Zaragoza, 21. April 2022 – LoCo CORP. gründete sich an der Universität von Zaragoza als Antwort auf den Mangel an fortschrittlichen und gleichzeitig erschwinglichen Robotiklösungen für Lernzwecke. Das Start-Up begann 2021 mit der Entwicklung erster Roboterbausätze für den Unterricht. Zu den zentralen Lerninhalten gehören zum Beispiel Themen wie Programmierung, Mechanik, Logik und Design. Vor wenigen Wochen stellte das Unternehmen dann die ersten Lernroboter vor: NOCTIS und AUREL.
LoCo CORP. arbeitet bereits mit Bildungs- und Kulturzentren in Zaragoza zusammen. Die Einrichtungen konnten ihren Schülern mithilfe der Bausätze eine neuartige Lernerfahrung ermöglichen, da die Roboter die Schüler:innen spielerisch an technische Themen heran führen. Parallel dazu hat LoCo CORP. einen Großteil seines Kapitals in die Entwicklung, Erprobung und Validierung einer eigenen Serie von Robotern investiert.
„Die Entwicklung von Lernrobotern ist keine leichte Aufgabe: Es geht um weit mehr als nur die reine Technik. Es kann sehr frustrierend sein sich technisches Wissen anzueignen. Wenn ein Projekt funktioniert, ist das sehr lohnend, allerdings muss man in der Regel viel Zeit und Mühe in den Prozess investieren. Wir wollen uns abheben, indem wir unseren Robotern eine fantasievolle Rahmengeschichte geben, die junge Roboterfans zusätzlich motivieren soll.“, sagt Manuel Bernal Lecina, Gründer von LoCo CORP.
Viele autodidaktische Bastler (auch Maker genannt) zitieren in ihren Projekten beliebte Strömungen der Popkultur. Auch deshalb hat sich LoCo CORP. dazu entschlossen sich nicht nur auf die Entwicklung der Roboterbausätze zu beschränken, sondern diese auch in ein eigenes fiktives Universum einzubetten – das „LoCoVerse“. Dabei handelt es sich um ein pädagogisches Ökosystem voller Geschichten, Kurse, Tutorials, Tipps und Unterhaltung.
Dazu Manuel Bernal Lecina, Gründer von LoCo CORP.: „Wir wollen qualitativ hochwertige Inhalte bereitstellen, die junge Leute für MINT-Themen begeistern. So fördern wir die Ausbildung angehender Ingenieur:innen und Wissenschaftler:innen.“
Das spanische Unternehmen möchte in Europa, wo es ein großes Wachstumspotenzial gibt, zu einer festen Größe bei der Ausbildung von MINT interessierten Menschen werden und so die Bildungsziele von Familien und Schulen unterstützen.
Künstliche Intelligenz (KI) gilt als Schlüsseltechnologie und birgt enormes wirtschaftliches Potenzial. Doch ein Blick in deutsche Produktionshallen zeigt noch ein anderes Bild: Lediglich 6,8 Prozent der Unternehmen aus den Bereichen Maschinenbau und Elektrotechnik setzen KI-Technologien ein (Stand 2019). Dabei birgt KI gerade für das produzierende Gewerbe zahlreiche Potenziale.
Künstliche Intelligenz ist ein Überbegriff, der den Ansatz beschreibt, mit Maschinen Probleme zu lösen und menschliche Intelligenz zu imitieren. Dabei spielt insbesondere ein Teilbereich, das Machine Learning (Maschinelles Lernen), in Unternehmen und Produktionen eine entscheidende Rolle. Machine Learning bedeutet, dass ein System aus Beispielen lernt und diese nach der Lernphase verallgemeinern kann.
In der Produktion kommt Machine Learning beispielsweise im Bereich Predictive Analytics zum Einsatz. Dort wird KI als Teil von Vorhersagemodellen zur Überwachung und Wartung von Produktionsanlagen eingesetzt, um frühzeitig auf kritische Zustände reagieren zu können.
Auch das Wissensmanagement greift für die Auswertung von internen Informationen und Daten auf Machine Learning zurück. Daten von Fertigungslinien, Lieferketten, aber auch von einzelnen Produkten werden für Unternehmensprozesse, die Produktentwicklung und neue Geschäftsmodelle ausgewertet. Ohne den Einsatz von KI wäre eine Analyse aufgrund der schieren Datenmenge nicht möglich.
