analiza aiqbench
This study benchmarks eighteen neural architectures on sequential tasks to identify compact models suitable for real-time robotic gesture speed estimation. The findings highlight BiGRU, TCN, Conv1D, and GRUReLU as top performers that balance accuracy with low parameter counts under 2,000. By applying these models to skeletal keypoint data, the research enables more responsive human-robot interaction systems capable of interpreting dynamic motion cues.
Neural Networks for Temporal Pattern Recognition and Dynamic Arm Gesture Speed Estimation for Robot Control
arXiv:2610.11631v1 Announce Type: cross Abstract: Deploying intelligent robotic systems that interact with humans through gestures requires neural networks capable of recognizing diverse temporal patterns. We present a systematic benchmark of ten abstract sequential tasks--five permutation-invariant (set) and five order-dependent (sequence) problems--evaluated across eighteen neural network architectures spanning recurrent, convolutional, attention-based, and set-function families. Beyond the core architecture-task grid, we explore numerous preprocessing and target-variable transformations, yielding more than 250 distinct experimental configurations. All variants are trained and tested under strictly identical conditions (fixed random seeds, shared hyperparameters, shared data splits) to ensure fair and reproducible comparison. Ranking across all ten tasks reveals four consistently top-performing architectures--BiGRU, TCN, Conv1D, and GRUReLU--all compact enough for real-time deployment (under 2,000 parameters in the benchmark setting). Based on this ranking, we apply three architecturally diverse top models (BiGRU, TCN, and GRUReLU) to a practical robotics problem: estimating the execution speed of dynamic arm gestures from skeletal keypoint sequences. Three speed interpretations (peak count, period time, and mean spike spacing) are evaluated on a custom dataset of eight traffic-related gesture classes comprising 256,710 frames recorded via OpenPose. The best configuration achieves a mean absolute error of 0.198 on the peak-count interpretation, corresponding to roughly 5% relative error, while the period-time interpretation reaches approximately 4% relative error, and the mean spike spacing interpretation approximately 8% relative error. These results demonstrate that neural networks can reliably estimate gesture speed from skeletal data, opening a path toward speed-aware gesture-controlled robotic systems.
Abstract:Deploying intelligent robotic systems that interact with humans through gestures requires neural networks capable of recognizing diverse temporal patterns. We present a systematic benchmark of ten abstract sequential tasks--five permutation-invariant (set) and five order-dependent (sequence) problems--evaluated across eighteen neural network architectures spanning recurrent, convolutional, attention-based, and set-function families. Beyond the core architecture-task grid, we explore numerous preprocessing and target-variable transformations, yielding more than 250 distinct experimental configurations. All variants are trained and tested under strictly identical conditions (fixed random seeds, shared hyperparameters, shared data splits) to ensure fair and reproducible comparison. Ranking across all ten tasks reveals four consistently top-performing architectures--BiGRU, TCN, Conv1D, and GRUReLU--all compact enough for real-time deployment (under 2,000 parameters in the benchmark setting). Based on this ranking, we apply three architecturally diverse top models (BiGRU, TCN, and GRUReLU) to a practical robotics problem: estimating the execution speed of dynamic arm gestures from skeletal keypoint sequences. Three speed interpretations (peak count, period time, and mean spike spacing) are evaluated on a custom dataset of eight traffic-related gesture classes comprising 256,710 frames recorded via OpenPose. The best configuration achieves a mean absolute error of 0.198 on the peak-count interpretation, corresponding to roughly 5% relative error, while the period-time interpretation reaches approximately 4% relative error, and the mean spike spacing interpretation approximately 8% relative error. These results demonstrate that neural networks can reliably estimate gesture speed from skeletal data, opening a path toward speed-aware gesture-controlled robotic systems.
10 pages, 6 figures, 4 tables. Published in Proceedings of the Intelligent Robotics FAIR 2026 (IntRob '26), June 18-19, 2026, Budapest, Hungary, ACM
Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2610.11631 [cs.RO]
(or arXiv:2610.11631v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.11631 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
Proceedings of the Intelligent Robotics FAIR 2026 (IntRob '26), ACM, 2026, pp. 140-149
https://doi.org/10.1145/3831600.3831618 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 386 cuvinte
Subiecte conexe
Light-based neural network processes signals with no imaging step
Quantum Zeitgeist · 17 sept. 2026
The Future of Physical AI Isn’t Smarter Robots, It’s Smarter Interfaces
IEEE Spectrum · 21 mai 2026
Chen and Colleagues Designs Recursive QLSTM Framework for Quantum Recurrent Learning
Quantum Zeitgeist · 15 iul. 2026
"I am an AI Safety Researcher"
LessWrong · 23 sept. 2026