Projects

Global warming and pollution are threatening the survival of one million over the eight million species in forests and oceans on the planet. The EU answer to these challenges is the set of deeply transformative policies contained in the European Green Deal. Among these policies a prominent role is given to the restoring and preservation of ecosystems by increasing the coverage of protected biodiversity-rich land and sea areas building on the Natura 2000 network.
Stretching over 18% of the EU’s land area and almost 6% of its marine territory, Natura 2000 is the largest coordinated network of protected areas in the world. The land and sea coverage will be increased up to 30% within 2030.
Today human operators are the only option to perform the environmental monitoring of such a large area. This is not only because of their specific expertise and knowledge in classifying plants and habitats but also because their physical intelligence allowing them to move for hours in wild unstructured environments such dunes, forests, and mountains.
The artificial alternative is robotics, which made tremendous advancements in recent years, however robots hardly leave laboratories and factories because they are not robust and efficient to survive in the real world. Flying robots do not have the required energy autonomy, while ground robots are not:

i) intelligent to autonomously percept, interpret, and interact with highly uneven, slipping and irregular grounds;

ii) physically robust to manage unexpected contacts and impacts.

The Natural Intelligence (NI) project aims to serve the European Green Deal via monitoring the natural habitats of N2000N with robots able to effectively move in dunes, grasslands, forests, and alpine terrains. NI robots will be empowered by Natural Intelligence, emerging by the interaction of environment, body and mind, leveraging on the fusion of artificial cognition and articulated soft-robotics bodies.

Currently industrial robots perform rigidly programmed tasks in highly-constrained settings. Any change in product or process requires costly restructuring of hardware and software.

ReconCycle will address these issues by introducing the concept of robotic self-reconfiguration in the largely unconstrained domain of electronic waste recycling, which is still dominated by manual labor. Automation in this sector can benefit from the fact that very large batches of the same device type are to be processed but with some model differences and showing different states of damage. To be able to deal with each of these individual models, the robotic system requires flexible adaptation.

Thus, the scientific objective of ReconCycle is to introduce in this sector self-reconfigurable hardware and software based on a reconfigurable robotic cell developed in a previous project. A two-step procedure is foreseen: When changing from one device-type to another, reconfiguration shall be performed in an interactive mode, where the application-engineer will be able to provide input. But, when changing from one device-model to another within a given device-type, the cell shall perform re-configuration on its own through a combination of sensorimotor learning approaches and other AI techniques. This constitutes the main novel scientific contributions of ReconCycle and is aimed at advancing our understanding of robotic perception-action processes in unconstrained industrial settings. We will use highly compliant soft robots and end-effectors, allowing humans to operate together with the machines to complete any missing steps. This reduces automation complexity and brings this project into a feasible regime for up to TRL 6. Electronic waste recycling is an important and strongly growing economic and environmental sector.

The industrial objective of ReconCycle is to introduce here a much-increased level of automation resulting in a potentially high long-term impact on industry and society.

qbrobotics company successfully realized an Internationalization project in United States and in China with the financial support of the funds related to the program “Programma operativo regionale (Por) Fondo europeo di sviluppo regionale (Fesr) 2014-2020” and promoted by Regione Toscana.

An old adage in the field of robotics says that “the best measure to assess the robustness of a robot system is how far you trust to be when the system is functioning”. This reflects both the fact that one of the most important aspect that distinguishes a good robotic system from a mediocre one, is its robustness to uncertainties and unexpected events, and the fact that measuring this difference is still mostly done with rules of the thumb. Both of these considerations are still very true for legged locomotion system. Important aspects that characterizes a legged robot system are the robustness of its static balance and of its dynamic walking gait.

The DYSTURBANCE project proposes to realize a perturbation system to be used for the systematic characterization of walking robots and locomotion systems. In particular, the system we plan to realize will enable reproducible issuing of both dynamic and static perturbations forces, that would enable the systematic study of gait and balance resilience and robustness. The proposed system draws inspiration from classical Resilience testing machines used in standardized testing of material samples (as the Charpy test rig) so to realize, in the simplest and easily reproducible way, a system capable of exerting a given desired force or impulse perturbation. The system will integrate position, and force sensors, so to be able to fully characterize the disturbance that we are applying to the walking system. Moreover, it will integrate a motorized shaft, so to be able to control the exertion of forces both in the static and dynamic cases. Finally, the system will be implemented in the form of a moveable portal for easy integration with other experimental rigs, as treadmills, sensorized platforms and other system.

“Picking and placing objects that are orderly presented to a robot is a task that can be easily performed by current robots. However, grasping and manipulating objects randomly placed in an unstructured environment remains one of the hardest challenges for robots. Examples of complex picking industrial applications include (i) bin picking for part feeding, (ii) raw food handling and (iii) waste sorting for recycling. Within the “”SoftHandler”” ERC Proof of Concept project, we propose to develop new industrial-grade systems, comprised of end-effectors based on the “”SoftHands”” technology, integrated with a novel manipulator, for automated picking and placing of objects of heterogeneous dimension, shape, weight, position and strength. The Proof of Concept project will be focused on building a commercially viable prototype, and demonstrating it in real-world scenarios.

