Paper Reading AI Learner

Dependable Voice Command for Multi-UAV Swarms Using Small Language Models

2026-11-13 20:26:03
Afshin Ameri, Luiz Giacomossi, H{\aa}kan Forsberg, Ivan Tomasic, Baran C\"ur\"ukl\"u

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.

Abstract (translated)

URL

https://arxiv.org/abs/2611.18924

PDF

https://arxiv.org/pdf/2611.18924.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot