-RI is significantly faster than previous MindCuber and PrimeCuber designs because it makes use of the fourth motor available in the Robot Inventor set to implement a faster tilting mechanism. Older MINDSTORMS and SPIKE Prime sets only included three motors.

Building instructions and software are now available on http://mindcuber.com/mindcuberri/mindcuberri.html alongside those for MindCuber for LEGO MINDSTORMS NXT, MindCub3r for LEGO MINDSTORMS EV3 and PrimeCuber for LEGO Education SPIKE® Prime.

Rotrics DexArm tricks Googles „I am not a Robot“ Captcha

Watch this video to learn how the smart robotic arm did it.

Smart Robotic Arm solves Googles „I am not a robot“ reCaptcha.

For more information on #Rotrics #DexArm, visit https://www.robots-blog.com or buy it directly at https://www.mybotshop.de/Rotrics-DexArm

If you have ideas, funny or useful, on what to do with a robot arm, contact us at [email protected]

Find the latest News on robots, drones, AI, robotic toys and gadgets at robots-blog.com. If you want to see your product featured on our Blog, Instagram, Facebook, Twitter or our other sites, contact us. #robots #robot #omgrobots #roboter #robotic #mycollection #collector #robotsblog #collection #botsofinstagram #bot #robotics #robotik #gadget #gadgets #toy #toys #drone #robotsofinstagram #instabots #photooftheday #picoftheday #followforfollow #instadaily #werbung #rotrics #dexarm #captcha #recaptcha #google #solution #solve