Learning Controllers for Reactive and Proactive Behaviors in Human–Robot Collaboration

Abstract

Designed to safely share the same workspace as humans and assist them in various tasks, the new collaborative robots are targeting manufacturing and service applications that once were considered unattainable. The large diversity of tasks to carry out, the unstructured environments, and the close interaction with humans call for collaborative robots to seamlessly adapt their behaviors, so as to cooperate with the users successfully under different and possibly new situations (characterized, for example, by positions of objects/landmarks in the environment or by the user pose). This paper investigates how controllers capable of reactive and proactive behaviors in collaborative tasks can be learned from demonstrations. The proposed approach exploits the temporal coherence and dynamic characteristics of the task observed during the training phase to build a probabilistic model that enables the robot to both react to the user actions and lead the task when needed. The method is an extension of the hidden semi-Markov model where the duration probability distribution is adapted according to the interaction with the user. This adaptive duration hidden semi-Markov model (ADHSMM) is used to retrieve a sequence of states governing a trajectory optimization that provides the reference and gain matrices to the robot controller. A proof-of-concept evaluation is first carried out in a pouring task. The proposed framework is then tested in a collaborative task using a 7-DOF backdrivable manipulator.

Interaction with proactive and reactive agents in box manipulation tasks in virtual environments

“…There are no interactions between users and agents. In robotics, approaches have been proposed to make controllers learn proactive or reactive behaviors . The controllers are often built up based on probability models.…”

“…In robotics, approaches have been proposed to make controllers learn proactive or reactive behaviors. [6][7][8] The controllers are often built up based on probability models. In a learning phase, the controllers encode human control at the preprocessing stage.…”

“…Proactive agents play a main leading role in guiding the process to complete tasks, whereas reactive agents respond to actions taken by users accordingly. Proactive and reactive controllers have been studied extensively in robotics . However, little attention is paid to investigate the user experience in interaction with proactive and reactive virtual agents in virtual environments.…”

“…Proactive and reactive controllers have been studied extensively in robotics. [6][7][8] However, little attention is paid to investigate the user experience in interaction with proactive and reactive virtual agents in virtual environments. We believe that such studies are important to understand user behaviors when users interact with these kinds of agents.…”

A Brief Survey on the Role of Dimensionality Reduction in Manipulation Learning and Control

“…Such trajectory distribution encoding with dynamic features has been exploited in robotics for human-like motion planning and control [36], [35], [37].…”