Autonomous and hybrid plants require a high level of automation and understanding of the processes within where collaborative robots have a high potential. The development of collaborative robotics as a research area is based on the study of computer vision, machine learning and artificial intelligence to provide robots with high vision skills and knowledge to interact safely and effectively in the workplace and assist humans in arduous or repetitive tasks.

In this training session, the first of a series of training workshops, several perception techniques to increase collaborative robots’ knowledge and skills to perceive, comprehend and reason about the surrounding environment were presented. The concepts presented included several technologies and methodologies to enhance the robot ability for the detection of the objects and humans in the environment, identify humans’ posture and activities and understand the human behavior or model desired motions for our robots.

During the session, showcasing basic concepts on methods to enrich collaborative robotics recognition and perception capabilities, Sharework researchers aimed to contribute to training the next generation of Human-Robot Collaboration investigators and disseminating project advancements to the scientific and education community. The session content comprised basic concepts and techniques used to perform an environmental analysis and provide robots with the necessary intelligence to recognise their surroundings and act accordingly. The concepts presented were exemplified with comprehensive case studies developed under the framework of the Sharework project.

Event topics:

• Basic concepts of machine learning to transport knowledge from artificial data to real-world applications.
• Human tracking concepts and revision of the state of the art with comprehensive examples.
• Density estimation models for robot motion prediction, gesture classification or motion generation.
• Basic knowledge of human-task recognition to develop a robust system predicting the action the worker is performing using multiple real-time video streams.
• How to design a robotic system knowledge base representing the general properties and featuring collaborative robotics application scenarios.

Targeted to:

• Undergraduate, graduate or master students willing to learn about the application of computer vision, learning primitives and machine learning to enhance collaborative robotics environmental perception ability.
• Researchers in Human-Robot Collaboration, cognition robotics and Human-Robot Interaction, computer vision from Universities and research centers.
• Professionals from companies in the field of robotics, computer vision or Industry 4.0.

Simona Neri, Sharework project coordinator, Eurecat

Program manager in the field of fund-raising industry. Enthusiastic about innovation, science and technology with a solid international experience, strong stakeholder management skills and proven scientific background and innovation experience. Currently working in Eurecat and proudly coordinating Sharework project.

 

 

 

 

Nils Mandischer, scientific employee, RWTH Aachen University

Nils Mandischer M.Sc. is a scientific employee of four years at the Institute of Mechanism Theory, Machine Dynamics and Robotics (IGMR) of RWTH Aachen University. His main fields of research are computer vision, sensor data analysis and human-robot-collaboration in firefighting, resulting in the team lead of human-robot-teaming special research group at IGMR. His main contribution in Sharework is in the field of autonomous item detection and localization and safety for industrial manipulators.

 

 

 

Andrea Orlandini, researcher, ISTC-CNR

Researcher working at the Institute of Cognitive Sciences and Technologies (ISTC-CNR), in Rome. He got a degree in Computer Science Engineering and he received his PhD in 2006 defending the thesis “Logical Based Approaches to Artificial Intelligence Planning and Robot Control” at the Roma Tre University in Rome (Italy). He is currently working within the Planning and Scheduling Team at ISTC-CNR, studying temporal plan validation and execution problem in research projects. His research interests span over automated planning, temporal logic, dependable plan execution and model-based robot control.

 

 

 

Magí Dalmau, researcher, Robotics & Automation Unit, Eurecat

Magí Dalmau received the Industrial Engineering degree from the Polytecnic University of Catalonia (UPC), in 2019; and a MSc in Intelligent Interactive Systems from Pompeu Fabra University (UPF), in 2022. He joined Eurecat in 2019, where he is Robotics Researcher within the Collaborative Manipulation research group and has actively participated in the research and developments of public (European and national) and private projects. His current research interests are focused on AI task and motion planning, RL-based robot behaviors generation, and human-robot interaction.

 

 

 

Julen Urain, PhD Candidate, Technical University Darmstadt

Julen Urain M.Sc. is a fourth year PhD candidate in the Intelligent Autonomous Systems group in Technical Universitat Darmstadt (TUDa). His main fields of research are the imitation learning and density estimation for robot motion generation. His main contribution in Sharework is in the field of building gesture and motion models to represent and predict human motion.

 

 

 

 

 

Néstor García, Principal Investigator, Robotics & Automation Unit, Eurecat

B.S. degree (with honors) in Industrial Engineering and the Ph.D. degree (also with honors) in Automatic Control, Robotics and Computer Vision, both from the Polytechnic University of Catalonia (UPC), Barcelona, Spain, in 2015 and 2019 respectively. He joined Eurecat in 2018, where he is the Principal Investigator of the Collaborative Manipulation research group. His current research interests are focused on task and motion planning, human-robot interaction, multirobot cooperation and learning in robotic systems.  He is acting Eurecat technical lead for the European projects Sharework, Bots2Rec and national project Simbiots.