Mit KI und Robotik Handarbeitsplätze automatisieren
Machine Learning, häufig in Kombination mit Machine Vision, kommt auch in den Bereichen Robotik und Automatisierung, Sensorik und bei fahrerlosen Transportsystemen zum Einsatz. Für die Fertigung ist dabei das Zusammenspiel von KI und Robotik ein wichtiger Schlüssel für die Zukunft.
KI-Produkte, wie beispielsweise Robotersteuerungen, ermöglichen es unter anderem, Handarbeitsplätze zu automatisieren. Ein nicht zu vernachlässigender Vorteil, denn Arbeitskräfte sind rar und der Mangel verschärft sich in den Jahren weiter, wie der Deutsche Industrie- und Handelskammertag (DIHK) prognostiziert. Übernehmen Roboter auch Aufgaben, für die es bisher die Flexibilität eines Menschen brauchte, sorgt das für die Entlastung der Stammbelegschaft, eine Auslastung der Maschinen und sichert auf lange Sicht die Wettbewerbsfähigkeit.
Robuster Umgang mit Varianzen
KI-Steuerungen wie MIRAI von Micropsi Industries ergänzen die native Steuerung eines Roboters. Der Roboter erhält dank einer Kamera und einem neuronalen Netzwerk die Auge-Hand-Koordination und eine vergleichbare Flexibilität wie ein Mensch. Ein solches intelligentes Robotersystem lernt bei neuen Aufgaben, bei anders geformten oder positionierten Werkteilen oder bei vergleichbaren Varianzen schnell, was es zu tun hat und passt bei Bedarf seine Bewegungen in Echtzeit eigenständig an. Ob es sich um das Picken einzelner Teile, Zustellbewegungen oder Fügen und Verfolgen handelt: Zahlreiche Tätigkeiten sind mit einer einzigen kleinen Kamera am Roboter-Handgelenk umsetzbar.
Diese Fähigkeiten lassen sich mit MIRAI durch menschliche Demonstration trainieren. Weder KI- noch Programmierkenntnisse sind erforderlich. Das Know-how bleibt selbst ohne KI-Fachkräfte im Unternehmen. Dem Roboter muss dafür das Ziel einige Male in typisch vorkommenden Varianzen mit der Kamera gezeigt werden. Die KI verallgemeinert im Anschluss die gezeigten Daten. Ein solches System kann in wenigen Stunden trainiert und sogar neu trainiert werden. Selbst eine Fertigung im High Mix-/Low-Volume lässt sich so rentabel automatisieren. Was intelligente Robotiklösungen bereits in der Praxis leisten, zeigen die folgenden Beispiele.
Intelligentes Handling-System bei ZF
Der Technologiekonzern ZF stand vor der Herausforderung, die Werkstückzufuhr einer großvolumigen Frässtation, in der Zahnräder produziert werden, zu automatisieren. Im Werkprozess werden Metallringe aus einer Kiste entnommen und auf ein Förderband gelegt, um später in die Produktion der Zahnräder einzufließen. Die Schwierigkeit: Der Produktionsschritt ist sehr variantenreich, da sich die Ringe in der angelieferten Gitterbox verschieben und dadurch zufällig angeordnet sind. Auch Platzierung und Form der Box variieren. Wechselnde Lichtverhältnisse stellen eine zusätzliche Herausforderung dar. Außerdem ist die Oberfläche der Ringe metallisch glänzend, teilweise ölverschmiert oder korrodiert, was eine klassische Automatisierung unmöglich machte.
Heute ist die KI-Steuerung MIRAI und ein Cobot vom Modell UR10e bei ZF in einer automatisierten Werkstückaufnahme im Einsatz. Mit seiner eigenen Steuerung bringt der Cobot sich über den Ringen in der Kiste in Position. Nun übernimmt das MIRAI-System die Kontrolle: Es bewegt den Roboter selbstständig zum nächsten Ring und bringt den Greifer in die korrekte dreidimensionale Greifposition. Danach übernimmt der UR10e wieder, nimmt den Ring auf und bewegt ihn zum Ablegen auf das Förderband. Das komplette Einrichten des Roboters dauerte lediglich wenige Tage – MIRAI löste in kürzester Zeit ein lang bestehendes Problem.
