Last update: 5 June 2021
Overview
Human-robot collaboration is a widely studied field in research. However, in industry it is adopted at a slower than expected rate.
Collaborative robots need to be safe for interaction with humans. At the same time, they need to be easily programmed by non-experts and operate in an intelligent and adaptive way.
Despite the continuous advances of HRC research, applications are few and are usually downgraded to workspace sharing rather than actual collaborative work.
Taking full advantage of cobots in tasks such as collaborative manipulation of heavy parts, machine feeding or assembly operations has yet to demonstrate tangible results for the industry.
In this workshop we will investigate some of the latest advances in HRC. With the help of robot-willing industry representatives, we will discuss the impediments of cobot adoption in industry. Also, we will investigate the necessary efforts that are needed to unlock their potential.
Objective
In this workshop we are going to present the state of the art in HRC and try to unlock its potential for industrial adoption. With a panel of high-profile researchers and industrial representatives, we will discuss what are the needs of the industry and what steps should be made in the research towards efficient, safe and useful human-robot collaboration.
We will also present the challenges in real deployment of robots in different industrial applications, allowing young researchers to exchange ideas and results with senior researchers from both academia and industry, towards the goal of boosting HRC capabilities for the factories of the future.
Program
Start time in Paris 10am | Athens 11am | Beijing 4pm | Tokyo 5pm
Talks format: 15’ pre-recorded video presentation + 5’ live Q&A
Contributed papers format: 3’ pre-recorded video presentation + 15′ live Q&A in breakout rooms
Speakers
 | Zoe Doulgeri Aristotle University of Thessaloniki, Greece |
Novel control schemes for assisting teaching and performing with safety and accuracy in collaborative tasks.
Collaborative robots should be able to learn effectively from human demonstration and be able to generalize and operate in a safe and accurate manner in a shared workspace or with humans in order to perform industrial tasks, like pick and place, collaborative manipulation and assembly. In my talk, I will present some of the latest novel control methods and achievements developed within the CoLLaboratE H2020 project.
 | Ales Ude Josef Stefan Institute, Slovenia |
Trajectory prediction for object handover tasks
In this talk I present a recurrent neural architecture, capable of transforming variable-length input motion videos into a set of parameters describing the observed motion trajectory, where predictions can be made after receiving only a few frames. A simulation environment is utilized to expand the training database and improve the network’s generalization capability. The resulting system has been successfully applied to implement object handover task.
 | Alessandro Zanella Fiat Research Center – Stellantis, Italy |
Industrial application approach in Human Robot Collaboration and Research and Innovation Opportunities
The talk will summarize why the industry needs HRC and how it applies it in production lines. We will discuss the limitations arising during the full applicability of HRC and the opportunities for a short- and long-term R&I application.
 | Sylvain Calinon IDIAP, Switzerland |
Intuitive robot programming from few demonstrations
A wide range of industrial applications can benefit from robots acquiring manipulation skills by interaction with humans. In this presentation, I will discuss the challenges that such learning process encompasses, including the development of intuitive interfaces to acquire meaningful demonstrations, the development of representations for manipulation skills that can exploit the structure and geometry of the acquired data in an efficient way, and the development of optimal control techniques that can exploit variations in manipulation tasks.
 | Bram Vanderborght Vrije University, Belgium |
Unlocking the potential of industrial human–robot collaboration
Collaborative robotics is a unique technology that with proper management has the potential to improve both the economy and the society while embracing Europe’s values. The presentation discusses the EU-report with a vision on collaborative industrial robotics based on 10 assessment criteria with seven recommendations.
 | Arash Ajoudani IIT, Italy |
A collaborative robotic approach to next-generation flexible manufacturing
The shift from mass production to mass customization in industrial societies is underway. To respond to the flexibility needs in this new trend, industrial robots must be embedded with advanced locomotion and manipulation skills. In this direction, this talk introduces new thinking and techniques to the development and deployment of mobile robotic manipulators in industrial settings.
