Archiv der Kategorie: Cobots

Robot plays „Rock, Paper, Scissors“ – Part 1/3

Veröffentlicht am von
Antworten

Gesture recognition with intelligent camera

I am passionate about technology and robotics. Here in my own blog, I am always taking on new tasks. But I have hardly ever worked with image processing. However, a colleague’s LEGO® MINDSTORMS® robot, which can recognize the rock, paper or scissors gestures of a hand with several different sensors, gave me an idea: „The robot should be able to ’see‘.“ Until now, the respective gesture had to be made at a very specific point in front of the robot in order to be reliably recognized. Several sensors were needed for this, which made the system inflexible and dampened the joy of playing. Can image processing solve this task more „elegantly“?

Rock-Paper-Scissors with Robot Inventor by Seshan Brothers. The robot which inspired me for this project

From the idea to implementation

In my search for a suitable camera, I came across IDS NXT – a complete system for the use of intelligent image processing. It fulfilled all my requirements and, thanks to artificial intelligence, much more besides pure gesture recognition. My interest was woken. Especially because the evaluation of the images and the communication of the results took place directly on or through the camera – without an additional PC! In addition, the IDS NXT Experience Kit came with all the components needed to start using the application immediately – without any prior knowledge of AI.

I took the idea further and began to develop a robot that would play the game „Rock, Paper, Scissors“ in the future – with a process similar to that in the classical sense: The (human) player is asked to perform one of the familiar gestures (scissors, stone, paper) in front of the camera. The virtual opponent has already randomly determined his gesture at this point. The move is evaluated in real time and the winner is displayed.

The first step: Gesture recognition by means of image processing

But until then, some intermediate steps were necessary. I began by implementing gesture recognition using image processing – new territory for me as a robotics fan. However, with the help of IDS lighthouse – a cloud-based AI vision studio – this was easier to realize than expected. Here, ideas evolve into complete applications. For this purpose, neural networks are trained by application images with the necessary product knowledge – such as in this case the individual gestures from different perspectives – and packaged into a suitable application workflow.

The training process was super easy, and I just used IDS Lighthouse’s step-by-step wizard after taking several hundred pictures of my hands using rock, scissor, or paper gestures from different angles against different backgrounds. The first trained AI was able to reliably recognize the gestures directly. This works for both left- and right-handers with a recognition rate of approx. 95%. Probabilities are returned for the labels „Rock“, „Paper“, „Scissor“, or „Nothing“. A satisfactory result. But what happens now with the data obtained?

Further processing

The further processing of the recognized gestures could be done by means of a specially created vision app. For this, the captured image of the respective gesture – after evaluation by the AI – must be passed on to the app. The latter „knows“ the rules of the game and can thus decide which gesture beats another. It then determines the winner. In the first stage of development, the app will also simulate the opponent. All this is currently in the making and will be implemented in the next step to become a „Rock, Paper, Scissors“-playing robot.

From play to everyday use

At first, the project is more of a gimmick. But what could come out of it? A gambling machine? Or maybe even an AI-based sign language translator?

To be continued…

Qviro Helps Robotics Buyers Make Transparent Choices with Biggest Marketplace

Veröffentlicht am von
Antworten

Qviro Revolutionizes Robotics Buying Experience

Qviro, one of the leading robotics platforms, introduces a groundbreaking marketplace, offering unparalleled transparency and choice. Users can effortlessly compare the full robotics market and access a vast selection of 211 cobots. 

The platform ensures transparent pricing, allowing buyers access to all cobot prices on Qviro. For added assistance, it provides an average cobot price of €27,158. Additionally, Qviro includes 400+ user reviews for informed decisions.

In the cobot category, Universal Robots leads with a 4.6 rating from over 41 user reviews. Their products excel in ease of use and integration, favored by engineers and enthusiasts.

For budget-conscious buyers, Elephant Robotics and Wlkata offer educational robots starting at $599. They provide cost-effective solutions for educational and hobbyist projects. Find Elephant Robotics‘ products at Elephant Robotics Products and Wlkata’s at Wlkata Products.

Sven De Donder, Co-CEO of Qviro, said, „Our user base in Europe and North America is growing exponentially due to unmatched transparency.“

Qviro transforms the robotics buying experience, offering an all-in-one solution for enthusiasts and professionals. With diverse options, transparent pricing, and a supportive user community, Qviro meets all your robotics needs.