BSH sucht mit KI nach Kältemittellecks
An ihrem spanischen Standort stellt die BSH Hausgeräte GmbH Kühl- und Gefrierschränke her. Im Herstellungsprozess muss das Unternehmen die Kupferrohrleitungen der Kühlschränke auf Leckagen testen. Für die sogenannte Dichtheitsprüfung wird eine Schnüffelsonde entlang der Kupferrohrleitungen und Kompressoren geführt, um Lötstellen auf austretendes Gas und Kältemittel zu prüfen. Das Besondere: Jede Rückseite der hergestellten Kühlschränke ist einzigartig, was Position, Farbe und Form der Lötpunkte angeht. Für einen herkömmlichen Roboter sind solche Varianzen ein unüberwindbares Hindernis. Der monotone Prüfprozess blieb dem Menschen vorbehalten – bis jetzt.
Den Prüfprozess übernimmt bei BSH nun eine Robotik-Komplettlösung den Prüfprozess. Dank der integrierten Robotersteuerung MIRAI ist es dem Roboter möglich, alle zu prüfenden Lötstellen verlässlich zu identifizieren und die Schnüffelsonde millimetergenau heranzuführen – unabhängig von Position, Form oder Farbe. Das System reagiert in Echtzeit auf seine Umwelt und handhabt selbst unvorhergesehene Abweichungen präzise. Die Roboterfähigkeiten wurden von Mitarbeitenden bei BSH durch menschliche Demonstration in nur wenigen Stunden trainiert. Weder Programmier- noch KI-Kenntnisse waren erforderlich. BSH konnte mit der Automatisierungslösung die laufenden Betriebskosten senken und Wartungen und Fehlerbehebungen reduzieren.
Neue Technologien als Wettbewerbsvorteil
Die Beispiele zeigen, dass Unternehmen mit KI sehr viel bewirken können: KI ermöglicht mehr Flexibilität, Unabhängigkeit, Effizienz und nicht zuletzt Resilienz. Nicht unwichtig in Zeiten wie diesen. Neue Technologien sollte dabei als Türöffner zu mehr Automatisierung verstanden werden. Leistungen, die bislang von Menschen oder Maschinen erbracht wurden, können nun von einer Software geliefert werden. Das ist nicht nur vorteilhaft beim drastisch zunehmenden Arbeitskräftemangel. Es erhöht auch die Flexibilität, Nachvollziehbarkeit und Zuverlässigkeit von Produktionsprozessen und verschafft einen dauerhaften Wettbewerbsvorsprung.
Robot’s Smartest Developer Platform, Now with ROS 2 and Python Support
BEDFORD, Mass., April 5, 2022 /PRNewswire/ — iRobot Corp. (NASDAQ: IRBT), a leader in consumer robots, today is expanding its educational product lineup with the launch of the Create® 3 educational robot – the company’s most capable developer platform to date. Based on the Roomba® i3 Series robot vacuum platform, Create 3 provides educators and advanced makers with a reliable, out of the box alternative to costly and labor-intensive robotics kits that require assembly and testing. Instead of cleaning people’s homes,1 the robot is designed to promote higher-level exploration for those seeking to advance their education or career in robotics.
In Celebration of National Robotics Week, iRobot launched the Create® 3 Educational Robot – the company’s most capable developer platform to date. Now with ROS 2 and Python Support, Create 3 provides educators and advanced makers with a reliable, out of the box alternative to costly and labor-intensive robotics kits that require assembly and testing. Create 3 is designed to promote higher-level exploration for those seeking to advance their education or career in robotics.
The launch of Create 3 coincides with National Robotics Week, which began April 2 and runs through April 10, 2022. National Robotics Week, founded and organized by iRobot, is a time to inspire students about robotics and STEM-related fields, and to share the excitement of robotics with audiences of all ages through a range of in-person and virtual events.
„iRobot is committed to delivering STEM tools to all levels of the educational community, empowering the next generation of engineers, scientists and enthusiasts to do more,“ said Colin Angle, chairman and CEO of iRobot. „The advanced capabilities we’ve made available on Create 3 enable higher-level students, educators and developers to be in the driver’s seat of robotics exploration, allowing them to one day discover new ways for robots to benefit society.“
With ROS 2 support, forget about building the platform, and focus on your application: The next generation of iRobot’s affordable and trusted all-in-one mobile robot development platform, Create 3 brings a variety of new functionalities to users, including compatibility with ROS 2, an industry-standard software for roboticists worldwide. Robots require many different components, such as actuators, sensors and control systems, to communicate with each other in order to work. ROS 2 enables this communication, allowing students to speed up the development of their project by focusing more on their core application rather than the platform itself. Learning ROS 2 also gives students valuable experience that many companies are seeking from robotics developers.