 | Kazuhiro Kosuge Tohoku University, Japan |
Co-worker Robot “PaDY” as an industrial application of pHRI
A co-worker robot PaDY (Parts and Tools Delivery Robot for You) is a robot which deliver a necessary part and a tool to a worker involved in as assembly process in an automobile factory. The robot delivers necessary items to the worker based on a predicted worker’s motion and generated trajectory using a receding horizon method. Several issues will be unveiled through real applications of the robot in the factory.
 | Pietro Falco ABB Corporate Research, Sweden |
Towards collaborative mobile manipulators
In my talk I will present the work on future ABB mobile manipulators and challenges to bring this technology in industrial and service application.
Contributed papers
We invite researchers to submit short papers (2-4 pages) presenting preliminary results, ongoing works and demos, relevant to the topic of the workshop. The papers will be reviewed by the organizers and acceptance will be based on the quality of the contribution, originality and relevance to the workshop’s topics of interest.
The accepted works will be presented in the workshop with a video presentation and a short live Q&A. The papers and the presentations will also be made available and archived on the workshop’s website.
Topics of interest:
- Physical Human-Robot Collaboration
- Shared Control
- Adaptation and Learning
- Physical Interaction Control
- Safe Human-Robot Collaboration
- Ergonomics
- Industrial collaborative robots
- Design, control and evaluation of robotic assistive devices
- Cognitive aspects of human-robot collaboration
- HRC applications
Contributed papers – Session I:
Real-Time Control of Robot Arms for Safe Human-Robot Coexistence
Kelly Merckaert, Bryan Convens, Marco M. Nicotra, and Bram Vanderborght
Robust, Unsupervised, and Ubiquitous Pose and Object Information for Robot Action Recognition
Dan Scarafoni, Irfan Essa, David Kent, Harish Ravichandar, Sonia Chernova and Thomas Plotz
Path Planning with Automatic Seam Extraction over Point Cloud Models for Robotic Arc Welding
Peng Zhou, Rui Peng, Maggie Xu, Victor Wu and David Navarro-Alarcon
Dynamic Active Constraint Construction for Enabling Human Safety During Human – Robot Collaboration
Georgia Peleka, Angeliki Topalidou-Kyniazopoulou, Ioannis Mariolis and Dimitrios Tzovaras
A Safety Kinodynamic Planning Framework for Human-Robot Collaboration
Andrea Pupa, Mohammad Arrfou, Gildo Andreoni and Cristian Secchi
Contributed papers – Session II
A Novel Tactile Device for Safe Human-Robot Interaction in Industrial Scenarios
Francesco Grella, Giulia Baldini1 Si Ao Wang, Keerthi Sagar, Alessandro Albini, Michal Jilich, Giorgio Cannata, Matteo Zoppi
Deep learning architectures applied for recognizing human motion primitives from the Ergonomic Assessment Worksheet
A. Aubert, B. E. Olivas-Padilla, V. Syrris, S. Manitsaris
Knowledge Representation for Collaborative Robotics and Adaptation
Alberto Olivares-Alarcos, Sergi Foix, Stefano Borgo and Guillem Aleny
APPRENTICE: Towards a Cobot Helper in Assembly Lines
Yunus Terzioglu, Ozgur Aslan, Burak Bolat, Batuhan Bal, Tugba Tumer, Fatih Can Kurnaz, Sinan Kalkan, Erol Sahin
Trust attribution in collaborative robots: An experimental investigation of non-verbal cues in a virtual human-robot interaction setting
Ahmet Meric¸ Ozcan, Cengiz Acarturk and Erol Sahin
Organizers
Aristotle University of Thessaloniki
Aristotle University of Thessaloniki
Josef Stefan Institute
Fiat Research Center – Stellantis
Supporters
Endorsed by the RAS Technical Committees
CoLLaboratE Project © 2018-2020 All rights reserved.