SMART – EU H2020 – MARIE SKLODOWSKA-CURIE G.A. N. 860108

Since March 2020 – Duration: 4 years

SMART Innovative Training Network (ITN) is a joint venture among academia and industry. The consortium aspires to exploit smart, stimuli-responsive material systems with actuation, sensing and self-healing capabilities towards a new era of more resilient class of robots. Three are the main objectives of the project. Intelligent control systems to enable interaction with the unpredictable outer world, revolutionary actuation abilities to work with sophisticated environments, structural health monitoring systems to automate the self-healing procedures during the time of damage/failure-in-intended-functionality.
Our group is responsible for the state-of-the-art machine learning based sophisticated control solutions for the high degree of freedom soft robots. Associated pictures and videos will be published soon (publications are still under review).
SMART brings together 8 beneficiaries and 11 partner organizations including 2 research institutes and 12 private companies, belonging to 7 EU member states, and 2 to associated states (Switzerland and Turkey).
Further information on the official website: http://www.smartitn.eu/.

PROBOSCIS – EU H2020-FETOPEN-2019-01 – G.A. N. 863212

Since November 2019  – Duration: 4 years

The project aims at developing a continuum Soft Manipulator inspired by the elephant trunk. Indeed, the elephant proboscis is a very interesting and multifunctional organ: besides serving physiological (e.g. breathing, smelling) and social (e.g. disciplining, communication) functions, it is the main organ by which elephants interact with the world, performing both strong and delicate, highly precise manipulation tasks (e.g. reaching, grasping) and other operations (e.g. collection, sucking, siphoning). This ambitious research envisions a new generation of universal robotic manipulators that, like elephants, engage with uncertain environments, promptly adapt to unexpected situations, and perform a multitude of real-world grasping tasks with high dexterity.
These robots will exploit intrinsic high mechanical compliance (soft body adaptability), and rich proprioceptive and exteroceptive sensorial feedback (distributed sensing), mainly based on artificial touch, to perceive the world and control the interaction with it.
Understanding of morphological, biomechanical and behavioural aspects is fundamental for the development of this new paradigm of bioinspired manipulators. In this challenging process, new robotic principles and technologies for fully embodied soft sensing and actuation will originate: soft and smart printable materials as well as additive manufacturing technologies will be developed; additionally, novel principles for active robotic exploration, grasping and manipulation driven by tactile sensing will be formulated.
The contribution of the BRAIR Lab as partners is mainly devoted to the definition of behavioral experiments for different grasping and manipulation strategies, that will provide data for the development of kinematic and dynamic models of the elephant trunk. Moreover, a huge effort is put to tailor the control of the artificial proboscis to achieve tactile-driven grasping and reaching and grasping motion strategies using machine learning techniques.
The other project partners are Istituto Italiano di Tecnologia (IIT), the Hebrew University of Jerusalem (HUJI), University of Geneva (UNIGE) and Photocentric (PHC).

Further information on the official website: https://proboscis.eu/.

GROWBOT – EU H2020-FETPROACT-2018-01 – G.A. N. 824074

Since November 2019 – Duration: 4 years and 6 months

This project proposes a disruptively new paradigm of movement in robotics inspired by the moving-by-growing abilities of climbing plants. Plants are still a quite unexplored model in robotics and ICT technologies, as their sessile nature leads to think that they do not move. Instead, they move greatly, on a different time scale, purposively, effectively and efficiently. To move from one point to another, plants must grow and continuously adapt their body to the external environmental conditions. This continuous growth is particularly evident in climbing plants. The GrowBot objective is to develop low-mass and low-volume robots capable of anchoring themselves, negotiating voids, and more generally climbing, where current climbing robots based on wheels, legs, or rails would get stuck or fall.
GrowBot is based on a strongly interdisciplinary character and can open the way for a new technological paradigm around the concept of growing robots, fostering a European innovation eco-system for several high-tech sectors.
Further information on the official website: https://growbot.eu/.

HUMAN BRAIN PROJECT

Since 2013 – Duration: 10 years

The Human Brain Project (HBP) is one of the three FET (Future and Emerging Technology) Flagship projects. More than 500 scientists and engineers at over than 140 universities, teaching hospitals, and research centres across Europe come together to address one of the most challenging research targets – the human brain. To tame brain complexity, the project is building a research infrastructure to help advance neuroscience, medicine, computing and brain-inspired technologies - EBRAINS.
The project provides a framework where teams of researchers and technologists work together to scale up ambitious ideas from the lab, explore the different aspects of brain organisation, and understand the mechanisms behind cognition, learning, or plasticity. Teams transfer the acquired knowledge to make an impact in health and innovation: insights from basic research are translated into medical applications, to prepare the ground for new diagnoses and therapies. Discoveries about learning and brain plasticity mechanisms are used to inspire technologic progress, e.g., in artificial intelligence. In addition, the project studies the ethical and societal implications of the advancement of neuroscience and related fields.
Currently in its final phase (April 2020 – March 2023), the HBP’s focus is to advance three core scientific areas – brain networks, their role in consciousness, and artificial neural nets – while further expanding EBRAINS.
Our group is involved in the “Adaptive networks for cognitive architectures: from advanced learning to neurorobotics and neuromorphic applications” Work Package (WP). The central ambition of the WP consists in achieving a measurable step forward in our understanding of human cognition; specifically, how biological learning networks enable human visuo-motor and cognitive functions. The approach implemented is to emulate the architecture and operation of the brain. In practice, this corresponds to the design of functional cognitive architectures, addressing challenging visuo-motor and cognitive problems.
Further information on the official website: https://www.humanbrainproject.eu/en/.