Expand your coding skills even further with Python support: iRobot also released a Python Web Playground for its iRobot Root® and Create 3 educational robots, providing a bridge for beginners to begin learning more advanced programming skills outside of the iRobot Coding App. Python, a commonly used coding language, enables users to broaden the complexity of projects that they work on. The iRobot Education Python Web Playground allows advanced learners and educators to program the iRobot Root and Create 3 educational robots with a common library written in Python. This provides users with a pathway to learn a new coding language, opening the door to further innovation and career development.
With more smarts, Create 3 lets you do more: As a connected robot, Create 3 comes equipped with Wi-Fi, Ethernet-over-USB host, and Bluetooth. Create 3 is also equipped with a suite of intelligent technology, including an inertial measurement unit (IMU), optical floor tracking sensor, wheel encoders, and infrared sensors for autonomous localization, navigation, and telepresence applications. Additionally, the robot includes cliff, bump and slip detection, along with LED lights and a speaker.
A 3D simulation of Create 3 is also available using Ignition Gazebo for increased access to robotics education and research.
VEXcode EXP is now available in a web-based version for Chrome browsers. The web-based version can be reached by navigating to codeexp.vex.com and contains all of the features and functionality of VEXcode EXP, but without the need to download or install anything! The new web-based version of VEXcode makes it easier for teachers and students to access projects from anywhere, at any time, on any device – including Chromebooks!
In addition to the built-in Help and Tutorials, the STEM Library contains additional resources and support for using web-based VEXcode EXP. Within the STEM Library you can find device-specific articles for connecting to web-based VEXcode EXP, loading and saving projects, updating firmware, and more. View the VEXcode EXP section of the STEM Library to learn more.
Web-based versions of VEXcode IQ and VEXcode V5 are in the works and will be available soon.
Establishing human-robot trust isn’t always easy. Beyond the fear of automation going rogue, robots simply don’t communicate how they are doing. When this happens, establishing a basis for humans to trust robots can be difficult.
Now, research is shedding light on how autonomous systems can foster human confidence in robots. Largely, the research suggests that humans have an easier time trusting a robot that offers some kind of self-assessment as it goes about its tasks, according to Aastha Acharya, a Draper Scholar and Ph.D. candidate at the University of Colorado Boulder.
Acharya said we need to start considering what communications are useful, particularly if we want to have humans trust and rely on their automated co-workers. “We can take cues from any effective workplace relationship, where the key to establishing trust is understanding co-workers’ capabilities and limitations,” she said. A gap in understanding can lead to improper tasking of the robot, and subsequent misuse, abuse or disuse of its autonomy.
To understand the problem, Acharya joined researchers from Draper and the University of Colorado Boulder to study how autonomous robots that use learned probabilistic world models can compute and express self-assessed competencies in the form of machine self-confidence. Probabilistic world models take into account the impact of uncertainties in events or actions in predicting the potential occurrence of future outcomes.
In the study, the world models were designed to enable the robots to forecast their behavior and report their own perspective about their tasking prior to task execution. With this information, a human can better judge whether a robot is sufficiently capable of completing a task, and adjust expectations to suit the situation.
To demonstrate their method, researchers developed and tested a probabilistic world model on a simulated intelligence, surveillance and reconnaissance mission for an autonomous uncrewed aerial vehicle (UAV). The UAV flew over a field populated by a radio tower, an airstrip and mountains. The mission was designed to collect data from the tower while avoiding detection by an adversary. The UAV was asked to consider factors such as detections, collections, battery life and environmental conditions to understand its task competency.
Findings were reported in the article “Generalizing Competency Self-Assessment for Autonomous Vehicles Using Deep Reinforcement Learning,” where the team addressed several important questions. How do we encourage appropriate human trust in an autonomous system? How do we know that self-assessed capabilities of the autonomous system are accurate?
Human-machine collaboration lies at the core of a wide spectrum of algorithmic strategies for generating soft assurances, which are collectively aimed at trust management, according to the paper. “Humans must be able to establish a basis for correctly using and relying on robotic autonomy for success,” the authors said. The team behind the paper includes Acharya’s advisors Rebecca Russell, Ph.D., from Draper and Nisar Ahmed, Ph.D., from the University of Colorado Boulder.
The research into autonomous self-assessment is based upon work supported by DARPA’s Competency-Aware Machine Learning (CAML) program.
In addition, funds for this study were provided by the Draper Scholar Program. The program gives graduate students the opportunity to conduct their thesis research under the supervision of both a faculty adviser and a member of Draper’s technical staff, in an area of mutual interest. Draper Scholars’ graduate degree tuition and stipends are funded by Draper.