THING will advance the perceptual capabilities of highly mobile legged platforms through haptic perception and active exploration. In this light, THING will deliver:

1. Novel foot designs for enhanced tactile perception and locomotion,
2. Improved perceptual capability, enriching existing modalities (lidar, vision) with haptic information,
3. Heightened physical sense of the environment, including friction, ground stability (difficult through vision alone), and
4. Enhanced mobility through improved perception, prediction, and control.

In the project “SoftHands” we have achieved not only a more thorough understanding of the organization and control of hands, but also a principled approach to taming the complexity of hand design. The original concept of “soft synergies” has underpinned the realization of radically new artificial hands: “SoftHands” have been demonstrated to be more adaptive and capable than most artificial hands, yet are simpler to control and more robust. One application of these ideas and technologies which stands out for potential impact and social relevance, although not originally foreseen in the ERC AG plan, is the realization of upper limb pros-theses.

The objective to realize a prosthetic hand that is anthropomorphic, aesthetically pleasing, and enables an amputee to perform most activities of daily living as well as advanced prostheses, while being robust, intuitive, and economic as basic body-powered split-hook prostheses requires a much longer and larger re-search and development effort than an ERC POC can support. In this proposal we study the feasibility of applying the SoftHand technology to address one particular, but very important, objective, i.e. work-oriented prostheses.

The specific requirements of these applications are high grip power, grasp versatility, resilience, resistance to water, dust, and temperature, durability, power autonomy and low cost – while factors such as aesthetics or silent operation are less dominant. Of particular relevance is the control interface with the patient. Virtually all work-oriented prostheses are operated via a body-powered cable, which is very intuitive to use and does not need batteries, motors, and sensors. On the other hand, advanced multi-fingered prostheses have sophisticated myoelectric control affording versatility and dexterity. In this project, we will engineer and experiment a novel hybrid control for a SoftHand prosthe-sis, whereby a traditional cable harness commands the advanced mechatronic system of the SoftHand.

Daedalus is conceived to enable the full exploitation of the CPS concept of virtualized intelligence, through the adoption of a completely distributed automation platform based on IEC-61499 standard, fostering the creation of a Digital Ecosystem that could go beyond the current limits of manufacturing control systems and propose an ever-growing market of innovative solutions for the design, engineering, production and maintenance of plants’ automation.

The following objectives will be reached:

• Ease the conception, development and distribution of intelligence into CPS for real-time execution of orchestrated manufacturing tasks;
• Foster interoperability of CPS from different vendors at orchestration-level (= “between CPS”);
• Simplify the design, implementation and integration of optimal coordinating control intelligence of CPS;
• Enable near-real-time co-simulation of manufacturing systems as a fully integrated “service” of a CPS;
• Create a Digital Marketplace to simplify the matchmaking between offer and demand within the Ecosystem;
• Conceive a multi-sided business model for the Automation Ecosystem and the corresponding business plans for its Complementors;
• Foster the widespread acceptance of the Ecosystem platform to guarantee success and impact of Daedalus multi-sided market.

The project approach is based on 3 technological pillars, one platform pillar and a final ecosystem pillar:

1. IEC61499-based reconfigurable automation platform for distributed orchestration of interoperable CPS;
2. “Simulation-as-a-service” for integrated near-real-time co-simulation of CPS behavioural models;
3. Advanced SDKs for simplified design of hierarchically distributed optimal control applications;
4. Digital Marketplace for the creation of an interdependent ecosystem of automation solutions providers;
5. Proof-of-concept showcases to accelerate the involvement of “complementors” and the maturation of the Ecosystem.

Although much has been done for developing technologies to bear upon problems of individuals with sensorimotor impairments, the impact of robotic aids on people with real needs in the real world is still very limited. Our main goal is to increase the cumulative benefits of assistive robotic technologies to society by enhancing their effectiveness AND the number of beneficiaries. The challenge is to increase both multipliers in the “performance times accessibility” product, subverting the traditional situation where one factor can only be increased at the expense of the other. We believe this is possible by investigating how the artificial can physically interact and effectively “talk to” the natural. Understanding such a “language” is crucial not only to improve performance of rehab technology, but also to tackle the most difficult problem of making it “simple enough” to be effective and accessible. We possess good clues about such a language, whose words we believe are sensorimotor synergies, and have the scientific competence to further its understanding and the technological prowess to translate it into a new generation of robotic assistive devices.

We know that a central ingredient for the applicability of synergy-based models to physical human-machine interaction is impedance adaptability, i.e. soft robotics technologies. We will develop soft synergy-based robotics technologies to produce new prostheses, exoskeletons, and assistive devices for upper limb rehabilitation.
Building on solid methodological bases, this project will have a significant social impact in promoting advanced robot prosthetic and assistive technology, while introducing disruptively new, admittedly risky, but potentially high-impact ideas and paradigms, such as the proposed pioneering work on supernumerary limbs for assistance and rehabilitation to motor impairments of the upper limb.

Cognitive Systems and Robotics Recent progress in physical Human-Robot Interaction showed that active and safe workspace sharing becomes possible in principle. SAPHARI will perform a fundamental paradigm shift in robot development in the sense that the human will be the centre of the entire design. The project will enable robots to track, understand and predict human motions in a weakly structured dynamic environment in real-time. The project will focus on industrial use cases that require contacts and force exchange in human-robot co-work, as well as on professional service scenarios in hospitals, in which a medical staff and an assisting robot interact closely during daily work. Results of this project will impact all applications where interactive robots can assist humans and release them from dangerous or routine tasks.