TableManeuver is proposed, an explainable LLM-based FMR method that reformulates multivariate flight parameter time series as table-understanding inputs and combines recognition accuracy, cross-aircraft robustness, and readable step-by-step reasoning evidence, offering a practical route for applying LLMs to aviation time series analysis.
Abstract
Complex flight maneuver recognition (FMR) underpins intelligent flight training, including training assessment, pilot skill profiling, and flight safety monitoring. Existing FMR methods typically require large labeled datasets, generalize poorly across aircraft, and provide limited decision transparency. We propose TableManeuver, an explainable LLM-based FMR method that reformulates multivariate flight parameter time series as table-understanding inputs. The method updates no base LLM parameters and uses a small labeled training set only as a retrieval library; it is therefore not a zero-shot setting. TableManeuver first converts flight parameter sequences into tabular text that preserves temporal indices and channel semantics, reducing the mismatch between numerical time series and the textual semantic space of LLMs. It then combines domain knowledge, neighborhood sample references, and task decomposition prompts in a retrieval-augmented reasoning architecture that guides explicit step-by-step inference. We evaluate the method on a flight dataset collected from human pilots on a high-fidelity flight simulation platform. Without base LLM parameter updates, TableManeuver achieves 96.2% precision, 96.8% recall, and a 96.5% F1 score, exceeding the strongest supervised baseline by 3.5 percentage points in F1. In cross-aircraft evaluation, the F1 score decreases by only 1.4 percentage points, which is substantially smaller than the degradation observed for deep learning baselines. Retrieval-only baselines that transfer neighbor labels without LLM inference perform markedly worse, indicating that the performance gains are not explained by neighbor label transfer alone. TableManeuver combines recognition accuracy, cross-aircraft robustness, and readable step-by-step reasoning evidence, offering a practical route for applying LLMs to aviation time series analysis.
FlightLLM, a prior-guided semantic LLM-based approach for interpretable flight safety analysis that achieves competitive classification performance while generating direct and reasonable explanations for event causes is proposed.
Visual navigation policies built on large pretrained models have so far followed a common recipe: a dedicated visual encoder, a bespoke action head, and training on thousands of hours of cross-embodiment datasets. We ask whether this recipe is necessary. In this paper, we introduce GemNav, a visual robot navigation policy that adapts a frozen Multimodal Large Language Model (MLLM) for short-to-medium horizon waypoint navigation using Low-Rank Adaptation (LoRA) on the language tower alone, with no auxiliary visual encoder and no continuous regression head. Waypoints and categorical navigation signals share a single discrete token vocabulary generated by the language-model head, and a soft-decoded auxiliary loss recovers the metric structure that pure cross-entropy training discards. On a single 8.7-hour open corpus, roughly three orders of magnitude smaller than competing training sets, the policy transfers zero-shot to four physically distinct unseen environments and stops within 0.25-0.42m of the goal across 20 real-world trials covering an open carpark, an obstacle carpark, a long outdoor chemical yard, and an indoor warehouse. Conditioning on short image histories improves offline metrics but yields no robot benefit, pointing to a ceiling on what temporal context adds once pretrained vision features are in place. These results indicate that discrete-token adaptation of frozen MLLMs can provide a data-efficient, deployable alternative for foundation model robot navigation.
Peter Bohm, Saimunur Rahman, Abdelwahed Khamis et al.· 0 citations
Air traffic control (ATC) communication is a safety-critical dialogue that remains largely human-driven even as other parts of air traffic management have been semi-automated. In this article, we experimentally evaluate whether large language models (LLMs) can generate operationally realistic ATC transmissions. An experimental general-aviation flight flying over the San Francisco"Bay Tour"route is hand-transcribed and used as ground truth (P0). Through a pilot-in-the-loop process we design five prompt structures (P1-P5) of increasing constraint and embed them in a stateful multi-turn pipeline, where the model plays ATC to a fixed pilot transcript while conditioning on the accumulating dialogue history. Across nine open- and closed-source LLMs we vary the prompt, the presence of a worked transcript from a different experimental flight as an in-context example, and whether the model conditions on its own prior replies or on injected ground-truth history. Turns are scored with lexical, structural, and semantic similarity metrics and by an LLM-as-judge (GPT-5.5) validated against human expert annotation. Supplying a worked example improves similarity, but tightening the prompt does not: the lightest prompts perform best and the most heavily scripted one collapses as its own errors accumulate through the dialogue, which injecting correct history repairs. These results outline a concrete path and its current limits toward LLM-assisted ATC.