About Qviro:

Qviro is a Belgium-based startup that is revolutionising the procurement process of industrial technology such as robots and machines through digitization. The company’s review platform, Qviro.com, provides factories and engineers with valuable insights and customer feedback to make confident purchasing decisions. At the same time, it offers vendors market intelligence and data to help them better understand their potential customers. As a SaaS platform, Qviro is dedicated to providing exceptional customer experiences and innovative solutions that drive growth and progress in the industry. To learn more about Qviro, visit www.Qviro.com.

Roboverse Reply leitet das EU-Projekt „Fluently“, das eine soziale Zusammenarbeit zwischen Menschen und Robotern mithilfe von KI ermöglicht

Veröffentlicht am von
Antworten

Roboverse Reply, das auf die Integration von Robotik-Lösungen spezialisierte Unternehmen der weltweit agierenden Reply Gruppe, leitet das von der EU finanzierte Projekt „Fluently“. Das Projekt zielt darauf ab, eine Plattform zu schaffen, die eine echte soziale Zusammenarbeit zwischen Menschen und Robotern in industriellen Umgebungen ermöglicht, indem sie die neuesten Fortschritte in der KI-basierten Entscheidungsfindung nutzt.

Ziel dieses dreijährigen Projekts ist es, eine Plattform sowie ein tragbares Gerät für Industriearbeiter und Roboter zu entwickeln, die den Maschinen ermöglichen, Sprache, Inhalt und Tonfall genauer zu interpretieren und Gesten automatisch in Roboteranweisungen umzuwandeln. Weiterer Bestandteil des Projekts ist der Aufbau des Trainingszentrums „Fluently RoboGym“, in dem Fabrikarbeiter und Roboter trainieren können, im Industrieprozess reibungslos zu interagieren.

Praktische Anwendungsfälle für die Mensch-Roboter-Kollaboration beziehen sich auf für die europäische Wirtschaft wichtige Wertschöpfungsketten, die hohe physische Belastungen und hohe Anforderungen an die menschliche Erfahrung sowie Kompetenz mit sich bringen. Dies betrifft z. B. die Demontage und das Recycling von Lithiumzellenbatterien, Prüf- und Montageprozesse in der Luft- und Raumfahrtindustrie sowie die Aufarbeitung komplexer Industrieteile mittels additiver Fertigung.

An dem Projekt sind zweiundzwanzig Partner beteiligt, darunter die Schweizer Universität SUPSI. Anna Valente, Leiterin des SUPSI-Labors für Automation, Robotik und Maschinen und Mitglied des Schweizer Wissenschaftsrats, fügt hinzu: „Das Projekt Fluently zielt darauf ab, Roboter zu Teamplayern auszubilden, die menschliche Arbeiter bestmöglich unterstützen. Als wissenschaftliche und technische Koordinatoren wollten wir mit Fluently einen wichtigen Beitrag zur Weiterentwicklung der Mensch-Roboter-Kollaboration leisten und gleichzeitig eine Best Practice und einen Proof of Concept (PoC) für integrativere sowie interaktive Ökosysteme schaffen.“

Das Projekt hat das erste Entwicklungsjahr erfolgreich abgeschlossen und erste Meilensteine erreicht. Das Team konzentriert sich aktuell auf drei Hauptarbeitspakete:

  • Design des Fluently Interfaces, bestehend aus dem Design des Fluently Geräts, Softwaretests und Integration in tragbare Steuerungs- und Robotersysteme;
  • Entwicklung von KI-Modellen, einschließlich Architekturdesign, Edge Computing, Training von RoboGym-Modellen und Unterstützung von Mensch-Roboter-Teamarbeit;
  • RoboGym-Design und -Implementierung, d. h. Festlegung der RoboGym-Spezifikationen und -Ziele sowie Entwicklung und Aufbau von drei Trainingsbereichen.

Das Fluently-System stützt sich auf innovative Technologien, um eine nahtlose Kommunikation zwischen Menschen und Robotern sicherzustellen. Die Verarbeitung natürlicher Sprache, Hardware für die freihändige Steuerung von Robotern aus der Ferne, Monitoring physiologischer Signale und Eye-Tracking werden im Rahmen dieses Projekts erforscht und integriert.  

