Versatile, reliable, able to perform various operations with precision, robots are the preferred tools in flexible automation systems, where manufacturing is expected to change based on the changing needs of the market. Typical robot operations include loading/unloading of machines, welding, painting, all tasks in which the speed of execution increases the productivity of the factory, decreasing cycle times and exempting humans from performing such tasks in uncomfortable conditions. The spread of the production paradigms of Industry 4.0 has given renewed importance to the use of robots, as highly digitalised machines. Alongside traditional industrial manipulator systems, mobile robots (AGV, AMR, LGV) are of increasing importance in industrial logistics and, in general, in applications relating to material flow and transport. Robotics also benefits from the evolution of other production technologies, in particular additive manufacturing, where the robot manipulator is equipped with a tool for deposition of material or is integrated with 3D printers to improve its productivity. Collaborative robotics is a key enabling technology for safe operation in mixed human‒robot environments.

INVERSE

INVERSE
  •  ​ INteractive robots that intuitiVely lEarn to inVErt tasks by ReaSoning about their Execution
  • ​  January 2024 ‒ December 2027
  • ​  7,999,873.50 €
Despite the impressive advancements in Artificial Intelligence (AI), current robotic solutions fall short of the expectations when they are requested to operate in partially unknown environments. Most of all, robots lack the cognitive capabilities to understand a task to the point of being able to perform it in a different domain. As humans, during the learning process we gain deep insights on the execution of a process, which allows us to replicate its execution in a different domain with a little effort. We are also able to invert the task execution and to react to contingencies, by focusing the attention to the most critical prediction phases. However, replicating these cognitive processes in AI-driven robots is challenging as it needs a profound rethinking of the robot learning paradigm itself. The robot needs to understand how to act and imagine, like humans do, the possible consequences of its actions in another domain. This demands for a novel framework that embraces different levels of abstraction, starting from physical interaction with the environment, passing through active perception and understanding, and ending-up with decision-making. The INVERSE project aims to provide robots with these essential cognitive abilities by adopting a continual learning approach. After an initial bootstrap phase, used to create initial knowledge from human-level specifications, the robot refines its repertoire by capitalising on its own experience and on human feedback. This experience-driven strategy permits to frame different problems, like performing a task in a different domain, as a problem of fault detection and recovery. Humans have a central role in INVERSE, since their supervision helps limit the complexity of the refinement loop, making the solution suitable for deployment in production scenarios. The effectiveness of developed solutions will be demonstrated in two complementary use cases designed to be a realistic instantiation of the actual work environments
 

MELODY

PRIN
  •  ​ Multi robot collaborativE manipuLation suppOrting DisassemblY tasks
  • ​  November 2023 ‒ November 2025
  • ​  220,921,17 €
The emerging Industry 5.0 paradigm emphasizes the role of research and innovation in facilitating the transition towards a sustainable, human-centered, and resilient industrial landscape. Aligned with these principles, the MELODY project is conceived to support the circular economy by optimizing the remanufacturing process and simultaneously alleviating the workload associated with ergonomically challenging tasks. In pursuit of these goals, MELODY aims to develop a cooperative framework for task disassembly, facilitating effective bidirectional interaction between humans and a robotic system comprising multiple manipulators.
 

TOP

UNINA
  •  ​ New Engineering & Manufacturing Enhanced System Innovation
  • ​  January 2020 ‒ December 2023
  • ​  3,500,000 €
The TOP project is aimed at expanding and enhancing the production capability, the processes and the organization of the manufacturing and assembly lines of the Leonardo plants in Pomigliano d'Arco. The research & development program focuses on the development of automated systems capable of supporting the production and assembly of sections and structural components of the ATR fuselage, designed in a digitized factory framework compliant with the Industry 4.0 paradigm. The technological solutions concern cyber physical systems, internet of things, big data, artificial intelligence, robotics and intelligent energy management.
 

foAIming

UNINA
  •  ​ Artificial intelligence and robotics in polymer foaming
  • ​  April 2021 ‒ March 2023
  • ​  39,795 €
The project aims at the introduction of artificial intelligence (AI) and robotics methods in the field of materials science and chemical processes engineering for improving the foaming processes and achieving new foams with enhanced properties. In particular, we propose the design and development of a system for remote management of foaming experiments that allows: autonomous/interactive conduct of the experiments; measurement of the foams' properties; analysis, modeling and regulation of the foaming process.
 

