Learning interaction for collaborative tasks with probabilistic movement primitives

Abstract

Abstract-This paper proposes a probabilistic framework based on movement primitives for robots that work in collaboration with a human coworker. Since the human coworker can execute a variety of unforeseen tasks a requirement of our system is that the robot assistant must be able to adapt and learn new skills on-demand, without the need of an expert programmer. Thus, this paper leverages on the framework of imitation learning and its application to human-robot interaction using the concept of Interaction Primitives (IPs). We introduce the use of Probabilistic Movement Primitives (ProMPs) to devise an interaction method that both recognizes the action of a human and generates the appropriate movement primitive of the robot assistant. We evaluate our method on experiments using a lightweight arm interacting with a human partner and also using motion capture trajectories of two humans assembling a box. The advantages of ProMPs in relation to the original formulation for interaction are exposed and compared.

A Probabilistic Framework for Semi-autonomous Robots Based on Interaction Primitives with Phase Estimation

“…ProMPs use the concept of phases in the same manner, with the difference that the basis functions are used to encode positions. This difference is fundamental for Interaction Primitives since estimating the forcing function of the human is nontrivial in practice, while positions can be often measured directly [14].…”

“…It leverages on the representation of movements with ProMPs, our developments into the context of human-robot interaction [1,14], and the ability to address multiple tasks [14,8]. While our previous interaction models were explicitly time-dependent, here, we introduce a phase-dependent method.…”

Probabilistic movement primitives for coordination of multiple human–robot collaborative tasks

“…Therefore, even if several trajectories of different components largely overlap in space, it is still possible to identify the correct component with high certainty as the order at which those measurements are made are also taken into account. (The interested reader also is referred to (Maeda et al, 2014), where action recognition experiments were conducted in more detail).…”

“…In the context of movement primitives, this clock is often referred to as the phase variable. In this paper, all human and robot trajectories collected during the experiments presented in Section 4 were aligned by using the method briefly presented in (Maeda et al, 2014) and will be described in detail here.…”

“…This paper consolidates the theoretical framework of a mixture of Interaction ProMPs and validates the method in assistive and collaborative tasks. In less detail, parts of this paper have previously appeared in conference proceedings (Maeda et al, 2014;Ewerton et al, n.d.) where preliminary versions of our algorithm have been described. The remainder of this paper is organized as follows, Section 2 describes related work, Section 3 describes the proposed method and compares our method with the previous framework of interaction primitives based on Dynamical Movement Primitives (DMPs).…”