11 papers
A Distributed Multi-Modal Sensing Approach for Human Activity Recognition in Real-Time Human-Robot Collaboration
Valerio Belcamino, Nhat Minh Dinh Le, Quan Khanh Luu +3
Human activity recognition (HAR) is fundamental in human-robot collaboration (HRC), enabling robots to respond to and dynamically adapt to human intentions. This paper introduces a…
Factored Reasoning with Inner Speech and Persistent Memory for Evidence-Grounded Human-Robot Interaction
Valerio Belcamino, Mariya Kilina, Alessandro Carfì +3
Dialogue-based human-robot interaction requires robot cognitive assistants to maintain persistent user context, recover from underspecified requests, and ground responses in extern…
On the Generalization Gap in LLM Planning: Tests and Verifier-Reward RL
Valerio Belcamino, Nicholas Attolino, Alessio Capitanelli +1
Recent work shows that fine-tuned Large Language Models (LLMs) can achieve high valid plan rates on PDDL planning tasks. However, it remains unclear whether this reflects transfera…
A Social Robot with Inner Speech for Dietary Guidance
Valerio Belcamino, Alessandro Carfì, Valeria Seidita +2
We explore the use of inner speech as a mechanism to enhance transparency and trust in social robots for dietary advice. In humans, inner speech structures thought processes and de…
A Comparative Study of Human Activity Recognition: Motion, Tactile, and multi-modal Approaches
Valerio Belcamino, Nhat Minh Dinh Le, Quan Khanh Luu +3
Human activity recognition (HAR) is essential for effective Human-Robot Collaboration (HRC), enabling robots to interpret and respond to human actions. This study evaluates the abi…
The Effects of Selected Object Features on a Pick-and-Place Task: a Human Multimodal Dataset
Linda Lastrico, Valerio Belcamino, Alessandro Carfì +4
We propose a dataset to study the influence of object-specific characteristics on human pick-and-place movements and compare the quality of the motion kinematics extracted by vario…