Robots in science fiction have incredible capabilities and are often seen blending rather well in human society, roaming around complex populated environments. But as roboticists have well learned, real robots are still far from this possibility, with robots that are often still kept at safety distances, caged, or in isolated environments, far from human reach. Two research directions have been trying to breach the barrier between humans and robots: physically (pHRI), and socially (sHRI). However, these two directions have been evolving without many intersections, with pHRI focused mainly on the development of controllers to guarantee efficiency and physical safety, and sHRI centralized on the perception and mental state of the human. But for robots to really coexist and collaborate with humans, it is necessary to take into account both physical and social interactions, achieving an active physical human-robot interaction (active pHRI): a type of physical interaction in which the robot should be able to achieve tasks optimally, efficiently, safely, and at the same time take into account the perception of human users. In this talk, I will illustrate the experiments we performed to take a first step towards achieving active pHRI by trying to understand humans, with some insights on the first results and perspectives on future developments.
