An experience-driven robotic assistant acquiring human knowledge to improve haptic cooperation

Abstract

Abstract-Physical cooperation with humans greatly enhances the capabilities of robotic systems when leaving standardized industrial settings. Our novel cognition-enabled control framework presented in this paper enables a robotic assistant to enrich its own experience by acquisition of human task knowledge during joint manipulation. Our robot incrementally learns semantic task structures during joint task execution using hierarchically clustered Hidden Markov Models. A semantic labeling of recognized task segments is acquired from the human partner through speech. After a small number of repetitions, the robot uses an anticipated task progress to generate a feed-forward set point for an admittance feedback control scheme. This paper describes the framework and its implementation on a mobile bi-manual platform. The evolution of the robot's task knowledge is presented and discussed. Finally, the cooperation quality is measured in terms of the robot's task contribution.

Towards safe physical human-robot interaction: An online optimal control scheme

“…One crucial question in this respect is how to model the human behavior. Learning methods are successfully employed to predict human intention in pHRI in a probabilistic fashion [1], those approaches are not suitable for absolute safety guarantees.…”

“…We consider a problem of controlling the linearized dynamics of a robotic manipulator in the task space, which is linearized by appropriate feedback linearization schemes [1], [2]. The discretized, linear, time invariant model of the manipulator is given by…”

“…In the first simulation, we consider the human is pushing the mass toward the vertical positive direction with a force of 1 N for 30 steps 1 . The desired reference trajectory is a step 1 Results are reported for one direction and can be used to both directions. of size 5.…”

“…However, in physical-human robot interaction (pHRI) autonomous robots need to operate not only in close vicinity of humans but even in direct contact with them [1]. According to Asimov's 1 st law, an essential requirement for coexistence of humans and robots is ensuring that the robot would not harm humans (highest priority), the environment, or itself.…”

Rapid Prototyping of Planning, Learning and Control in Physical Human-Robot Interaction

“…of Automatic Control Eng., 80290 Munich, Germany, e-mail: {ml, medina, hirche}@tum.de control [27,16,15,15,34,6] for physical human-robot interaction (pHRI) in a separate way. Only very few works consider the combination of learning and control in pHRI [11,20]. Another substantial difference in pHRI to classical robotics is the need for human user studies to evaluate the robot behavior in a human-centered way.…”