Projects

Selected ongoing projects:

CoBoTaT – Laboratory for Advancing Collaborative Robot Behaviors in Physical Human-Robot Interaction Scenarios

JSI DIRECTOR’S FUND

Recent technology developments enable robots to safely share a common workspace with humans. Europe is currently leading the robotic market for safety-certified robots by providing tools that can react to unintentional contacts. CoBoTaT will leverage these technologies and strengthen the position of JSI in Europe by developing a fully sensorized laboratory environment for studying human-robot collaboration, enabling us to enhance robots’ capabilities of learning, working and assisting people in their natural environments. By exploiting this environment, CoBoTaT will generate novel technological and scientific breakthroughs. This will have a positive social impact on humans by improving the assistive capabilities of robots for applications such as household keeping, assistance in working environments, and even elderly care.

PI: Doc. Dr. Tadej Petric (JSI)


PhRoCiety – Collaborative Capabilities in Physical Human-Robot Interaction Scenarios

ARRS
(no.: N2-0130)

The aim of PhRoCiety is to advance cognitive understanding and the current control about cooperative and robust multi-contact physical interaction between multiple agents, where agents are humans or robots. PhRoCiety will go beyond traditional approaches by: (1) proposing novel control methodologies for performing cooperative tasks with multiple agents in physical human-robot or robot-robot interaction scenarios; (2) combining cognitive learning and physical interaction with predictable and unpredictable events; (3) validating theoretical advances in real-world physical interactive scenarios.

PI: Doc. Dr. Tadej Petric (JSI)


SWITCH – Learning by Switching Roles in Physical Human-Robot Collaboration

Bilateral project SNSF/ARRS
(no.: N2-0153)

In physical human-robot collaboration, robots currently face a shortcoming due to their limitations in observing and adapting to human dynamics. This further results in inefficient collaboration and unergonomic interaction. SWITCH will address this shortcoming by developing methods that can efficiently observe human dynamics in real-time and learn anticipatory models from a demonstration. First, we will collect several datasets of force and motion capture data for a human-human standing up task. We will then develop models that can learn the behaviors of the two agents (assistant and assisted) in a probabilistic fashion. These models will be exploited for the on-line control of robots with reactive and anticipative capabilities.

PIs: Dr Sylvain Calinon (Idiap) & Doc. Dr. Tadej Petric (JSI)


Generation and Learning of Adaptive Cyclic Movements in Assist-As-Needed Applications for Human-Robot Interaction

In the scope of this project, we strengthen the connections between our group and the group at the Johannes Kepler University in Linz.

PIs: Univ.-Prof. Dr.-Ing. habil. Andreas Müller (JKU) & Doc. Dr. Tadej Petric (JSI)


Past projects

Establishing new tools to facilitate new generation humanoid robot capabilities for collaborative human-robot object manipulation

In the scope of this project, we strengthen the connections between our group and the group at the University of Belgrade, Faculty of Electrical Engineering.

PIs: Asst. Prof. Kosta Jovanovic (JKU) & Doc. Dr. Tadej Petric (JSI)