We research on autonomous mobile robots with a seamless integration of perception, cognition, and action. In this talk, I will first introduce our CoBot service robots and their novel localization and symbiotic autonomy, which enable them to consistently move in our buildings, now for more than 1,000km. I will then introduce multiple human-robot interaction contributions, and detail the use and planning for language-based complex commands, and robot learning from instruction and correction. I will conclude with the robot explanation generation to reply to language-based requests about their autonomous experience.

Recently, there is an increased interest towards advanced technologies in the automotive industry such as autonomous driving and connectivity. There is a sharp increase in the investment in the related technologies. The future mobility will be based on eco-friendly, high-efficiency and high-safety features. Furthermore, conventional powertrain systems based on combustion engines are expected to be rapidly co-utilized or replaced with various kinds of electrical powertrain systems. Modern vehicles are integrated with advanced technologies such as artificial intelligence, environmental perceptibility and V2X communication. In their implementation and usage, these technologies are very similar to those used in the robotics field. Therefore, it is no longer needed to differentiate between automotive engineering and robotics. We are living in the world where the words 'robotics' and 'automotive engineering' are becoming synonyms. Automotive engineering is well-positioned to provide insights on advanced technology it accumulates from mass-produced vehicles. This is a unique advantage of automotive industry in contributing to the robotics research for human-beings. Therefore, it is necessary to synthesize robotics and automotive engineering in order to share their technological benefits for improving overall human society.

There are on the order of 1 billion motor vehicles in service around the world, traveling on the order of 10 trillion miles each year. Presently, nearly all of the those miles are driven by human beings, with on the order of 1 million fatalities worldwide per year. Despite this terribly high number of fatalities, dividing fatalities by miles yields a per-mile fatality rate for human driving on the order of 1 fatality per 10 million miles worldwide (it is on the order of 1 fatality per 100 million miles in developed countries). If fatalities caused by drunk, distracted, and drowsy driving are excluded, the reliability of human driving in developed countries is on the order of 1 fatality per billion miles.
Autonomous driving has been discussed in the media as promising improvements in safety, access and convenience, a lowering of traffic, and an improvement of the environment. These are wonderful, and real, benefits that autonomous cars would bring. But how reliable must autonomous cars be before they actually improve safety? To improve upon average non-drunk, non-distracted, and non-drowsy human driving in developed countries, autonomous vehicles must cause less than 1 fatality per billion miles. There is reason to believe that to be socially accepted, autonomous cars must actually be significantly safer than this. Creating an autonomous car with this level of safety is quite difficult. Luckily, we can improve safety, access, convenience, traffic, and the environment on the way to autonomous driving in ways that are synergistic with the development of self-driving cars. This talk will describe Toyota Research Institute's approach to the problem. .

Empowering robots with human intelligence represents one of the ultimate goals in robotics research and recent advances in AI and machine learning are challenging our traditional approaches to robot intelligence. Rather than relying mainly on high-level knowledge abstraction and environment modeling; learning and adaptation are now at centre stage, focusing on seamless transfer of knowledge between the human and robot. The purpose of this talk is to outline the main concepts and practical examples of perceptual docking for harmonizing human robot interaction. It represents a major shift of perceptual learning and knowledge acquisition for robotic systems as operator specific motor and perceptual/cognitive behaviours are acquired in situ through human-robot interaction. The talk will use robotic surgery as an example to illustrate different ways of gauging the underlying decision process of the operator and how human intension and skills can be learnt in real-time by robots. It will demonstrate the use of gaze contingent control, motor channelling, and mutual learning for controlling a range of platforms, from master-slave systems, continuum robots to micro-manipulators. The regulatory, ethical and legal barriers imposed on interventional surgical robots give rise to the need of a tightly integrated control between the operator and robot when autonomy is pursued. The use of perceptual docking naturally avoids some of the major technical hurdles of existing approaches and the talk will also illustrate how this concept can benefit other applications of robotic control beyond surgery.