„Wir sind stolz darauf, das innovative Fluently-Projekt zu koordinieren, das Partner aus Wissenschaft und Industrie zusammenbringt, um eine empathische Roboterplattform zu entwickeln, die Sprachinhalte, Tonfall und Gesten interpretieren kann und Industrieroboter für jedes Qualifikationsprofil einsetzbar macht“, kommentiert Filippo Rizzante, CTO von Reply. „Roboter, die mit Fluently ausgestattet sind, werden den Menschen bei physischen wie kognitiven Aufgaben unterstützen, lernen und Erfahrungen mit den menschlichen Teamkollegen sammeln.“

Kurzinterview: 4 Fragen an Etienne Lacroix, CEO of Vention

Veröffentlicht am von
Antworten
Etienne Lacroix, CEO Vention (Copyright Vention)

Robots-Blog: Wie ist die aktuelle Situation für kleine und mittelständische Unternehmen (KMU) bei der Automatisierung?

Etienne Lacroix: Bisher wurde Automatisierungstechnologie für die Fertigung mit hohem Durchsatz entwickelt, sodass sie für Unternehmen geeignet ist, die sich komplexe, maßgeschneiderte Integrationsdienste leisten können. Dadurch blieben kleine und mittlere Unternehmen zurück, die eigentlich von der Demokratisierung der Automatisierung hätten profitieren können. Durch neue Technologien und Ansätze ändert sich das jetzt.

Robots-Blog: Was sind die größten Herausforderungen und Vorteile der Automatisierung für kleine und mittlere Unternehmen?

Etienne Lacroix: Die größte Herausforderung für KMU liegt in den Kosten für die Automatisierung ihrer Produktionsabläufe. Die Kosten der Technologie führen in Kombination mit den Kosten eines externen Systemintegrators meist zu einer Investitionssumme, die sich nur dann amortisieren lässt, wenn Sie ein Hersteller mit hohem Durchsatz sind. Was auf dem Markt fehlt, sind Automatisierungstechnologien, die es allen Herstellern ermöglichen, profitabel zu automatisieren.

Foto: (Copyright Vention)

Robots-Blog: Welches Angebot bietet Vention und welchen Nutzen haben KMU davon?

Etienne Lacroix: Vention demokratisiert die industrielle Automatisierung durch eine intuitive Self-Service-Manufacturing Automation Platform (MAP). Mit Vention können Hersteller Lösungen in einer digitalen Umgebung entwerfen, automatisieren, bestellen und bereitstellen. Dies führt dazu, dass sich die Projektlaufzeiten um das Dreifache verkürzen und die Kosten um bis zu 40 Prozent sinken.

Robots-Blog: Gibt es einen Rat, den Sie KMU geben möchten, die sich mit der Automatisierung befassen?

Etienne Lacroix: Ja, natürlich! Erstens: Identifizieren Sie zunächst sich wiederholende, zeitaufwändige und fehleranfällige Prozesse und fangen Sie klein an. Zweitens: Wählen Sie einen Automatisierungspartner, der Transparenz über Kosten, Zeitpläne und Amortisierung bietet. Drittens sollten Sie bei Ihrem ersten Projekt von Anfang an ein funktionsübergreifendes Team aufstellen, dass das Projekt technisch umsetzt, aber auch die Menschen mit einbezieht, die später in dem automatisierten Umfeld arbeiten werden

Robots-Blog: Vielen Dank für das kurze Interview und die interessanten Einblicke.

Amazing Advancements in Soft Robotics

Veröffentlicht am von
1

Soft robotics represents a groundbreaking advancement in the field, standing apart from the rigid structures people usually associate with traditional robotic systems. Learn more about recent advances in this field and the many benefits.

The Era of Soft Robots

Nature and biology heavily influence soft robots, giving them the flexibility and ability to adapt to their surroundings. For example, some commercially available soft robotic designs mimic fish, octopi and worms.

Innovative materials such as shape-memory alloys, dielectric elastomers and liquid crystal elastomers are critical to soft robotics. These materials change their properties in response to various stimuli. Grippers on soft robots, made of high-tech elastomers, mold to the target object’s shape. This flexibility ensures a gentler and more adaptable grip than rigid robots, making them ideal for tasks like fruit picking. 

Soft robots also use self-healing materials made from shape-memory alloys. These alloys allow the robots to repair themselves after damage, increasing their operational life span and reducing maintenance needs.

As technology progresses, scientists outfit soft robots with sensory systems, enhancing their ability to understand their surroundings. For example, soft pressure sensors can tell a robot if it’s gripping too hard. Some researchers are even developing soft robots capable of working in swarms, emulating the behavior of fish, bees and birds. 

3D printing, a form of advanced manufacturing, has revolutionized how scientists design and produce intricate soft robotic parts, driving innovation and accessibility in this sector. Some robots incorporate the strengths of both rigid and soft systems, resulting in hybrids that offer improved strength, precision and flexibility. Instead of traditional motors, there’s a growing trend towards fluidic actuation. Robots use liquids or air for movement, making their movements more natural. 

Soft Robotics in Medicine

Robotics is revolutionizing various aspects of modern medicine. In rehabilitation and physiotherapy, soft robotic exosuits or exoskeletons support patients recovering from strokes, spinal cord injuries or surgeries. These devices gently guide and assist patients, helping them regain motor functions, relearn movements and restore strength.

In assistive medical devices, soft wearable robots are emerging to help those with mobility issues. The Wyss Institute at Harvard University developed a soft, wearable robotic glove that assists individuals with hand disabilities in performing day-to-day activities. This glove, made from soft elastomers, can assist in gripping objects, potentially improving rehabilitation outcomes.

Scientists at the City University of Hong Kong developed a soft robot capable of maneuvering inside the stomach and intestine. The robot can change shape and size, facilitating better imaging and allowing localized drug delivery or biopsies.

A collaboration between Boston Children’s Hospital and Harvard University resulted in a soft robotic sleeve that surgeons can place around the heart. This device helps the heart pump more efficiently in patients with heart failure, providing a potential alternative to organ transplants.

In diagnostics, soft robots simplify procedures like endoscopy, making it less invasive and patient-friendly. Patients can now swallow endoscopy capsules equipped with a camera and a tissue collection mechanism to get the same results traditionally obtained by putting patients under general anesthesia. 

Research teams at institutes like the Sant’Anna School of Advanced Studies in Italy have been working on developing soft robotic arms that can assist surgeons. Due to their soft and pliant design, these arms can navigate the body with minimal risk of damaging tissues or organs.

Soft Robotics in Marine Conservation

Equipped with sensors, soft robots can monitor water quality, track marine species and evaluate the health of habitats over prolonged periods. Their non-intrusive nature and versatility enable them to probe areas inaccessible to traditional robots. MIT’s Computer Science and Artificial Intelligence Laboratory developed a soft robotic fish named „SoFi“ that can swim naturally in the ocean, recording close-up videos of marine life and providing insights without alarming or disturbing the aquatic life.

Soft robots also offer the potential for marine clean-up efforts, such as removing pollutants like microplastics and oil spills. The WasteShark, developed by RanMarine Technology, is an ASV designed to „eat“ or collect trash in harbors and other waters close to the shore. This drone skims the water’s surface, collecting waste in its path, thereby aiding in marine clean-up.

The Ocean Exploration Trust’s E/V Nautilus expeditions have been using ROVs to explore and map uncharted coral reefs, helping scientists understand their structures, the species they harbor and their overall health. Similar soft robots can be deployed to plant sea grass and maintain coral reefs. 

ROVs like the Hercules, also from the E/V Nautilus expedition, have robotic arms that can collect geological and biological samples from the deep sea that can help scientists study ecosystems in abyssal regions, leading to new species discoveries and insights into deep-sea conservation needs.

The Challenges Ahead

Soft robotics faces challenges, but its vast potential is undeniable. A primary focus lies in developing innovative materials that combine durability, flexibility and responsiveness. While traditional actuators, like motors, aren’t suitable for soft robots, alternatives like pneumatic and hydraulic systems are on the rise, promising unparalleled autonomy.

Manufacturing these robots at scale is now more feasible due to advanced construction techniques and materials. Even as these robots retain flexibility, integrating crucial rigid components, like batteries, is becoming smoother. The scientific community aims to enhance the response times of soft actuation mechanisms to match or exceed traditional systems.

Safety remains a top priority in soft robotics, especially in applications involving humans or medical scenarios. Although the field recognizes the higher initial research and production costs, they believe ongoing advancements will reduce expenses. 

Guest article by Ellie Gabel. Ellie is a writer living in Raleigh, NC. She's passionate about keeping up with the latest innovations in tech and science. She also works as an associate editor for Revolutionized.