ICOSAF

ICOSAF
  •  ​ Integrated and collaborative systems for the intelligent factory
  • ​  September 2018 ‒ March 2021
  • ​  4,927,079 €
ICOSAF aims at technologies and systems for a collaborative factory with a growing integration of the operator in line with the principles of Industry 4.0 (interconnected automation) and 5.0 (humanization and re-use of resources). This vision includes mobile and fixed robotic systems, active monitoring systems of quality and machinery operator assistants and AGVs that interact with operators and environment. The integration of these systems into the smart factory leads to improvements in productivity, quality, flexibility and ergonomics. The enhancement of operator’s capabilities, assisted by automated systems in low-value added operation, enables more pervasive utilization of human intelligence and flexibility along with the high performance of the automation. New technologies and cooperative systems are analyzed at the level of modeling, theoretical development and realization of prototypes which are then validated in enterprises-driven test cases.
 

REFILLS

REFILLS
  •  ​ Robotics Enabling Fully-Integrated Logistics Lines for Supermarkets
  • ​  January 2017 ‒ December 2020
  • ​  3,692,850 €
  • ​ ​website

While online grocery stores are expanding, supermarkets continue to provide customers with the sensory experience of choosing goods while walking between display shelves. Retail and logistics companies are committed towards a shopping experience more comfortable and exciting while, at the same time, using technology to reduce costs and increase efficiency. REFILLS is to improve logistics in a supermarket thanks to mobile robotic systems in close and smart collaboration with humans, addressing the main in-store logistics processes for retail shops such as smarter shelf refilling. Information on the articles is exploited to create powerful knowledge bases, used by the robots to identify shelves, recognize missing or misplaced articles, handle them and navigate the shop. Reasoning allows robots to cope with changing task requirements and contexts, and perception-guided reactive control makes them robust to execution errors and uncertainty.

 

ROMOLO

ROMOLO
  •  ​ Modular robots for hospital logistics
  • ​  June 2017 ‒ December 2019
  • ​  853,617 €

The project is focused on modular robotic systems capable of working in hospitals by performing different tasks in the logistics. Proper systems and components are to be developed with appropriate interfaces to users and with hospital networks and systems. These technologies can make more efficient hospitals and have a positive impact on patients and staff. The proposed robotic system consists of an omnidirectional mobile base capable of transport, after a suitable coupling, various accessory modules, e.g. trolley with laundry, system drug dispenser, telepresence vision system, through the wards of a hospital.

 

RODYMAN

REFILLS
  •  ​ Robotic Dynamic Manipulation
  • ​  June 2013 ‒ May 2019
  • ​  2,496,600 €
  • ​ ​website
The goal of the RODYMAN project is the derivation of a unified framework for dynamic manipulation where the mobile nature of the robotic system and the manipulation of non-prehensile non-rigid or deformable objects are taken into account. Novel techniques for 3D object perception, dynamic manipulation control and reactive planning will be proposed. An innovative mobile platform with a torso, two lightweight arms with multi-fingered hands, and a sensorized head is to be developed for effective execution of complex manipulation tasks, also in the presence of humans. Dynamic manipulation is tested on an advanced demonstrator, i.e. pizza making process, which is currently unfeasible with the prototypes available in the labs. The research results to be achieved in RODYMAN contribute to paving the way towards enhancing autonomy and operational capabilities of service robots, with the ambitious goal of bridging the gap between robotic and human task execution capability.
 

DEXMART

DEXMART
  •  ​ Dexterous and Autonomous Dual-Arm/Hand Robotic Manipulation with Smart Sensory-Motor Skills: A Bridge from Natural to Artificial Cognition
  • ​  February 2008 ‒ January 2012
  • ​  6,300,000 €
  • ​ ​website

The DEXMART project is focused on artificial systems reproducing smart sensory-motor human skills, which operate in unstructured real-world environments. The emphasis is on manipulation capabilities achieved by dexterous, autonomous, human-aware dual-arm/hand robotic systems. The goal is to allow a dual-arm robot including two multi-fingered redundant hands to grasp and manipulate objects with different shape, dimension and weight. Manipulation takes place in an unsupervised, robust and dependable manner so as to allow the robot to safely cooperate with humans for the execution of given tasks. The robotic system has: to possess the ability to autonomously decide between different manipulation options, to properly and quickly react to unexpected situations and events such as changes in human cooperation, to acquire knowledge by learning new action sequences so as to create a consistent and comprehensive manipulation knowledge base through an actual reasoning process.