The talk first explains our early ideas on how sensor-controlled robots in close cooperation with humans and in applications like assembly should perform and react. Soon after improving industrial robot dynamics using the first powerful PC-processors turned out to become a major surprising success. Being part of DLR (German aerospace research establishment), space robotics has then much influenced our work in the robotics and mechatronics center RMC. Before and after ROTEX, the first remotely controlled space robot (followed by two other exciting space robot experiments), we enforced two scientific-technical areas: the development of impedance joint-torque- controlled ultra-light weight robots, which (after many inspiring discussions with dynamics and control pioneer Oussama Khatib) to me appeared as the ultimate solution in future robotics including robonauts, and the development of delay-compensating telepresence techniques with shared autonomy concepts. Telepresent minimally invasive surgical systems with force-reflection and heart motion compensation resulted from the latter work. It has been widely confirmed that in 3D-vision our Semi -Global Matching algorithm SGM has not only had a remarkable impact on modern photogrammetry e.g. for modeling landscapes and cities in 3D using aerborn cameras, but realtime versions have pushed forward semi-automatic car (including electromobile) driving in Germany, too and are now entering industrial robotics. Flying robots (helicopters) equipped with manipulating arms had found particular attention in our institute’s work as well as solarelectric unmanned airplanes for the stratosphere, a topic I am now pushing forward by a startup company. Yet the biggest joy I feel presently is the fact that though many robot experts have predicted that safe, high-fidelity joint-torque controlled robots will be too expensive to produce, the contrast has been proven now by our former control specialist Sami Haddadin with his new robot FRANKA and its intuitive programming techniques.

Opportunities: they come from the environment we find ourselves in, and our life depends on how we deal with them.  It is the familiar principle of feedback control. For a given target the path will vary according to the disturbances and noise we encounter, but we determine the reaction to disturbances based on our internal feedback algorithms given the physical and psychological energy to act. Our future opportunities depend on how we deal with the opportunities we choose to pursue and how we pursue them.
Shall I feel I am the luckiest guy in the world, to have the opportunities I have? Or be jealous of others? It seems the best solution is to find the advantages given by your situation, whatever that may be.  Want to be a university professor? Then you should be raised on a small farm. REALLY? After sixty years I realize the advantages of home cooking, hard work, hands-on equipment experience, high expectations, basic education, the opportunity to dream and a little hazing to robustify your feedback control. Another’s advantages may be an urban environment with many interactions, a museum and library down the street, transportation challenges, and perhaps low expectations that you know you can beat (and some home cooking).
At some point in our lives we should realize how lucky we are, and everyone who reads this is really lucky; fortunate beyond all reason. At some point the role we play must adjust to cope with this inequity of most of the world. How will we give a hand up to those who cannot leverage their environment to move up in the world; those who don’t have the basic “energy” from food, education and expectations to convert their environmental challenges to personal progress. We may help those next door, across a border or on the other side of the world. But our luck should not blind us to this role as a responsible human being who is really lucky. 
This talk will explore opportunities we have and some ways we can change the world, a world that can use some changes. Engineers can do that!

Research on high level HRI systems that aim skill transfer, language acquisition, dialogue management, and so on requires large-scaled experience based on social and embodied interaction. However, huge costs for development/maintenance of robots and performing HRI sessions are required to use real robot systems. If we choose virtual robot simulator, limitation on embodied interaction arises between virtual robots and real users. I thus have proposed an enhanced robot simulator that enables multiuser to connect to central VR world, and enables users to join the virtual world through immersive user interfaces. As an example, we propose an application to RoboCup@Home tasks that requires sharing of embodied experience between virtual robots and real users. In this talk, I explain the configuration of our simulator platform and feasibility of the system in several applications including RoboCup@Home.

A spring is an elastic object used to store mechanical energy. Springs have been widely used in various mechanical systems for centuries, but seldom employed in robots that often require positioning accuracy. In recent years, however, springs have emerged as very cheap but useful elements for robots that require either compliance or safety. Typical examples are variable stiffness actuators, series elastic actuators, safety mechanisms, counterbalance mechanisms and so on. This keynote speech will give an overview of the smart use of springs for robot mechanisms.
A variable stiffness actuator (VSA) can change its stiffness in real time by combining linear springs, some mechanical components and actuators. Among many different types, a hybrid VSA is introduced. A safe joint mechanism (SJM) was developed to ensure safety by abruptly reducing an impact force upon a collision between a robot and a human. Because it is a purely passive device without any sensors or active components, it offers faster response, higher reliability and much lower cost than those based on active compliance. A series elastic actuator (SEA) with a spring at the drivetrain can offer both compliant behavior and enable torque sensing based on the encoders. A counterbalance robot is capable of mechanical gravity compensation. This mechanism can effectively compensate for the gravitational torques required at each joint to support the robot mass for any robot configuration and is extendable to multi DOF robot arms.