Robots-Blog.com at Automatica 2023

Veröffentlicht am von
Antworten

Robot-based automation: 3 tips for a time and cost-efficient implementation

Veröffentlicht am von
1

Why no-code & low-code tools have become indispensable in robotics

Using robots is almost always worthwhile for companies. They can reduce labor costs, relieve employees, and make production more flexible – because the required batch sizes are becoming smaller and production processes more individual. In addition, a robot or cobot offers another major advantage: it can work without breaks and fatigue, thereby increasing product quality and reducing scrap.

With modern robot systems, almost all processes can now be automated. Usually, robots take over simple, dirty, monotonous, physically demanding, or even dangerous tasks. However, with the right hardware and, above all, software, very complex or particularly demanding tasks, so-called „Advanced Robotics“ applications, can also be solved. Examples of this include the assembly of flexible and bendable components such as cables, wires, or hoses or force-controlled surface processing.

When teach points can be transferred from the real robot back to the programming software as well, such a solution seamlessly integrates into the commissioning process and saves unexpected effort; Source: Ridvan – stock.adobe.com

Following the no-code/low-code trend, there are various software solutions on the market that enable graphical and therefore simplified and faster programming. The advantage is that no special programming skills are required. The portfolio ranges from manufacturer-specific solutions to independent offerings that can be used to program robots from different manufacturers with one single software. Especially in the latter case, experts recommend using tools that automatically generate native robot code for the particular robot controller instead of controlling the robot arm via a separate IPC.

In the first case, users remain flexible when it comes to adjustments or optimizations during operation and avoid a lock-in effect, as they can continue to program the robot in the traditional way using line code even without using the software.

Whether with external engineering tools or line code, there are factors on the path to robot-based automation that users often underestimate and therefore do not pay enough attention to. How to avoid three of the most important stumbling blocks will be briefly explained below.

No-code/low-code tools simplify and speed up robot programming thanks to their template-based approach; Source: ArtiMinds Robotics GmbH

FACTOR 1: PROGRAMMING EFFORT

The time required for programming an application is usually not underestimated, but there are other pitfalls in this phase: for example, process tolerances and variances that have not been taken into account or the increased complexity when incorporating sensors or establishing a communication between the robot and a PLC. In addition, programming a system is often a tailor-made and complex solution that is difficult to adapt. Moreover, programmers often have their own style, which can make the resulting code or program difficult to understand and modify for other programmers. At this point, the market supports the user with the aforementioned no-code/low-code solutions. For example, with pre-defined function blocks, programs can be constructed and structured in a clear and understandable manner for others. Process tolerances and variances can also be automatically compensated, analyzed, and optimized by using the right software. If the corresponding interfaces are already integrated, the effort required to connect sensors or set up a PLC communication is also immensely reduced.

FACTOR 2: EFFORT DURING COMMISSIONING

A rule of thumb states that the cost of the robot itself is only about one-third of the initial cost of the cell, and experience shows that around 45 percent of the typical costs are incurred during ramp-up. This is because users often underestimate the time required for commissioning. Although the system is programmed offline and simulated throughout in advance, differences between theory and practice often become apparent during commissioning.

Thus, despite good preparation, the process can take significantly longer than planned, and adjustments and changes can quickly become expensive In addition, factors that were not apparent during digital preparation now need to be addressed on-site during commissioning. This makes this phase difficult to calculate. With consistent tools, the ramp-up can be implemented in a controlled manner and without great loss of time, so that this phase does not become a cost driver. It is important to combine simulation, programming, sensors, and data analysis in one single software package. This way, the engineering chain becomes consistent without the user having to compromise on functionality.

Programs can be structured and made traceable using pre-defined function blocks. Before commissioning, the process can be simulated as realistically as possible in a 3D simulation environment and tested; Source: ArtiMinds Robotics GmbH

This makes changes and adjustments faster, more flexible and easier. With ideally automatically generated robot code and the ability to transfer teach points back from the real robot into the software, such a solution integrates seamlessly and optimally into existing commissioning and maintenance processes. This also offers the greatest flexibility in terms of online and offline programming, allowing the user to choose the best option and easiest way for the respective task.


FACTOR 3: CHANGES DURING THE LIFECYCLE OF THE CELL

Even when the robot is running, there is still a danger that is often not considered: Over the system runtime, numerous changes in general conditions can occur that require adaptation of the programming.

These can be vibrations and shocks, for example caused from forklifts or other machines, wear and tear of tools, replacement parts that react differently than the previous components, changes in workpiece batches, and the space available in the hall or a change of the operating personnel. Changed lighting conditions and temperature conditions or the difference between a cold-started and warmed-up robot can also have an impact.

