A robot providing mealtime assistance must perform specialized maneuvers with various utensils in order to pick up and feed a range of food items. Beyond these dexterous low-level skills, an assistive robot must also plan these strategies in sequence over a long horizon to clear a plate and complete a meal. Previous methods in robot-assisted feeding introduce highly specialized primitives for food handling without a means to compose them together. Meanwhile, existing approaches to long-horizon manipulation lack the flexibility to embed highly specialized primitives into their frameworks. We propose Visual Action Planning OveR Sequences (VAPORS), a framework for long-horizon food acquisition. VAPORS learns a policy for high-level action selection by leveraging learned latent plate dynamics in simulation. To carry out sequential plans in the real world, VAPORS delegates action execution to visually parameterized primitives. We validate our approach on complex real-world acquisition trials involving noodle acquisition and bimanual scooping of jelly beans. Across 38 plates, VAPORS acquires much more efficiently than baselines, generalizes across realistic plate variations such as toppings and sauces, and qualitatively appeals to user feeding preferences in a survey conducted across 49 individuals. Code, datasets, videos, and supplementary materials can be found on our website: https://sites.google.com/view/vaporsbot.

Imagine this chilling possibility: as you sleep peacefully, someone in your home picks up your iPhone. It's shocking to think that anyone can unlock your phone without your knowledge when you're sleeping. As anyone with a relatively modern iPhone knows, it's possible using Apple's Face ID to open your phone just by looking at it A common fear is that someone could hold your phone to your face while you're sleeping to unlock it As anyone with a relatively modern iPhone knows, it's possible using Apple's Face ID to open your phone just by looking at it. It maps all your curves and wrinkles and stores that data as a key to unlock your phone. If there's a more significant change in your appearance, like shaving your beard, Face ID confirms your identity by using your passcode prior to updating your face data.

An exoskeleton boot that enables the wearer to walk 9 per cent faster than with normal shoes, and with 17 per cent less effort, has been revealed by scientists. Created at Stanford University, the robotic footwear comes with a motor that works with calf muscles to give the wearer an extra push with every step. The precisely-timed motor controls the boot so that it imparts a'torque' – a twisting force that can cause rotation around an axis – at the leg joint. The new creation could be widely used in everyday life, by people with mobility impairments or with physically demanding jobs, for example. The exoskeleton'boot' can adapt to the user to help people walk faster and more efficiently in real-world conditions.

Researchers from the RIKEN Guardian Robot Project and collaborators have used a combination of lightweight material engineering and artificial intelligence to create an exoskeleton robot that could help people with mobility impairments. An important element of the new device is technology that allows the skeleton to effectively guess the intentions of the user. Robotic exoskeletons promise to play an important role in supporting an aging population. Essentially, they are suits that people can wear, allowing them to exert strength when their old bodies are not capable of exerting strength themselves. However, developing exoskeletons has been hampered by the fact that they are generally heavy, and if not properly controlled can act as hindrances rather than assistance.

To dance is human; people of all ages and levels of motor ability express movements in response to music. Professional dancers exert a great deal of creativity and energy toward developing their skills and different styles of dance. How dancers move in beautiful and sometimes unexpected ways can delight, and the synchrony between dancers moving together can be entrancing. To us as a neuroscientist and biomechanist (Lena), and a rehabilitation scientist and dancer (Madeleine), understanding the complexities of motor skill in a ballet move, or the physical language of coordination in partner dance, is an inspiring and daunting challenge. Understanding how dancers move has important real-world implications, too. In our work, we're studying gait and balance in different populations, as well as how holding hands – such as in partner dance – can actually help people walk and balance better.

Two UD researchers--James C. (Cole) Galloway, associate professor of physical therapy, and Sunil Agrawal, professor of mechanical engineering--have outfitted kid-size robots to provide mobility to children who are unable to fully explore the world on their own. The work is important because much of infant development, both of the brain and behavior, emerges from the thousands of experiences each day that arise as babies independently move and explore their world. This is the concept of "embodied development," Galloway said. Infants with Down Syndrome, cerebral palsy, autism and other disorders can have mobility limitations that disconnect them from the ongoing exploration that their peers enjoy. "If these infants were adults, therapists would have options of assistive technology such as power wheelchairs," Galloway said.