In many instances of manufacturing tasks that require high dexterity manipulation skills and fine force contact with object surfaces, such as fine electronic part assembly and precision part polishing, the skills of human works are critical. In ultrahigh precision component fabrication, the skills and experiences of the master play a crucial role because the human worker carries out the task using multi-modal interaction, such as visual, tactile, auditory feedback to make real-time adjustment. An industrial robot with hybrid force and position control ability simply cannot mimic such feedback to achieve such precision. In this speech, we will examine how to model, capture, and automate such tacit manufacturing knowledge from the human workers from the perspective of human-robot-environment interaction with an industrial application. The result of this study could have significant impact on the design of next generation of industrial robots. First, we need to understand and quantify skills in humans (trained personnel) during complex assembly/tooling tasks (human-human interaction). Secondly, new task acquisition technology for capturing, processing and characterizing human and tool motion, tool dynamics, and continuous contact interaction between the tool and work piece is needed (human-environment interaction). And lastly, we shall characterize and map human skill onto the robot programming in order to control the robot performing the tasks in a human-inspired manner (human-robot interaction). Along the way we get to the final goal, we would find new paradigms and new design methodology for a new breed of cost-effective human-inspired industrial robots, with sufficient degrees of dexterity and the underlying human-inspired actuation and control strategies, to handle delicate manufacturing tasks that have never been automated before..

Recent advances in artificial intelligence and robotics are taking on ever more cognitive tasks, spreading concerns that the entire job market and economy will be affected by this technology soon. Breakthroughs in human-centered robots that can effectively enhance our lives, however, have less attention although they have higher potential to be readily accepted. Conventional robots may be efficient and robust for routine works but are not suitable for humans to cooperate in unpredictable environments. Rigid, heavy structures and gear based force transmission make robots intrinsically unsafe for human to exist in same space. The purpose of this talk is to address the importance of human-centered design of robots and commercialization effort that could completely change the life of elderly people and patients. The talk will use a number of such efforts made in Samsung Electronics as examples to demonstrate how fundamental research in robotics progressed into single-port surgical robots and exoskeletons for augmenting physical strength. Computer simulation of human anatomy and neuromuscular system enabled to minimize regulatory and ethical problems when testing such devices on human throughout the research.

Robotics will change the world! It will unleash the same if not an even more disruptive and transformational power within the next 50 years as mainstream IT-technology and the Internet have over the last half a century. Nurtured by technological breakthroughs in industrial automation, robotics will exhaustively permeate all domains of the human living realm. Hence, our grandchildren will grow up in a society that is enriched and enhanced by assistive technologies in every imaginable way. Robotics and automation will be tailored into many everyday objects, becoming an integral part of all kinds of appliances. This Generation 'R' will be without fear of these technologies perceiving their beneficial nature - they will grow up as Robotic Natives. This implies, that today's people are already born to become the first society of Robotic Immigrants. Although it is not possible to precisely predict the world of tomorrow, the presented model of the 4 Robotic Revolutions provides a compelling, holistic approach to describe the future phases of robotic evolution, characterizing them according to their technological enablers and underlying interaction paradigms. Unfortunately, all technological disruptions also entail challenges and issues. But, compared to the evolution of the internet, we are facing one big chance: The internet more or less just "happened" – regarding robotics, automation and artificial intelligence we can still address possibly arising issues in advance. Involving self-regulation in the sense of Technology & Robotic Governance, these challenges have to be discussed on a broad, fact based and interdisciplinary level. Nevertheless, in order to enable sustainable technologies and really responsibly drive "Technology for Humanity" (as the IEEE claims), we all have to change the way we are thinking and engage in discourse! The 2nd IEEE IROS Futurist Forum and www.roboticgovernance.com provide a platform for further exchange and discussions.