Software that standardizes and simplifies programming allows the user to react simply, quickly, and flexibly to these and many other changes and to make necessary adjustments in the program itself. If the worker uses a tool that also makes changes or the resulting consequences visible early on in terms of forces, cycle times, or defects and quality, it becomes easier to analyze and derive possible optimizations, which makes the user best prepared.

A guest article by ArtiMinds Robotics

Are We Ready for Humanoid Robots?

Veröffentlicht am von
1

With the development of AI, robots have become a lot smarter. A quick Google or Youtube search will reveal many cases of people using advanced robots. For example, videos of robots packing shelves in factories or, even more impressive, the Ocean One Robot, an advanced humanoid that explores shipwrecks and plane crashes. 

These videos make many wonder how far we are from using such robotics in everyday life. Learn what today’s robots are capable of, what potential challenges need to be solved and if humanoids are ready for daily life.

https://unsplash.com/de/fotos/jIBMSMs4_kA
HD-Foto von Possessed Photography (@possessedphotography) https://unsplash.com/

3 Humanoids Robots Helping Humans Today

One reason advanced humanoid robots are in demand is their ability to handle dangerous and repetitive operations. This frees up humans to focus on other essential, safer tasks. Current AI robots such as humanoids and cobots are already assisting humans by completing various tasks — bomb disposal, surgery, packing items in grocery stores, self-driving vehicles and much more. 

One industry that frequently utilizes AI robots is the manufacturing sector. They mostly complete repetitive assignments such as packing items, material handling, assembly and welding. This speeds up production time and allows humans to tackle more complex or demanding tasks. Here are three different humanoid robots helping people. 

  1. Digit

Agility Robotics has developed a humanoid robot well-suited for many tedious operations. The humanoid is called Digit and has fully functional limbs making it excellent at unloading packages from trailers and also delivering them. Digit is equipped with sensors in his torso to help him easily navigate complex environments. 

  1. Nadine

Nadine is a realistic-looking social humanoid robot with various facial expressions and movements. She was developed in Singapore by researchers from the Nanyang Technological University. Nadine can recognize different gestures, faces, objects and is able to perform various social tasks associated with customer service. 

  1. Promobot

Promobot is a humanoid that is suitable for many different service-oriented roles. In hotels, promobot can recognize guests, print receipts, issue keycards and check guests in. This humanoid is customizable and can even work as a medical assistant — measure blood oxygen and blood sugar levels.

Are Humanoids Ready for Daily Life?

Today’s humanoids are undoubtedly impressive, but AI robots have yet to reach the level of generative artificial intelligence — an advanced form of AI capable of holding detailed conversations when prompted. Many companies aim to combine generative AI with advanced robotics to make it more applicable for a wider variety of use cases. 

Since most AI machines are developed for the use of single tasks, they tend to struggle when taking on multiple operations simultaneously. In other words, they aren’t very good at multitasking. This complex aspect would need to be addressed for AI robots to become a reality in daily life. The most advanced form of AI robots available today are self-driving cars, which have a long way to go before they are truly self-driving. 

It is the same with humanoid robots. Although many of the AI robots available are amazing, it is clear there are still advancements needed, especially in the case of processing abilities. AI robots will need to understand a wide variety of interactions no matter how they are carried out — voice, keyboard commands, hand gestures and sometimes even facial expressions. 

For AI humanoids to be applicable in daily life, humans need a deeper understanding of how they operate — training might be required. 

Potential Challenges to Overcome With Future Humanoids

One of the biggest problems with AI humanoids today is their battery life. They can usually only work for an hour or two and then require charging. While the goal would be to use them for multiple hours on end, another approach might be to increase the battery life by a few hours and add fast charging. 

In terms of complex and challenging tasks, many humanoids and cobots are quite advanced and can solve them with relevant ease. However, this usually means they lack in other areas, such as movement. In most cases, the humanoid has advanced movement or impressive processing abilities, but not both. 

In addition, the technology today’s humanoids use will also need further improvements. Better censoring capabilities are necessary in terms of in-depth cameras, voice and visual sensors to make them more applicable in modern life. For humanoids to become more widely used, their movement and processing abilities require further refinement. 

Humanoids also need to operate safely and effectively while working with multiple humans at the same time. The robot will need to comprehend numerous interactions with different people simultaneously to react appropriately. The current training methods used with humanoids today are slow and would need further refinements to make them available for daily life. 