Since 1973, the Draper Scholar Program, formerly known as the Draper Fellow Program, has supported more than 1,000 graduate students pursuing advanced degrees in engineering and the sciences. Draper Scholars are from both civilian and military backgrounds, and Draper Scholar alumni excel worldwide in the technical, corporate, government, academic, and entrepreneurship sectors.
Draper
At Draper, we believe exciting things happen when new capabilities are imagined and created. Whether formulating a concept and developing each component to achieve a field-ready prototype, or combining existing technologies in new ways, Draper engineers apply multidisciplinary approaches that deliver new capabilities to customers. As a nonprofit engineering innovation company, Draper focuses on the design, development and deployment of advanced technological solutions for the world’s most challenging and important problems. We provide engineering solutions directly to government, industry and academia; work on teams as prime contractor or subcontractor; and participate as a collaborator in consortia. We provide unbiased assessments of technology or systems designed or recommended by other organizations—custom designed, as well as commercial-off-the-shelf. Visit Draper at http://www.draper.com.
We, the Munich Institute of Robotics and Machine Intelligence (MIRMI) of the Technical University of Munich (TUM), in collaboration with Messe München
and automatica have launched successfully a new high-tech platform calledmunich_iin 2021, an event bringing together the world’s leading thought leaders and personalities from AI and robotics.
munich_i will take place again at the next automatica from June 21-24, 2022 in Munich, therefore
Robothon®, the international competition to develop skills in robot manipulations, will also go into the second round!!
Robothon® – The Grand Challenge Series focuses on pressing and unsolved challenges of our time and was 2021 held digitally in the run-up to the automatica sprint
with 9 international teams and a renowned Grand Challenge Jury. As a highlight, it ended with the Award Ceremony on June 22, 2021
with 4 winning teams, a total prize money of € 22,500, great recognition and an expansion of our community.
Are you a motivated robotics enthusiast looking for new challenges?
QUBS (www.qubs.toys) is a Swiss company producing traditionally-designed wooden toys with hidden high-tech magic: liberating children to explore their imagination, safely learn future skills and engage in educational, screen-free fun.
Inspired by the Montessori method, QUBS STEM toys educate as well as entertain. Playing with QUBS toys provides children, through play, with developmental skills in science, technology, engineering, and mathematics.
Loved by parents, teachers and, most importantly, young users (3 to 12 years), QUBS’ intuitive, gender neutral toys – made from responsibly sourced and long lasting beechwood – contain patented technology which brings them to life. Unlike other tech-enabled STEM children’s toys, QUBS’ toys have an eternal shelf life, do not require updates nor access to the internet, and are completely screen-less, empowering children to become creators, rather than passive users of laptop or smartphone screens.
Each block and toy component contains a QUBS-developed and patented version of RFID (Radio Frequency Identification) technology (the innovation most commonly-used in contactless payments and key fobs). RFID technology is 100% safe and secure for children and grown-ups, allowing the individual tiles and blocks to interact, all within their own secure universe.
Cody Block
QUBS’ first product, CodyBlock- to be showcased at Nuremberg Toy Fair – Spielwarenmesse Digital (where it has been shortlisted for the prestigious annual ‘Toy Award’) – features an independently-moving car (Cody), whose journey changes in response to a child’s placement and arrangement of wooden blocks within its environment. Encouraging creativity and teamwork, Cody Block introduces children to computer programming concepts, robotics, and the Internet Of Things through fun and accessible play.
Learning computational skills in early years is essential. Cody the car, and the wooden toy blocks which shape his journey, teach kids to think like a programmer: being introduced to principles of debugging (the process of identifying a problem and correcting it) and sequencing (the specific order in which instructions are performed in an algorithm) through physical play.
The task is to plan a path that leads Cody through the city and back home, his movements changing in response to the child’s arrangement and rearrangement of the wooden blocks (each containing RFID tech). Each block denotes a different directional command (e.g. ‘turn left’, ‘turn right’, ‘u-turn’ etc.), creating a sequence of instructions. This allows children to improve their motor skills, critical thinking, creativity and spatial awareness.
Cody Blockis designed for kids aged 3-12, and will be available to ship in Q2 2022.
Matty Block
QUBS’ second product, MattyBlock, is designed for ages 3-9, it helps children develop self confidence in mathematics by introducing the concepts of addition, subtraction and multiplication.