For the intelligent robots to operate in very complex environments, it is essential to have a robust perception system using many different sensors, such as cameras and lidar depth sensors. There have been significant advances in the perception technology for intelligent robots in the last decade. We, however, often encounter many problems in applying the state-of-the-art computer vision solutions to intelligent robots in real-world environments. The failures are mainly due to the lack of robustness of computer vision solutions in extremely difficult conditions, such as bad weather and cluttered backgrounds. For example, the DRC-HUBO+ often failed to detect and grasp objects, such as a drill, a door handle, and a valve, in the DRC missions with the well-known computer vision solutions. In this talk, we present our experiences in developing robust computer techniques for intelligent robots to operate in challenging conditions. Specifically, a simple camera distortion model shows much improvement in the camera-lidar calibration with the sub-pixel accuracy of re-projection error. A fusion algorithm for the camera and lidar sensors successfully aligns the color and depth images with the smallest error, as of today, in the Middlebury benchmarking data. The resulting fused images provide the accuracy required for the position-based DRC-HUBO+ to successfully carry out given missions in the DRC Finals, such as stair climbing, opening door, drilling a hole, and operating a valve. Our novel CNN network, called "AttentionNet", is developed to accurately classify and localize the target objects in the given input image. The AttentionNet-based CNN architecture has been applied to the Classification and Localization task of the ILSVRC. Finally, we present the DRC-HUBO+ robot system with a video clip of the DARPA Robotics Challenge (DRC) Finals

In this talk, I will describe our recent progress in developing fault-tolerant distributed control policies for multi-robot systems. We consider two problems: rendezvous and coverage. For the former, the goal is to bring all robots to a common location, while for the latter the goal is to deploy robots to achieve optimal coverage of an environment.
We consider the case in which each robot is an autonomous decision maker that is anonymous, memoryless, and dimensionless, i.e., robots are indistinguishable to one another, make decisions based upon only current information, and do not consider collisions. Each robot has a limited sensing range, and is able to directly estimate the state of only those robots within that sensing range, which induces a network topology for the multi-robot system. We assume that it is not possible for the fault-free robots to identify the faulty robots (e.g., due to the anonymous property of the robots). For each problem, we provide an efficient computational framework and analysis of algorithms, all of which converge in the face of faulty robots under a few assumptions on the network topology and sensing abilities. .

Probabilistic techniques for robot navigation have become key enablers in different application domains including self-driving cars, logistics, service robots and mobile manipulation. In this talk, I will present the key techniques for building successfully navigating robots including particle filters and methods for solving the simultaneous localization and mapping (SLAM) problem. I will furthermore describe how these methods have been turned into several effective real-world applications. I will furthermore present probabilistic methods for combining state estimation with action selection approaches. At the very end, I will briefly discuss how recent methods coming from the domain of deep networks can be used for building robustly navigating robots.

The mechatronic development of humanoid robots has considerably progressed during the past two decades with various designs based on different actuation technologies, from motorized based systems to hydraulic and soft actuation technologies. Despite though the advancements in the design of motorized humanoids/bipeds significant barriers still remain, preventing the robot hardware (physical structure and actuation) from equalling the performance of human in locomotion and full body motion in terms of physical robustness, power performance and efficiency. Considering the compliant actuation principles and technologies developed at IIT this talk will present their application on the development of COMAN and WALK-MAN humanoid platforms. Details on the actuation and robot design approaches to achieve the necessary performance in terms of physical resilience, high power and fast motion capabilities will be discussed. Recent work on energy efficiency considerations will also be introduced showing the potential of compliant actuation arrangements in reducing the energy consumption of articulated robotic systems.

In a dynamic and changing world, a robust and effective robot system must have adaptive behaviors, incrementally learnable skills and a high-level conceptual understanding of the world it inhabits, as well as planning capabilities for autonomous operations. Future intelligent control systems will benefit from the recent research on neurocognitive models in processing multisensory data, exploiting synergy, integrating high-level knowledge and learning, etc. I will first introduce crossmodal integration methods for intelligent service robots. Then I will present our investigation and experiments on synergy technique which uses fewer parameters to govern the high DOF of multifinger robot movement. The third part of my talk will demonstrate how an intelligent system like a robot can evolve its model as a result of learning from experiences; and how such a model allows a robot to better understand new situations by integration of knowledge, planning and learning. I will show some integrated results of operational mobile robot platforms with grasping facilities in a restaurant service scenario.