Humanoids Robots Still Have a Long Way to Go

The advance of technology and AI is astounding, especially when combined to create robots that assist humans with numerous tasks. However, there are still a few areas where humanoids need refinement to become suitable for everyday use. Undoubtedly, humans will benefit significantly from utilizing advanced AI robotics in their daily life, but for this to become a reality, humanoids still have a long way to go.

Guest article by Ellie Gabel. Ellie is a writer living in Raleigh, NC. She's passionate about keeping up with the latest innovations in tech and science. She also works as an associate editor for Revolutionized.

Weltweit abgeschiedenster Roboter automatisiert Wiederaufforstung im Amazonas

Veröffentlicht am von
2

Ein Pilotprojekt von ABB Robotics und der US-amerikanischen Non-Profit-Organisation Junglekeepers zeigt auf, welche Rolle Cloudtechnologie für eine schnellere, effizientere und skalierbare Wiederaufforstung spielen kann.

ABB Robotics unterstützt Junglekeepers bei ihrem Vorhaben, rund 22.000 Hektar Amazonas-Regenwald zu schützen und die Entwaldung umzukehren. In einer bislang einzigartigen Demonstration automatisiert der kollaborative Roboter (Cobot) YuMi von ABB Pflanzarbeiten an einem Forschungs- und Versuchsstandort mitten im Dschungel. Dabei beschleunigt er das Verfahren erheblich, so dass die Freiwilligen von Junglekeepers ihre wertvolle Zeit und Ressourcen für bedeutendere Arbeiten einsetzen können.

Pilotprojekt von ABB Robotics zur Wiederaufforstung im Amazonas: Im Rahmen des Pilotprogramms setzt YuMi jeden Morgen rund 640 Saatgutbeutel ein.

Mit Hilfe der RobotStudio Cloud-Technologie von ABB simulieren, optimieren und realisieren ABB-Experten die Programmierung für YuMis Tätigkeiten im Regenwald vom 12.000 Kilometer entfernten Västerås in Schweden aus und ermöglichen damit den abgeschiedensten Robotereinsatz der Welt.

„Die Zusammenarbeit von ABB und Junglekeepers zeigt, dass Roboter- und Cloudtechnologien eine zentrale Rolle bei der Bekämpfung der Entwaldung spielen können. Letztere zählt zu den Hauptverursachern des Klimawandels“, sagt Sami Atiya, Leiter des Geschäftsbereichs Robotik & Fertigungsautomation von ABB. „Unser Pilotprojekt mit dem abgeschiedensten Robotereinsatz der Welt ermöglicht die Automatisierung stark repetitiver Aufgaben. So haben die Ranger mehr Zeit für wirkungsvollere Arbeiten im Regenwald und können das Land, auf dem sie leben, besser schützen.“

Pilotprojekt von ABB Robotics zur Wiederaufforstung im Amazonas: YuMi übernimmt repetitive Aufgaben, damit die Ranger von Junglekeeper mehr Zeit für wirkungsvollere Arbeiten haben.

In einem Forschungs- und Versuchslabor in einer abgeschiedenen Region im peruanischen Amazonasgebiet wurde ein YuMi-Cobot installiert, um zentrale Aufgaben bei der Einpflanzung von Saatgut zu automatisieren – bisher eine rein manuelle Tätigkeit. Der Cobot gräbt ein Loch in die Erde, legt das Saatgut ein, verdichtet die Erde darüber und markiert die Stelle mit einem farbigen Etikett. Mit dem Einsatz von YuMi kann Junglekeepers täglich eine Fläche von zwei Fußballfeldern wieder bepflanzen. Dank der Automatisierung können die Freiwilligen von Junglekeepers ihre wertvolle Zeit und Ressourcen für wirkungsvollere Arbeiten einsetzen. Dazu gehören etwa Patrouillen zur Abschreckung illegaler Holzfäller, die Aufklärung der lokalen Bevölkerung über den Erhalt des Regenwaldes und das Einpflanzen von jungen Bäumen.

Die vollständig abgelegene und autonome Cobot-Installation löst ein weiteres Problem: Menschen zu finden, die für einen längeren Zeitraum an diesem abgelegenen Ort im Dschungel arbeiten wollen. Nach der ersten Installation kann YuMi seine Aufgaben selbstständig ausführen und muss sich nur bei Bedarf einer Fehlerbehebung unterziehen.