Mahyar Ghazanfari, Matthias Casanova, Jordan Kam et al.· 0 citations
Test-time scaling offers a promising method to improve the inference performance of Vision-Language Models (VLMs) without additional training. Existing approaches to vision-language navigation (VLN) for Unmanned Aerial Vehicle (UAV) typically relies on a single inference pass, which can falter in complex environments by producing suboptimal or unsafe trajectories. In this paper, we explore a simple and effective approach to apply test-time scaling to VLN for UAV. We enhance navigation reasoning through an iterative refinement process that requires no extra model training, guiding the model to re-evaluate its initial navigation plan for better accuracy and safety. Our method first prompts the model to generate multiple parallel candidates and then performs a self-correction step, achieving deeper and more robust planning without changing the underlying model. To further strengthen decision-making, we design a multi-criteria scoring function to evaluate the refined candidates based on safety, goal alignment, and forward-progress. This simple yet powerful combination enables a frozen UAV navigation VLMs to self-correct and generate more accurate and reliable flight plans, achieving SOTA performance in this task.
Feinan Cheng, Dongliang Xu, Wenli Nong et al.· 0 citations
Multimodal Large Language Models (MLLMs) have shown strong semantic understanding capabilities, but their direct use in low-altitude Unmanned Aerial Vehicle (UAV) mission generation remains limited by weak spatial optimization and inefficient route planning. To address this issue, we propose ARIES-Mission2, a zero-shot Vision-Language-Action (VLA) framework that decouples visual-semantic perception from physical route optimization. Given natural-language instructions and satellite imagery, ARIES-Mission2 first uses DeepSeek-V3 for task parsing and Molmo-7B for zero-shot target grounding, and then converts detected pixel locations into GPS waypoints through geospatial interpolation. To reduce the redundant backtracking caused by raw VLM-generated visiting orders, the back end formulates multi-target UAV traversal as a Traveling Salesperson Problem (TSP) and compares four candidate routes, including the raw VLM order and the routes optimized by PSO, GPSO, and IPSO. The minimum-cost closed-loop route is then selected for mission generation. Experiments on the UAV-VLPA-nano-30 benchmark show that ARIES-Mission2 achieves a total flight distance of 62.43 km, reducing the route length by 21.6% compared with the unoptimized VLA baseline (79.66 km) and by 9.5% compared with manual human planning (69.00 km). The complete 30-task workflow takes 575.40 s, averaging 19.18 s per task, which is approximately 3.6 times faster than human expert planning. Component-level timing shows that VLM inference dominates the runtime with 19.02 s per task, while the TSP solver requires only 0.16 s per task. Scalability analysis further indicates that the TSP module maintains lower growth in computation time as the number of targets increases.
Junhao Wei, Yanxiao Li, Haochen Li et al.· 0 citations
Time series forecasting with pretrained foundation models has demonstrated strong zero-shot capabilities. However, achieving optimal performance on time series with short or negligible historical data in domain-specific applications typically requires adaptation via either fine-tuning or RAG. While fine-tuning is effective, it incurs substantial computational costs. This work explores RAG within univariate time series (Retrieval Augmented Generation) as a more efficient alternative, in particular RAF (Retrieval Augmented Forecasting), and introduces RAEF (Retrieval-Augmented Extended Forecasting), a model-agnostic method built upon RAF. RAEF incorporates key refinements to the retrieval and aggregation mechanisms: (1) direct retrieval in input-space rather than embedding-space, reducing inference overhead, and (2) concatenation-based aggregation that preserves temporal structure instead of averaging. Empirical evaluation across multiple benchmark datasets demonstrates that RAEF outperforms RAF in both accuracy and inference overhead. Furthermore, comprehensive comparisons with zero-shot and fine-tuned foundation models show that RAEF achieves competitive or superior performance to fine-tuning while avoiding its computational burden, establishing it as a practical and scalable approach for domain adaptation in time series forecasting.
Juan Pablo Villa Serna, Rohan Asthana, Vasileios Belagiannis· 0 citations