Robot Performs COVID-19 Tests

The COVID-19 pandemic has given a boost to service robotics. Transport, safety and care robots are in demand, as are cleaning and disinfection robots. Service robots measure the temperature of passengers at airports and railway stations. Now they can also perform COVID-19 tests.  “Robotics researchers from the University of Southern Denmark have developed the world’s first fully automatic robot capable of carrying out throat swabs for Covid-19, so that healthcare professionals are not exposed to the risk of infection. The prototype has successfully performed throat swabs on several people. The scientists behind are cheering: The technology works!” (Website SDU, 27 May 2020) A robot arm as known from the industry was used. The end piece comes from the 3D printer. This is another example from the health sector that shows how industrial robots – such as cobots – can become service robots. More information via

A Robot Dog as Sheepdog

In May 2020 the media was interested in a video by Rocos showing a robot from Boston Dynamics trying to be a shepherd dog. You could see the artificial quadruped running towards a flock of sheep. “Now, it’s clear that the video is mostly a fun teaser rather than a serious claim by Rocos (or Boston Dynamics) that robots will soon be replacing sheepdogs.” (The Verge, 22 May 2020) According to the magazine, it does invite a tantalizing question: if that did happen, “how well would the robots fare” (The Verge, 22 May 2020)? “Terrible”, is the straight answer of sheep farmer and author James Rebanks. “The robot might be an amazing tool for lots of things but it is worthless and unwanted as a sheepdog …” (The Verge, 22 May 2020) However, the profession of shepherd is not everywhere in the world the dream of all boys and girls, and shepherd dogs do not fall from the sky. It is also not clear whether there is a big difference for the sheep and how positively or negatively they react to the machine. It is just as unclear whether lambs that have never met real dogs would be comfortable with it. This would have to be researched in animal psychology and social robotics and in disciplines such as animal-machine interaction, which are still in their infancy. Only then would one know whether the shepherd interviewed by the magazine is right.

And the Winner is … Lio!

DIH-HERO is a project in the healthcare sector supported by the European Union since January 2019. According to the website, the mission is to create a sustaining network that connects players in the healthcare sector and to support small and medium sized enterprises. “Currently, Europe and countries all over the world are facing a global pandemic. Together with its extensive Robotics in Healthcare European network DIH-HERO decided to support the fight against COVID-19 by providing €1,000,000 for robotic technologies that can be deployed timely, in order to support healthcare professionals and save lives by satisfying a current clinical demand or need.” (Website DIH-HERO) F&P Robotics based in Switzerland is one of the winners of the announcement. Lio – one of the company’s flagships – will now learn new tasks in the field of disinfection (door traps, lift buttons). The normal use of the care robot was last described in a paper by Oliver Bendel (School of Business FHNW), Alina Gasser and Joel Siebenmann (F&P Robotics) that was accepted at the AAAI 2020 Spring Symposia. Because of COVID-19 the lecture was postponed to late autumn.

Towards Animal-machine Interaction

Animal-machine interaction (AMI) and animal-computer interaction (ACI) are increasingly important research areas. For years, semi-autonomous and autonomous machines have been multiplying all over the world, not only in factories, but also in outdoor areas and in households. Robots in agriculture and service robots, some with artificial intelligence, encounter wild animals, farm animals and pets. Jackie Snow, who writes for New York Times, National Geographic, and Wall Street Journal, talked to several people on the subject last year. In an article for Fast Company, she quoted the ethicists Oliver Bendel (“Handbuch Maschinenethik”) and Peter Singer (“Animal Liberation”). Clara Mancini (“Animal-computer interaction: A manifesto”) also expressed her point of view. The article with the title “AI’s next ethical challenge: how to treat animals” can be accessed here. Today, research is also devoted to social robots. One question is how animals react to them. Human-computer interaction (HCI) experts from Yale University recently looked into this topic. Another question is whether we can create social robots specifically for animals. The first beginnings were made with toys and automatic feeders for pets. Could a social robot replace a contact person for weeks on end? What features should it have? In this context, we must pay attention to animal welfare from the outset. Some animals will love the new freedom, others will hate it.

From Cozmo to Moxie

In 2016, the roboticist Maja Matarić founded Embodied, together with Paolo Pirjanian, former CTO of iRobot. In April 2020, the company started accepting preorders for Moxie, its first social robot. “Whereas other companion robots like the household assistant Jibo or Paro the robotic seal are designed for adults or the elderly, Moxie is built to foster social, cognitive, and emotional development in children. These are skills that are typically imparted to kids by their parents, teachers, and other adults, but Pirjanian noticed that many families want some extra help.” (Wired, 30 April 2020) According to the company, weekly themes and missions with Moxie explore human experiences, ideas, and life skills like kindness, empathy, and respect. Showing emotions is an important skill of social robots. SoftBank has created a model example with Pepper. Cozmo by Anki – currently not available – can also show emotions, even a multitude. And both Pepper and Cozmo create emotions in the user. Cozmo and Moxie have something in common, namely an effort of Pixar: “Taking a page from Anki’s Cozmo playbook, the company has enlisted the help of employees from Pixar and Jim Henson to flesh out the real-world robotic character. At first glance, the results are plenty impressive.” (TechCrunch, 4 May 2020)