Children place Matty the farmer on a board above a sum of their own creation, formed by numbered tiles (representing seeds). With a nod or shake of his head, Matty guides young users to the right answer to the sum. MattyBlockfeatures voice feedback in six languages (English, German, French, Spanish, Italian and Mandarin), making it the perfect tool for children to play and learn autonomously. Its story setting provides a fun and comprehensive introduction to numbers and equations, while exploring the delicate and ever-changing world of nature.
Matty Blockwill be available in 2023.
About QUBS
Based in Zurich, Paris and London, QUBS Toys was founded by Hayri Bulman in 2019, a Swiss entrepreneur with over 30 years of IT expertise, working for GE (General Electric) and Xerox. Hayri’s own fatherhood, passion for wooden toys and firm grasp of technology motivated him to create QUBS to better equip the future generations for the digital world. Inspired by the toy company TEGU in 2015, Hayri sought out to merge classic wooden toys with modern technology and soon started working on concepts that combined RFID technology with wooden blocks. Since then, QUBS has expanded into a vast team of designers, engineers and creatives from all across Europe.
In April 2020, at the very beginning of the global pandemic, QUBS raised CHF 88,887 (~£70,000) by 503 backers during a Kickstarter campaign.
QUBS Toys will be available for purchase online from www.qubs.toys, as well as from major stockists.
Sophie writes on behalf of Panda Security covering cybersecurity and online safety best practices for consumers and families. Specifically, she is interested in removing the barriers of complicated cybersecurity topics and teaching data security in a way that is accessible to all. Her most recent piece is on the evolution of robotic dogs and where they're headed next.
Robots have been a point of fascination and study for centuries as researchers and inventors have sought to explore the potential for automated technology. While there’s a long history of the development and creation of autonomous machines, mobile, quadrupedal robots — or four-legged robotic dogs — have seen a significant boom in the last few decades.
The development of quadrupedal robots stems from the necessity of mobile robots in exploring dangerous or unstructured terrains. Compared to other mobile robots (like wheeled or bipedal/two-legged robots), quadrupedal robots are a superior locomotion system in terms of stability, control and speed.
The capabilities of quadrupedal robots are being explored in a variety of fields, from construction and entertainment to space exploration and military operations. Today, modern robotic dogs can be purchased by businesses and developers to complete tasks and explore environments deemed too dangerous for humans. Read on for the evolution of robotic dogs and where they might be headed in the future.
1966: Phony Pony
Although it technically mirrored the form of a horse, the Phony Pony was the first autonomous quadrupedal robot to emerge in the U.S. that set the precedent for robotic dogs of the future. Equipped with electrical motors, the Pony Pony had two degrees of freedom, or joints, in each leg (the hip and the knee) and one adaptive joint in the frontal plane. The hip and knee joints were identical, allowing for both forward and backward walking movements.
The Phony Pony was capable of crawling, walking and trotting, albeit at a very slow speed. Thanks to its spring-restrained “pelvic” structure, it was able to maintain static vertical stability during movement. Since the Phony Pony was developed before the advent of microprocessors, it could only be controlled through cables connected to a remote computer in an adjacent building.
Developer: Frank and McGhee
Use: Initial research and development of autonomous quadrupeds
1999: AIBO
In the late 1990s, Sony’s AIBO — one of the most iconic and advanced entertainment robotic dogs — hit the market. While the AIBO (Artificial Intelligence RoBOt) was constructed for entertainment purposes, its machinery is still highly complex.
Developed with touch, hearing, sight and balancing capabilities, it can respond to voice commands, shake hands, walk and chase a ball. It can also express six “emotions”: happiness, sadness, fear, anger, dislike and surprise. Its emotional state is expressed through tail wagging, eye color changes and body movements, as well as through a series of sounds including barks, whines and growls. Today, the AIBO has been used across many research groups for the purpose of testing artificial intelligence and sensory integration techniques.
Developer: Sony
Use: Toys and entertainment
2005: BigDog
Boston Dynamics has become a leader in the world of robotics, specifically in their development of canine-inspired quadrupeds. Their first robotic dog, coined BigDog, arrived in 2005. Measuring three by two feet and weighing in at 240 pounds, BigDog was designed to support soldiers in the military. It can carry 340 pounds, climb up and down 35-degree inclines and successfully hike over rough terrains.
Each of BigDog’s legs has a passive linear pneumatic compliance — a system that controls contact forces between a robot and a rigid environment — and three active joints in the knees and hips. The robot is powered by a one-cylinder go-kart engine, and its dynamic regulating system allows it to maintain balance. Its movement sensors embrace joint position, joint force, ground contact, ground load and a stereo vision system.