The problem of building an autonomous robot has traditionally been viewed as one of integration: connecting together modular components, each one designed to handle some portion of the perception and decision making process. For example, a vision system might be connected to a planner that might in turn provide commands to a low-level controller that drives the robot's motors. In this talk, I will discuss how ideas from deep learning can allow us to build robotic control mechanisms that combine both perception and control into a single system. This system can then be trained end-to-end on the task at hand. I will show how this end-to-end approach actually simplifies the perception and control problems, by allowing the perception and control mechanisms to adapt to one another and to the task. I will also present some recent work on scaling up deep robotic learning on a cluster consisting of multiple robotic arms, and demonstrate results for learning grasping strategies that involve continuous feedback and hand-eye coordination using deep convolutional neural networks.

Thanks to big data, deep learning algorithms and high-performance computing, artificial intelligence (AI) technologies have gained dramatic developments in the past a few years. At Baidu, AI is the (next) big thing. This talk will present our strategy and practice. Aiming to achieve artificial general intelligence one day, we are taking two directions simultaneously: 1) developing common fundamental technologies ranging from deep learning platform, basic computer vision technologies such as image classification, object detection/tracking, image/video segmentation, etc.; 2) building ultimate-level AI technologies in vertical domains such as food recognition, car/pedestrian detection, etc. The talk will present some case studies with strong emphasis on forming the close loop of algorithms, applications, users and data. These advances in deep learning and computer vision offer up new possibilities not only for mobile/internet apps but also for robotics.

Unmanned aerial vehicles have undergone rapid development since 1990s. Originally developed for military applications, they have been extremely successful for missions where direct human participation is deemed dull or dangerous. Thanks to their remarkable success, they began to enter the civil airspace for border patrol and aerial surveillance in late 1990s. During the last few years, the field of UAVs are seeing yet another revolution: the advent of small multirotor drones. This new type of drone is affordable yet very capable for aerial photography and even package deliveries. These two types of drones are entering the airspace in two distinct ways: the larger ones are now considered for full integration for civil airspace by International Civil Aviation Organization. The accommodation of small drones are trickier: they need a whole new way of integration, which is now being tackled by a number of researchers. The success of drone is in debt to the advances in computers, sensors, communications and algorithms: they can perform various missions with great flexibility and reliability. It is very impressive to see how a new robotic device is conceived, developed, and evolved into a mature system so that a whole new industry is formed and rules and regulations are created for them. The speaker intends to share his views obtained from his research since 1991 and also his activities as a member of ICAO RPAS Panel. .

Exploration of the polar region is of great importance for scientific research on global climate change and the evolution of the earth. However, the tough environment, e.g., low temperature, strong wind, complex terrains, makes human exploration difficult and dangerous. In 2011, the China National High Technology Research and Development (863) Program and National Antarctic Research Expedition (CHINARE) jointly launched a project to design ground mobile and flying robots to conduct large-scale scientific explorations on Antarctica. In this talk, the corresponding techniques, especially the polar rover's prototypes and autonomous control, as well as the preliminary field test results on Antarctica are introduced. The challenging open problems are also summarized as conclusion..

Current AI systems for perception and action incorporate a number of techniques: Bayesian state estimation, probabilistic mapping, trajectory planning, and feedback control. I will describe and demonstrate some of these methods on various autonomous systems including wheeled, legged, and flying robots. In order to model variability due to pose, illumination, and background changes, low-dimensional manifold representations have been used for learning in these systems. But how well can such manifolds be processed by neural networks? I will show how notions of linear separability and VC dimension can be generalized from input points to manifolds. This analysis provides theoretical predictions for the capacity and generalization ability of invariant classifiers, and better understanding of the performance of deep neural networks. .

Efforts to develop and commercialize medical robots (specifically, surgical robots) has been made intensively all over the world. However, there are only a few number of output that make success in commercialization. In light of this fact, this talk would like to discuss about several aspects that enable us to produce fruitful research output and allow translation to industry. Specifically, this talk would like to discuss about how society can contribute to raise engineer in medical robotics research. Education for engineers in medical robotics involves general education program in engineering and clinic. However, there exists another important issue that has been ignored or has not been paid much attention in medical robotics area. That is the education that considers the certification process in medical robotics. Many countries make an effort to get certification when they develop medical equipment (ME). Certification is necessary not only for commercialization but also for user safety. The certification authorities of the United States, Europe, and Korea are FDA, CE, and KFDA, respectively. Typically ME standards are defined by the Quality Assurance System which vouches the manufactured medical equipment being safe and effective. The Korean standard of medical equipment is followed by the International Standard IEC 60601 which is the same as Europe, Japan, and U.S.A. This talk briefly goes over medical equipment certification standards. Prior to development of ME, the grade of the device should be determined first. Usually, ME is classified by four or three grades according to the purpose of use and potential risks. For instance, the VI master-slave robot that inserts a catheter into the patient's vessel is classified as the 2nd grade. This is because the risk to life is low, even though there is some risk to human health in case of breakdown or malfunction. Initially, process of identifying four grades is also explained. Several successful and failed examples for each grade will be addressed. For certification, developers have to adjust to several standards. These standards are for biological safety, electrical safety, and mechanical et al. This talk will take otologic surgical device and vascular intervention robotic system as examples to explain the standards for safety and performance of medical devices. Specially, safety of electric and mechanical aspects will be mainly introduced through modified design examples of medical robots.

