aiqbench analysis
This study addresses a critical bottleneck in Human-Robot Interaction by demonstrating that robust activity recognition using EMG and IMU signals requires subject-specific personalization to overcome significant generalization gaps. The introduction of the MAGIC-HRI dataset provides a rigorous benchmark for evaluating these multimodal models across diverse tasks like object handover and assembly, moving beyond generic classification toward practical deployment.
Why Personalization Matters: Cross-Subject Challenges in EMG-IMU-based HRI Activity Recognition
arXiv:2608.21620v1 Announce Type: new Abstract: 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.
Abstract: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.
Data collection was approved by the Federal University of Technology-Paraná Ethics Committee (CAAE 91430125.0.0000.0177). The MAGIC-HRI (Multimodal Activity, Gesture, and Intention Collection for HRI) dataset is available at [this https URL](this https URL). This paper will be presented at IEEE RO-MAN 2026
Robotics (cs.RO)
arXiv:2608.21620 [cs.RO]
(or arXiv:2608.21620v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2608.21620 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 248 words
Related coverage
Game Design Creativity evals
LessWrong · Oct 12, 2026
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · Oct 13, 2026
LiveLaw Supreme Court Half-Yearly Digest: January - June 2026 [Part 2]
livelaw.in · Sep 13, 2026
BRICS Draws a New Global Line: Full Text of New Delhi Declaration
slguardian.org · Sep 12, 2026