Online Survey on Hugs by Robots

Embraces by robots are possible if they have two arms, such as Pepper and P-Care, restricted also with one arm. However, the hugs and touches feel different to those made by humans. When one uses warmth and softness, like in the HuggieBot project, the effect improves, but is still not the same. In hugs it is important that another person hugs us (hugging ourselves is totally different), and that this person is in a certain relationship to us. He or she may be strange to us, but there must be trust or desire. Whether this is the case with a robot must be assessed on a case-by-case basis. A multi-stage HUGGIE project is currently underway at the School of Business FHNW under the supervision of Prof. Dr. Oliver Bendel. Ümmühan Korucu and Leonie Brogle started with an online survey that targets the entire German-speaking world. The aim is to gain insights into how people of all ages and sexes judge a hug by a robot. In crises and catastrophes involving prolonged isolation, such as the COVID 19 pandemic, proxy hugs of this kind could well play a role. Prisons and longer journeys through space are also possible fields of applications. Click here for the survey (only in German):

Imitating the Agile Locomotion Skills of Four-legged Animals

Imitating the agile locomotion skills of animals has been a longstanding challenge in robotics. Manually-designed controllers have been able to reproduce many complex behaviors, but building such controllers is time-consuming and difficult. According to Xue Bin Peng (Google Research and University of California, Berkeley) and his co-authors, reinforcement learning provides an interesting alternative for automating the manual effort involved in the development of controllers. In their work, they present “an imitation learning system that enables legged robots to learn agile locomotion skills by imitating real-world animals” (Xue Bin Peng et al. 2020). They show “that by leveraging reference motion data, a single learning-based approach is able to automatically synthesize controllers for a diverse repertoire behaviors for legged robots” (Xue Bin Peng et al. 2020). By incorporating sample efficient domain adaptation techniques into the training process, their system “is able to learn adaptive policies in simulation that can then be quickly adapted for real-world deployment” (Xue Bin Peng et al. 2020). For demonstration purposes, the scientists trained “a quadruped robot to perform a variety of agile behaviors ranging from different locomotion gaits to dynamic hops and turns” (Xue Bin Peng et al. 2020).


Space travel includes travel and transport to, through and from space for civil or military purposes. The take-off on earth is usually done with a launch vehicle. The spaceship, like the lander, is manned or unmanned. The target can be the orbit of a celestial body, a satellite, planet or comet. Man has been to the moon several times, now man wants to go to Mars. The astronaut will not greet the robots that are already there as if he or she had been lonely for months. For on the spaceship he or she had been in the best of company. SPACE THEA spoke to him or her every day. When she noticed that he or she had problems, she changed her tone of voice, the voice became softer and happier, and what she said gave the astronaut hope again. How SPACE THEA really sounds and what she should say is the subject of a research project that will start in spring 2020 at the School of Business FHNW. Under the supervision of Prof. Dr. Oliver Bendel, a student is developing a voicebot that shows empathy towards an astronaut. The scenario is a proposal that can also be rejected. Maybe in these times it is more important to have a virtual assistant for crises and catastrophes in case one is in isolation or quarantine. However, the project in the fields of social robotics and machine ethics is entitled “THE EMPHATIC ASSISTANT IN SPACE (SPACE THEA)”. The results – including the prototype – will be available by the end of 2020.

The Comeback of Cozmo

According to The Robot Report, Anki’s little robots might be making a comeback. Digital Dream Labs in Pittsburgh acquired the patents, trademarks, and domain. The start-up company “is planning to revive and manufacture more units of each product in the following order: Overdrive, Cozmo, Vector” (The Robot Report, 26 December 2019). Digital Dream Labs founder H. Jacob Hanchar told The Robot Report “the goal is to have all three products available for purchase for Christmas 2020” (The Robot Report, 26 December 2019). The small robots belong to the best that the industry has produced. What is special about Cozmo is the many emotions it can show (but of course doesn’t have). It also has face recognition and a night vision device. The future of it and its siblings is not yet clear, as Digital Dream Labs has not purchased “physical assets and inventory” (The Robot Report, 26 December 2019). Fans are waiting and hoping.

How to Improve Robot Hugs

Hugs are very important to many of us. We are embraced by familiar and strange people. When we hug ourselves, it does not have the same effect. And when a robot hugs us, it has no effect at all – or we don’t feel comfortable. But you can change that a bit. Alexis E. Block and Katherine J. Kuchenbecker from the Max Planck Institute for Intelligent Systems have published a paper on a research project in this field. The purpose of the project was to evaluate human responses to different robot physical characteristics and hugging behaviors. “Analysis of the results showed that people significantly prefer soft, warm hugs over hard, cold hugs. Furthermore, users prefer hugs that physically squeeze them and release immediately when they are ready for the hug to end. Taking part in the experiment also significantly increased positive user opinions of robots and robot use.” (Abstract) The paper “Softness, Warmth, and Responsiveness Improve Robot Hugs” was published in the International Journal of Social Robotics in January 2019 (First Online: 25 October 2018). It is available via