Minimally invasive endoscopic surgery is now recognized as a standard operation in almost all of the surgical fields. Thanks to the development of information and robotic technology, the technical difficulties have been overcome in part, especially in the movement of the instruments and in the operative fields by introducing super-hand with 7 degrees of freedom and 3D endoscope, respectively. However, the surgical application of the robotic surgery is still limited to the pelvic cavity. There are many problems for further development to be solved in clinical situation. Among them education is the most important issue for both engineers and medical doctors to understand the whole process from creating an idea to producing commercial products. The final purpose is to contribute to human healthcare with medical devices which are useful to care the patients. However, the big difference between the industrial devices and medical devices is the contact to human. More attention has to be paid to “safety” rather than “benefit” of the patients. If “cost performance is poorer compared to that of conventional one, hospital director would not allow the each doctor to use or purchase it. When the medical devices are for the operative use, sterilization is often no marked by engineers. They must have an experience to observe the real clinical situation and to understand how the devices are used in OR and what is the needs in clinical situation. According to the current change of real condition, our interests are now being moved on personalized precision medicine based on multidisciplinary computational anatomy as well as on less invasiveness from the view point of quality of life. Integration of medicine and engineering is one of the solutions for the current problems. The ideal circumstance might be where multidisciplinary personnel with the same purpose is working together in the same room of the same hospital at the same time.

Robotic assisted surgery has given surgeons open surgery-like capabilities in minimally invasive format. To advance the capabilities of the next generation of robotic assisted surgery, we should challenge ourselves to increase usability and convenience for the operating room staff while improving the information available to surgeons helping them to make faster decisions and achieve better patient outcomes. The next generation of engineers developing robotic assisted surgical systems must be able to apply the latest advancements in technologies (haptics, optics, controls, and mechatronics) with improved application of human factors and usability design. To foster cross-discipline learning for engineers, training pathways designed to promote advanced learning through deep understanding of engineering sciences and experimental methods is essential, so they can best meet the needs of the surgical community. Mr. Brogna will share insights and real company experiences in bridging medical needs with engineering technology for the next generation of surgery.

Decades of research into intelligent, playful technology and user-friendly man-machine interfaces has provided important insight into the creation of robotic systems and intelligent interactive systems which are much more user-friendly, safer and cheaper than what appeared possible merely a decade or two ago. This is significantly disrupting the industry in several market sectors. This award talk describes the components of the playware and embodied artificial intelligence research that has led to disruption in the industrial robotics sector, and which points to the next disruption of the health care sector. The components include playful robotics, LEGO robots for kids, minimal robot systems, user-friendly, behavior-based, biomimetic, modular robotics and intelligent systems. The insight into these components and the use in synthesis for designing robots and intelligent systems allows anybody, anywhere, anytime to use these systems, providing an unforeseen flexibility into the sectors (e.g. the health sector), which become disrupted with these systems. The Playware ABC concept will allow you to develop life-changing solutions for anybody, anywhere, anytime through building bodies and brains to allow people to construct, combine and create. Indeed, with recent technology development, we become able to exploit robotics and modern artificial intelligence (AI) to create playware in the form of intelligent hardware and software that creates play and playful experiences for users of all ages. Such playware technology acts as a play force which inspires and motivates you to enter into a play dynamics, in which you forget about time and place, and simultaneously become highly creative and increase your skills - cognitive, physical, and social skills. Clinical effect studies in the health sector show that play with the Moto tiles (www.moto-tiles.com) have a remarkable effect on functional abilities, including balancing, of older adults. It is shown how many older adults even are able to throw away their walking aids after playing on the Moto tiles