A5062246894- Human-Automation Interaction and Safety
- Robot Manipulation and Learning
- Social Robot Interaction and HRI
- Occupational Health and Safety Research
- Ergonomics and Musculoskeletal Disorders
- Ergonomics and Human Factors
- Musculoskeletal pain and rehabilitation
- Scheduling and Optimization Algorithms
- Anomaly Detection Techniques and Applications
- Human Pose and Action Recognition
- Robotics and Automated Systems
- Context-Aware Activity Recognition Systems
- Gastrointestinal Bleeding Diagnosis and Treatment
- AI in Service Interactions
- Fuzzy Logic and Control Systems
- Hand Gesture Recognition Systems
- Speech and dialogue systems
- Manufacturing Process and Optimization
- Virtual Reality Applications and Impacts
- MRI in cancer diagnosis
- AI in cancer detection
- Healthcare Technology and Patient Monitoring
- Modular Robots and Swarm Intelligence
Italian Institute of Technology
2021-2025
Politecnico di Milano
2021-2023
University of Genoa
2020-2023
University of Twente
2021
Human-robot collaborative assembly systems enhance the efficiency and productivity of workplace but may increase workers' cognitive demand. This paper proposes an online quantitative framework to assess workload induced by interaction with a co-worker, either human operator or industrial robot different control strategies. The approach monitors operator's attention distribution upper-body kinematics benefiting from input images low-cost stereo camera cutting-edge artificial intelligence...
Handing objects to humans is an essential capability for collaborative robots. Previous research works on human-robot handovers focus facilitating the performance of human partner and possibly minimising physical effort needed grasp object. However, altruistic robot behaviours may result in protracted awkward motions, contributing unpleasant sensations by affecting perceived safety social acceptance. This paper investigates whether transferring cognitive science principle that "humans act...
In hybrid industrial environments, workers' comfort and positive perception of safety are essential requirements for successful acceptance usage collaborative robots. This paper proposes a novel human-robot interaction framework in which the robot behaviour is adapted online according to operator's cognitive workload stress. The method exploits generation B-spline trajectories joint space formulation multi-objective optimisation problem adjust total execution time smoothness trajectories....
This paper introduces a new Cloud platform providing services for culturally competent interaction, that has been developed to expand the capabilities of Socially Assistive Robots and virtual assistants interacting with older persons. The rationale behind proposed architecture is discussed, by outlining key principles as well functionalities provided, specific focus on verbal interaction. Three case studies, humanoid robot Pepper, robotic medicine dispenser Pillo, custom-built Android-based...
Achieving natural and engaging verbal interactions is one of the main challenges faced by Social Robotics. In this context, physical embodiment may be most critical factors: indeed, previous work indicates that robots elicit more favorable social responses than virtual agents. However, effects have been analysed only in some specific limited scenarios, where interaction was reduced to basic commands.The current aims at investigating effect robots' a pure conversation task, considering...
This paper presents a new method to describe spatio-temporal relations between objects and hands, recognize both interactions activities within video demonstrations of manual tasks. The approach exploits Scene Graphs extract key interaction features from image sequences while simultaneously encoding motion patterns context. Additionally, the introduces event-based automatic segmentation clustering, which allow for grouping similar events detect if monitored activity is executed correctly....
A biopsy is the only diagnostic procedure for accurate histological confirmation of breast cancer. When sonographic placement not feasible, a Magnetic Resonance Imaging(MRI)-guided often preferred. The lack real-time imaging information and deformations make it challenging to bring needle precisely towards tumour detected in pre-interventional (MR) images. current manual MRI-guided workflow inaccurate would benefit from technique that allows tracking localisation lesion during insertion....
Despite impressive advancements of industrial collaborative robots, their potential remains largely untapped due to the difficulty in balancing human safety and comfort with fast production constraints. To help address this challenge, we present PRO-MIND, a novel human-in-the-loop framework that leverages valuable data about co-worker optimise robot trajectories. By estimating attention mental effort, our method dynamically adjusts zones enables on-the-fly alterations path enhance optimal...
Observational learning is a promising approach to enable people without expertise in programming transfer skills robots user-friendly manner, since it mirrors how humans learn new behaviors by observing others. Many existing methods focus on instructing mimic human trajectories, but motion-level strategies often pose challenges generalization across diverse environments. This paper proposes novel framework that allows achieve \textit{higher-level} understanding of human-demonstrated manual...
This paper presents a new method to describe spatio-temporal relations between objects and hands, recognize both interactions activities within video demonstrations of manual tasks. The approach exploits Scene Graphs extract key interaction features from image sequences while simultaneously encoding motion patterns context. Additionally, the introduces event-based automatic segmentation clustering, which allow for grouping similar events detect if monitored activity is executed correctly....
In hybrid industrial environments, workers' comfort and positive perception of safety are essential requirements for successful acceptance usage collaborative robots. This paper proposes a novel human-robot interaction framework in which the robot behaviour is adapted online according to operator's cognitive workload stress. The method exploits generation B-spline trajectories joint space formulation multi-objective optimisation problem adjust total execution time smoothness trajectories....
Close human-robot interaction (HRI), especially in industrial scenarios, has been vastly investigated for the advantages of combining human and robot skills. For an effective HRI, validity currently available human-machine communication media or tools should be questioned, new modalities explored. This article proposes a modular architecture allowing operators to interact with robots through different modalities. In particular, we implemented handle gestural touchscreen input, respectively,...