arXiv subjects

Giovanni Braglia

Publications and source records attributed to Giovanni Braglia.

4 recordsLinked to original sources

arXiv2026

Why Personalization Matters: Cross-Subject Challenges in EMG-IMU-based HRI Activity Recognition

This paper investigates wearable-based recognition of human activities and gestures to support Human-Robot Interaction (HRI) in object-handover and assembly-like scenarios. Electromyography (EMG) and Inertial Measurement Unit (IMU) signals were collected using a Myo armband, culminating in a novel dataset introduced as MAGIC-HRI (Multimodal Activity, Gesture and Intention Collection) with a large taxonomy of 53 movement classes, including Brazilian Sign Language (LIBRAS) numbers (0-9), hand gestures, object/tool handover actions (pick up/give/hold), tool-manipulation tasks, and generic assembly/idle motions, collected from 11 participants with 10 samples per class (530 samples per participant). Signals are segmented by detecting muscle activation via an EMG energy envelope, then processed using sliding windows; time- and frequency-domain features are extracted. Multiple classical classifiers are tuned via cross-validated grid search, with Random Forest as the strongest baseline. A Leave-One-Subject-Out (LOSO) protocol reveals a large generalization gap, indicating substantial subject dependence. A personalized adaptation experiment suggests that injecting a small number of samples from a new user can markedly improve recognition. Overall, the study contributes a broad, HRI-driven multimodal dataset, a rigorous evaluation emphasizing generalization, and practical evidence that personalization is likely required for robust deployment in practical HRI.

cs.RO↗

arXiv2025

Arc-Length-Based Warping for Robot Skill Synthesis from Multiple Demonstrations

In robotics, Learning from Demonstration (LfD) aims to transfer skills to robots by using multiple demonstrations of the same task. These demonstrations are recorded and processed to extract a consistent skill representation. This process typically requires temporal alignment through techniques such as Dynamic Time Warping (DTW). In this paper, we consider a novel algorithm, named Spatial Sampling (SS), specifically designed for robot trajectories, that enables time-independent alignment of the trajectories by providing an arc-length parametrization of the signals. This approach eliminates the need for temporal alignment, enhancing the accuracy and robustness of skill representation, especially when recorded movements are subject to intermittent motions or extremely variable speeds, a common characteristic of operations based on kinesthetic teaching, where the operator may encounter difficulties in guiding the end-effector smoothly. To prove this, we built a custom publicly available dataset of robot recordings to test real-world movements, where the user tracks the same geometric path multiple times, with motion laws that vary greatly and are subject to starting and stopping. The SS demonstrates better performances against state-of-the-art algorithms in terms of (i) trajectory synchronization and (ii) quality of the extracted skill.

cs.RO↗

arXiv2025

Phase-Independent Dynamic Movement Primitives With Applications to Human-Robot Co-manipulation and Time Optimal Planning

Dynamic Movement Primitives (DMP) are an established and efficient method for encoding robotic tasks that require adaptation based on reference motions. Typically, the nominal trajectory is obtained through Programming by Demonstration (PbD), where the robot learns a task via kinesthetic guidance and reproduces it in terms of both geometric path and timing law. Modifying the duration of the execution in standard DMPs is achieved by adjusting a time constant in the model. This paper introduces a novel approach to fully decouple the geometric information of a task from its temporal information using an algorithm called spatial sampling, which allows parameterizing the demonstrated curve by its arc-length. This leads to the definition of the Geometric DMP (GDMP). The proposed spatial sampling algorithm guarantees the regularity of the demonstrated curve and ensures a consistent projection of the human force throughout the task in a human-in-the-loop scenario. GDMP exhibits phase independence, as its phase variable is no longer constrained to the demonstration's timing law, enabling a wide range of applications, including phase optimization problems and human-in-the-loop applications. Firstly, a minimum task duration optimization problem subject to velocity and acceleration constraints is formulated. The decoupling of path and speed in GDMP allows to achieve optimal time duration without violating the constraints. Secondly, GDMP is validated in a human-in-the-loop application, providing a theoretical passivity analysis and an experimental stability evaluation in co-manipulation tasks. Finally, GDMP is compared with other DMP architectures available in the literature, both for the phase optimization problem and experimentally with reference to an insertion task, showcasing the enhanced performance of GDMP with respect to other solutions.

cs.RO↗

arXiv2024

A Minimum-Jerk Approach to Handle Singularities in Virtual Fixtures

Implementing virtual fixtures in guiding tasks constrains the movement of the robot's end effector to specific curves within its workspace. However, incorporating guiding frameworks may encounter discontinuities when optimizing the reference target position to the nearest point relative to the current robot position. This article aims to give a geometric interpretation of such discontinuities, with specific reference to the commonly adopted Gauss-Newton algorithm. The effect of such discontinuities, defined as Euclidean Distance Singularities, is experimentally proved. We then propose a solution that is based on a Linear Quadratic Tracking problem with minimum jerk command, then compare and validate the performances of the proposed framework in two different human-robot interaction scenarios.

cs.RO↗