A5086291668- Robot Manipulation and Learning
- Teleoperation and Haptic Systems
- Prosthetics and Rehabilitation Robotics
- Soft Robotics and Applications
- Muscle activation and electromyography studies
- Reinforcement Learning in Robotics
- Manufacturing Process and Optimization
- Stroke Rehabilitation and Recovery
- Robotic Path Planning Algorithms
- EEG and Brain-Computer Interfaces
- Robotic Mechanisms and Dynamics
- Human-Automation Interaction and Safety
- Digital Transformation in Industry
- Advanced Control Systems Optimization
- Human Pose and Action Recognition
- Tactile and Sensory Interactions
- Musculoskeletal pain and rehabilitation
- Hydraulic and Pneumatic Systems
- COVID-19 Clinical Research Studies
- Flexible and Reconfigurable Manufacturing Systems
- Industrial Vision Systems and Defect Detection
- Robotic Locomotion and Control
- Modular Robots and Swarm Intelligence
- COVID-19 diagnosis using AI
- Advanced Vision and Imaging
University of Applied Sciences and Arts of Southern Switzerland
2019-2024
Università della Svizzera italiana
2019-2024
Dalle Molle Institute for Artificial Intelligence Research
2019-2024
Stanford University
2024
Politecnico di Milano
2014-2023
University of Salerno
2023
University of Parma
2021
National Research Council
2014-2020
Institute of Intelligent Industrial Systems and Technologies for Advanced Manufacturing
2019-2020
Institute of Intelligent Systems for Automation
2020
The letter presents a force-tracking impedance controller granting free-overshoots contact force (mandatory performance for many critical interaction tasks such as polishing) partially unknown interacting environments (such leather or hard-fragile materials). As in applications, the robot has to gently approach target environment (whose position is usually not well-known), then execute task. Therefore, algorithm been designed deal with both free space approaching motion (phase a.) and...
Physical human-robot collaboration is increasingly required in many contexts (such as industrial and rehabilitation applications). The robot needs to interact with the human perform target task while relieving user from workload. To do that, should be able recognize human's intentions guarantee safe adaptive behavior along intended motion directions. robot-control strategies such attributes are particularly demanded field, where operator guides manually manipulate heavy parts (e.g., teaching...
Abstract This paper presents a learning-based method that uses simulation data to learn an object manipulation task using two model-free reinforcement learning (RL) algorithms. The performance is compared across on-policy and off-policy algorithms: Proximal Policy Optimization (PPO) Soft Actor-Critic (SAC). In order accelerate the process, fine-tuning procedure proposed demonstrates continuous adaptation of RL new environments, allowing learned policy adapt execute (partially) modified task....
The paper focuses on industrial interaction robotics tasks, investigating a control approach involving multiples learning levels for training the manipulator to execute repetitive (partially) changeable task, accurately controlling interaction. Based compliance control, proposed consists of two main levels: 1) iterative friction compensation controller with reinforcement and 2) force-tracking reinforcement. algorithms rely procedures automatize controllers parameters tuning. procedure has...
Robots are increasingly exploited in production plants. Within the Industry 4.0 paradigm, robot complements human's capabilities, learning new tasks and adapting itself to compensate for uncertainties. With this aim, presented paper focuses on investigation of machine techniques make a sensorless able learn optimize an industrial assembly task. Relying Cartesian impedance control, two main contributions defined: (1) task-trajectory algorithm based few demonstrations (exploiting Hidden Markov...
Human-robot cooperation is increasingly demanded in industrial applications. Many tasks require the robot to enhance capabilities of humans. In this scenario, safety also plays an important role avoiding any accident involving humans, robots and environment. With aim, paper proposes a cooperative fuzzy-impedance control with embedded rules assist human operators heavy applications while manipulating unknown weight parts. The proposed methodology composed by four main components: i) inner...
Background Several models have been developed to predict mortality in patients with COVID-19 pneumonia, but only a few demonstrated enough discriminatory capacity. Machine learning algorithms represent novel approach for the data-driven prediction of clinical outcomes advantages over statistical modeling. Objective We aimed develop machine learning–based score—the Piacenza score—for 30-day pneumonia. Methods The study comprised 852 admitted Guglielmo da Saliceto Hospital Italy from February...