„Wir haben bisher 20 Prozent des gesamten Amazonas-Regenwaldes verloren, und ohne den Einsatz von Technologie kommen wir beim Naturschutz nicht mehr weiter“, erklärt Moshin Kazmi, Mitgründer von Junglekeepers. „YuMi vor Ort zu haben ist eine ausgezeichnete Möglichkeit, unsere Ranger mit neuen Arbeitsweisen vertraut zu machen. Er beschleunigt und erweitert unsere Aktivitäten und bringt unsere Mission voran.“

Die Zerstörung des Amazonas-Regenwaldes durch menschliche Eingriffe wie Abholzung und Brandrodung zur Gewinnung von Flächen für die Landwirtschaft trägt erheblich zu den verheerenden Auswirkungen des Klimawandels bei. Seit 1985 wurden schätzungsweise mehr als 870.000 km² des Amazonas-Regenwaldes gerodet – eine Fläche, die größer ist als Frankreich, das Vereinigte Königreich und Belgien zusammen.1 Da bereits mehrere Milliarden Bäume verschwunden sind, erwärmt sich die Region schnell.

Pilotprojekt von ABB Robotics zur Wiederaufforstung im Amazonas: Der ABB-Cobot YuMi kümmert sich um die Saatgutbeutel in der Basisstation von Junglekeepers.

„Der Amazonas ist in Gefahr. Um ihn zu retten, müssen wir Technologie, Wissenschaft und lokales Wissen bündeln, andernfalls wird es zu spät sein. Der Regenwald kann gerettet werden, aber wir müssen alle diese Elemente zusammenführen, um wirklich etwas zu bewirken“, betont Dennis del Castillo Torres, Director of Forest Management Research am Peruvian Amazon Research Institute. „Es ist sehr wichtig, Spitzentechnologie und Naturschutz zu vereinen. Es gibt viele Technologien, die wir für den Erhalt des Waldes nutzen können. Dieser Roboter kann die Wiederaufforstung beschleunigen, muss aber sehr gezielt eingesetzt werden. Wir sollten ihn in stark entwaldeten Gebieten zur Beschleunigung der Neubepflanzung nutzen.“

Das Pilotprojekt wird durch die RobotStudio Cloud-Technologie von ABB unterstützt, die Teams auf der ganzen Welt ermöglicht, in Echtzeit zusammenzuarbeiten. Diese innovative Art der Fernprogrammierung ermöglicht ein neues Maß an Flexibilität und sofortiger Optimierung, was die Effizienz und Resilienz steigert und Zeitverluste bei der Bepflanzung verhindert. Gestützt auf mehr als 25 Jahre Erfahrung in der Offline-Programmierung bietet RobotStudio branchenführende digitale Technologie und gewährleistet eine 99-prozentige Übereinstimmung zwischen Simulation und Realität. So können Anwender den Zeitaufwand für Tests von Roboterlösungen um 50 Prozent reduzieren und Produktionsunterbrechungen vollständig vermeiden.

Pilotprojekt von ABB Robotics zur Wiederaufforstung im Amazonas: solarbetriebener und mit der Cloud verbundener YuMi-Cobot im peruanischen Amazonasgebiet

Das Pilotprojekt von ABB Robotics im Amazonasgebiet unterstützt das Ziel der Division, mit intelligenten Roboter- und Automatisierungslösungen zu einer nachhaltigen Transformation beizutragen und Unternehmen zu helfen, ihre Produktivität zu steigern, Abfallmengen zu verringern und die Effizienz zu maximieren. 2022 arbeitete ABB Robotics mit der gemeinnützigen Organisation und dem globalen Netzwerk Parley for the Oceans zusammen, das sich gegen die Plastikverschmutzung und Zerstörung der Weltmeere einsetzt. ABB Roboter stellten per additivem 3D-Druck personalisierte Designobjekte aus recyceltem Parley Ocean Plastic® her.

Auf Wunsch von Junglekeepers wird das Pilotprojekt mit RobotStudio Cloud und YuMi im Regenwald über rund sechs Wochen laufen (im Mai und Juni 2023). Nach Abschluss des Pilotprogramms wird ABB Möglichkeiten zur weiteren Unterstützung von Junglekeepers ausloten. Außerdem will das Unternehmen prüfen, wie seine Roboterlösungen und Cloudtechnologien die nachhaltige Transformation zusätzlich maßgeblich fördern können.