AI & ML
Dependable Voice Command for Multi-UAV Swarms Using Small Language Models
arXiv cs.RO0 views
arXiv:2611.18924v1 Announce Type: cross Abstract: Supervisory control of multiple autonomous unmanned aerial vehicles (UAVs) imposes high visual and cognitive demands on human operators, particularly when communicating mission objectives and system constraints. Voice command provides a natural interaction modality that can reduce operator workload; however, its reliability is affected by environmental noise, speech variability, and recognition errors. This paper presents a dependable voice command framework for multi-UAV swarm supervision using Small Language Models (SLMs). The proposed architecture integrates an Automatic Speech Recognition (ASR) module with an SLM-based semantic processing layer to transform spoken operator commands into structured task definitions for downstream multi-UAV planning and execution. To evaluate robustness, an end-to-end assessment pipeline is developed using a Probabilistic Context-Free Grammar (PCFG) to generate synthetic supervisory commands, which are converted into audio samples with varying operator accents and environmental signal-to-noise ratios (SNR). The resulting speech signals are processed by the ASR module, and the SLM performs contextual interpretation and phonetic correction of transcriptions when required. The evaluation isolates the resilience of the voice command pipeline under acoustic degradation and speech variation, demonstrating reliable task generation for multi-UAV supervision in challenging operational conditions.
Source:https://arxiv.org/abs/2611.18924PreviousFrame First, Decode Once: Object-Centric Coordinates and Single-Pass Decoding for System-1 World ModelsNextReliable Conditioned Hamilton-Jacobi Reachability via Subsolution Learning on Exact Local Windows
Related posts
Microsoft Built Its Own Coding Model, and the Price Is the Point
0dev.to

El diario económico coreano Maeil Business cuenta 12 primeros puestos de Darwin en Hugging Face: cuéntalos tú con Python
0dev.to
Can Peer Review Survive AI-Generated Text? [pdf]
0Hacker News
Toward Planning Representations That Separate Task Structure from Visual Content
0arXiv cs.RO
Spectral Steering: Local Inverse Geometry for Frozen Diffusion Generators
0arXiv cs.RO
Representing Differential Inclusions as Monads: A Framework for Compositional Controller Synthesis
0arXiv cs.RO