Abstract Industrial robots are increasingly used to perform tasks requiring an interaction with the surrounding environment ( e.g. , assembly tasks). Such environments usually (partially) unknown robot, implemented controllers suitably react established interaction. Standard require force/torque measurements close loop. However, most of industrial manipulators do not have embedded sensor(s) and such integration results in additional costs implementation effort. To extend use compliant...
One of the main objectives fifth industrial revolution is design and implementation human-centric production environments. The human is, indeed, placed in center environment, having a supervision/leading role instead carrying out heavy/repetitive tasks. To enhance such an paradigm change, operators have to be provided with tools they need naturally easily transfer their knowledge robotic systems. Such expertise, fact, difficult coded, especially for non-expert programmers. In addition, due...
A deformation-tracking impedance control strategy is discussed for applications where a manipulator interacts with environments of unknown geometrical and mechanical properties, especially stiffness comparable to controlled robot stiffness. Based on force-tracking controls, the allows desired deformation target environment, requiring on-line estimation environment An Extended Kalman Filter used because measurement uncertainties errors in compound interaction model. The tasks presented...
Just like in humans vision plays a fundamental role guiding adaptive locomotion, when designing the control strategy for walking assistive technology, use of computer may substantially improve modulation assistance based on external environment. In this letter, we developed hip exosuit controller able to distinguish among three different terrains through an RGB camera and adapt accordingly. The system was tested with seven healthy participants throughout overground path comprising staircases...
In the context of current societal challenges, such as climate neutrality, industry digitization, and circular economy, this paper addresses importance improving recycling practices for electric vehicle (EV) battery packs, with a specific focus on lithium–ion batteries (LIBs). To achieve this, conducts systematic review (using Google Scholar, Scopus, Web Science search engines), considering last 10 years, to examine existing methods, robotic/collaborative disassembly cells, associated...
Industry 5.0 aims to prioritize human operators, focusing on their well-being and capabilities, while promoting collaboration between humans robots enhance efficiency productivity. The integration of collaborative must ensure the health operators. Indeed, this paper addresses need for a human-centered framework proposing preference-based optimization algorithm in human–robot (HRC) scenario with an ergonomics assessment improve working conditions. HRC application consists optimizing robot...
Abstract Wearable exoskeletons hold the potential to provide valuable physical assistance across a range of tasks, with applications steadily expanding different scenarios. However, lack universally accepted testbeds and standardized protocols limits systematic benchmarking these devices. In response, STEPbySTEP project, funded within Eurobench framework, proposes modular, sensorized, reconfigurable staircase testbed designed as novel evaluation approach first European infrastructure for...
Manual labor is still strongly present in many industrial contexts (such as aerospace industry). Such operations commonly involve onerous tasks requiring to work non-ergonomic conditions and manipulate heavy parts. As a result, work-related musculoskeletal disorders are major problem tackle workplace. In particular, back one of the most affected regions. To solve such issue, efforts have been made design control exoskeleton devices, relieving human from task load. Besides upper limbs lower...
Robots are nowadays increasingly required to deal with (partially) unknown tasks and situations. The robot has, therefore, adapt its behavior the specific working conditions. Classical control methods in robotics require manually programming all actions of a robot. While very effective fixed conditions, such model-based approaches cannot handle variations, demanding tedious tuning parameters for every new task. Reinforcement learning (RL) holds promise autonomously policies through...
Industrial robots are increasingly used to perform tasks that require an interaction with the surrounding environment (e.g., assembly tasks). Such environments usually (partially) unknown robot (in terms of dynamic characteristics), demanding implemented controllers suitably react established interaction. Standard force/torque measurements close loop, making it, if possible, adapt behavior specific environment. However, most industrial manipulators do not have embedded sensor(s), which...
Human-robot interaction is a rapidly developing field and robots have been taking more active roles in our daily lives. Patient care one of the fields which are becoming present, especially for people with disabilities. People neurodegenerative disorders might not consciously or voluntarily produce movements other than those involving eyes eyelids. In this context, Brain-Computer Interface (BCI) systems present an alternative way to communicate interact external world. order improve lives...