In this paper, we present AR3n (pronounced as Aaron), an assist-as-needed (AAN) controller that utilizes reinforcement learning to supply adaptive assistance during a robot assisted handwriting rehabilitation task. Unlike previous AAN controllers, our method does not rely on patient specific controller parameters or physical models. We propose the use of a virtual patient model to generalize AR3n across multiple subjects. The system modulates robotic assistance in realtime based on a subject's tracking error, while minimizing the amount of robotic assistance. The controller is experimentally validated through a set of simulations and human subject experiments. Finally, a comparative study with a traditional rule-based controller is conducted to analyze differences in assistance mechanisms of the two controllers.

Digital documentation of large interiors of historical buildings is an exhausting task since most of the areas of interest are beyond typical human reach. We advocate the use of autonomous teams of multi-rotor Unmanned Aerial Vehicles (UAVs) to speed up the documentation process by several orders of magnitude while allowing for a repeatable, accurate, and condition-independent solution capable of precise collision-free operation at great heights. The proposed multi-robot approach allows for performing tasks requiring dynamic scene illumination in large-scale real-world scenarios, a process previously applicable only in small-scale laboratory-like conditions. Extensive experimental analyses range from single-UAV imaging to specialized lighting techniques requiring accurate coordination of multiple UAVs. The system's robustness is demonstrated in more than two hundred autonomous flights in fifteen historical monuments requiring superior safety while lacking access to external localization. This unique experimental campaign, cooperated with restorers and conservators, brought numerous lessons transferable to other safety-critical robotic missions in documentation and inspection tasks.

Randomized Structure from Motion Based on Atomic 3D Models from Camera Triplets.

Back in April, Stanford University professor Oussama Khatib led a team of researchers on an underwater archaeological expedition, 30 kilometers off the southern coast of France, to La Lune, King Louis XIV's sunken 17th-century flagship. Rather than dive to the site of the wreck 100 meters below the surface, which is a very bad idea for almost everyone, Khatib's team brought along a custom-made humanoid submarine robot called Ocean One. In this month's issue of IEEE Robotics and Automation Magazine, the Stanford researchers describe in detail how they designed and built the robot, a hybrid between a humanoid and an underwater remotely operated vehicle (ROV), and also how they managed to send it down to the resting place of La Lune, where it used its three-fingered hands to retrieve a vase. Most ocean-ready ROVs are boxy little submarines that might have an arm on them if you're lucky, but they're not really designed for the kind of fine manipulation that underwater archaeology demands. You could send down a human diver instead, but once you get past about 40 meters, things start to get both complicated and dangerous.