In 2012, developers were still working to refine BigDog’s capabilities before plans to officially deploy it to military squads. However, the project was discontinued in 2015 after concluding its gas-powered engine was too noisy to be used in combat.
Developer: Boston Dynamics
Use: Assist soldiers in unsafe terrains
2009: LittleDog
Four years after BigDog came LittleDog, Boston Dynamics’ smallest quadrupedal robot to date. LittleDog was developed specifically for research purposes to be used by third parties investigating quadrupedal locomotion.
Each of LittleDog’s legs are powered by three electric motors fueled by lithium polymer batteries and have a maximum operation time of thirty minutes. LittleDog maintains a large range of motion and is capable of climbing, crawling and walking across rocky terrains. A PC-level computer placed on top of LittleDog is responsible for its movement sensors, controls and communications. It can be controlled remotely and includes data-logging support for data analysis purposes.
Developer: Boston Dynamics
Use: Research on locomotion in quadrupeds
2011: AlphaDog Proto
Continuing their efforts to develop military-grade robots, Boston Dynamics released AlphaDog Proto in 2011. Powered by a hydraulic actuation system, AlphaDog Proto is designed to support soldiers in carrying heavy gear across rocky terrains. It’s capable of carrying up to 400 pounds for as far as 20 miles, all within the span of 24 hours, without needing to refuel.
AlphaDog Proto is equipped with a GPS navigation and computer vision system that allows it to follow soldiers while carrying their gear. Thanks to an internal combustion engine, AlphaDog Proto proved to be quieter than its predecessor BigDog, making it more suitable for field missions.
Developer: Boston Dynamics
Use: Assist soldiers in carrying heavy gear over unsafe terrains
2012: Legged Squad Support System (LS3)
Boston Dynamics’ development of the Legged Squad Support System (LS3) came soon after the creation of BigDog in their efforts to continue refining their quadrupedal robots for soldiers and Marines. LS3 was capable of operating in hot, cold, wet and otherwise unfavorable conditions. It contained a stereo vision system with a pair of stereo cameras, which were mounted inside the robot’s head. This operated in conjunction with a light-detecting and ranging unit that allowed it to follow a soldier’s lead and record feedback obtained from the camera.
Compared to BigDog, LS3 was around 10 times quieter at certain times and had an increased walking speed of one to three miles per hour, increased jogging speed of five miles per hour and the ability to run across flat surfaces at seven miles per hour. It was also capable of responding to ten voice commands, which was a more efficient function for soldiers who would be too preoccupied with a mission to use manual controls.
Five years into development, LS3 had successfully been refined enough to be able to operate with Marines in a realistic combat exercise and was used to resupply combat squads in locations that were difficult for squad vehicles to reach. By 2015, however, the LS3 was shelved due to noise and repair limitations. While the Marines were ultimately unable to use the LS3 in service, it provided valuable research insights in the field of autonomous technology.
Developer: Boston Dynamics
Use: Assist soldiers in carrying heavy gear over unsafe terrains
2016: Spot
Spot is Boston Dynamics’ next creation in their line of quadrupedal robots, designed in an effort to move away from developing quadrupeds strictly for military use and instead move into more commercial use. Spot is significantly smaller than their previous models, weighing just 160 pounds. Spot is capable of exploring rocky terrains, avoiding objects in its path during travel and climbing stairs and hills.
Spot’s hardware is equipped with powerful control boards and five sensor units on all sides of its body that allow it to navigate an area autonomously from any angle. Twelve custom motors power Spot’s legs, gaining speed of up to five feet per second and operating for up to 90 minutes. Its sensors are able to capture spherical images and also allow for mobile manipulation for tasks such as opening doors and grasping objects. Spot’s control methods are far more advanced than Boston Dynamics’ earlier robots, allowing for autonomous control in a wider variety of situations.
Developer: Boston Dynamics
Use: Documenting construction process and monitoring remote high-risk environments
2016: ANYmal
While Boston Dynamics had been the main leader in quadrupedal robots since the early 2000s, Swiss robotics company ANYbotics came out with its own iteration of the robotic dog in 2016. Positioned as an end-to-end robotic inspection solution, ANYmal was developed for industrial use, specifically the inspection of unsafe environments like energy and industrial plants.
ANYmal is mounted with a variety of laser inspection sensors to provide visual, thermal and acoustic readings. Equipped with an on-board camera, it’s capable of remote panning and tilting settings to adjust views of the inspection site. ANYmal is capable of autonomously perceiving its environment, planning its navigation path and selecting proper footholds during travel. It can even walk up stairs and fit into difficult-to-reach areas that traditional wheeled robots can’t.
ANYmal has undergone a handful of development iterations since 2016 and is available for purchase as of 2021. ANYbotics is currently working on an upgraded version of the robot suitable for potentially explosive environments.
Developer: ETH Zurich and ANYbotics
Use: Remote inspection of unsafe environments
2021: Vision 60
One of the latest developments in quadrupedal robots is Ghost Robotics’ Vision 60 robotic dog, which has recently been tested at the U.S. Air Force’s Scott Air Force Base in Illinois as part of its one-year pilot testing program. Built to mitigate risks faced by Air Force pilots, Vision 60 features a rifle mounted on its back contained in a gun pod and is equipped with sensors that allow it to operate in a wide variety of unstable terrains. It’s also capable of thermal imaging, infrared configuration and high-definition video streaming.
Vision 60 can carry a maximum of 31 pounds and can travel at up to 5.24 feet per second. It’s considered a semi-autonomous robot due to its accompanying rifle; while it can accurately line up with a target on its own, it can’t open fire without a human operator (in accordance with the U.S. military’s autonomous systems policy prohibiting automatic target engagement).
Developer: Ghost Robotics
Use: Military and Homeland Security operations
2021: CyberDog
With more companies embracing the development of quadrupeds, Xiaomi Global followed suit and released their version named CyberDog. CyberDog is an experimental, open-source robot promoted as both a human-friendly companion and an asset by law enforcement and military. CyberDog is sleeker and smaller than its other robotic dog predecessors, carrying a payload of just 6.6 pounds and running over 10 feet per second.
CyberDog is equipped with multiple cameras and image sensors located across its body, including touch sensors and an ultra-wide fisheye lens. CyberDog can hold 128 gigabytes of storage and is powered by Nvidia’s Jetson Xavier AI platform to perform real-time analyses of its surroundings, create navigation paths, plot its destination and avoid obstacles. CyberDog can also perform backflips and respond to voice commands thanks to its six microphones.
By making CyberDog an open-source project, Xiaomi hopes to expand its reach into the future of robot development and innovation. Its open-source nature is meant to encourage robotics enthusiasts to try their hand at writing code for CyberDog, giving the project more exposure and bolstering Xiaomi’s reputation in the robotics community.
Developer: Xiaomi Global
Use: An open-source platform for developers to build upon
While the market for quadrupedal robots is still in its early stages, interest is steadily growing in a wide range of industries. As for fears of robots pushing out the need for traditionally human-led jobs, these machines are more intended to support humans alongside their jobs rather than replace them outright.
On the other hand, privacy concerns associated with robots aren’t to be ignored. As with any tech-enabled device, hacking is always possible, especially for open-source robotic models that can put users’ personal information at risk. This applies not only to the quadrupeds discussed above, but to more common commercial robotic systems like baby monitors, security systems and other WiFi-connected devices. It’s important to ensure your home network system is as strong and secure as possible with a home antivirus platform.
The true AI vision robotic arm powered by Jetson Nano is affordable and open-source, making your AI creativity into reality.
In recent years, there are more makers, students, enthusiasts, and engineers learning artificial intelligence technology, and many interesting AI projects are being developed as well.Hiwonder brings the power of AI to robot, build a true AI robotic arm— JetMax, to enhance the AI and robotic learning experience for everyone.
JetMax featurs Deep Learning and Computer Vision abilities. It is equipped with Jetson Nano and HD Wide Angle camera, which enables it to interact with the perceived environment efficiently. It empowers you to skillfully make your AI creativity into reality.
Being an AI Vision Robotic Arm, JetMax not only features AI vision but has a clever brain as well. Supporting you in learning coding, researching AI robotics applications, and bringing your AI ideas to life. It can be your helping hand in a lab, university, or workshop.
Powered by NVIDIA Jetson Nano
The open-source JetMax robot arm is powered by Jetson Nano, featuring deep learning, computer vision and more. Jetson Nano has the performance needed to power modern AI workloads to enable JetMax robot arm with advanced AI capabilities.
Supports multiple types of EoAT (End-of-Arm Tooling)
Supporting multiple types of end-of-arm tooling such as grippers, suction cup, pen holder, electromagnet etc, JetMax provides you with many ways of creative design applications.
Open-Source
JetMax is an open platform hardware product. We contribute numerous project source and AI tutorials. Additionally, the API interface is completely opened for customization and supports, such as Python, C++ and JAVA languages.
