Language Conditioning Improves Accuracy of Aircraft Goal Prediction in Untowered Airspace

2025-09-17

AI Summary

In uncontrolled airspace lacking tower-based air traffic services, autonomous aircraft lack collaborative decision-support systems and rely solely on pilot voice communications, resulting in insufficient accuracy for inferring peer aircraft intentions and predicting target positions. This paper proposes a novel multimodal prediction framework that introduces language-conditioned intention understanding—first of its kind—for aircraft trajectory forecasting. It employs automatic speech recognition (ASR) and large language models to parse radio transmissions and extract semantic intention labels; models kinematic trajectories via temporal convolutional networks; and achieves cross-modal fusion of linguistic and trajectory information using Gaussian mixture models to generate probabilistic target position predictions. Evaluated on a real-world uncontrolled-airport dataset, the method significantly enhances situational awareness and substantially reduces prediction error. Results demonstrate the efficacy and innovation of leveraging spoken-language semantics to improve socially aware, autonomous decision-making in shared airspace.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Autonomous aircraft must safely operate in untowered airspace, where coordination relies on voice-based communication among human pilots. Safe operation requires an aircraft to predict the intent, and corresponding goal location, of other aircraft. This paper introduces a multimodal framework for aircraft goal prediction that integrates natural language understanding with spatial reasoning to improve autonomous decision-making in such environments. We leverage automatic speech recognition and large language models to transcribe and interpret pilot radio calls, identify aircraft, and extract discrete intent labels. These intent labels are fused with observed trajectories to condition a temporal convolutional network and Gaussian mixture model for probabilistic goal prediction. Our method significantly reduces goal prediction error compared to baselines that rely solely on motion history, demonstrating that language-conditioned prediction increases prediction accuracy. Experiments on a real-world dataset from an untowered airport validate the approach and highlight its potential to enable socially aware, language-conditioned robotic motion planning.

Problem

• Predict aircraft intent in untowered airspace
• Integrate language understanding with spatial reasoning
• Improve autonomous decision-making through multimodal fusion

Innovation

• Integrates natural language understanding with spatial reasoning
• Uses automatic speech recognition and large language models
• Fuses intent labels with trajectories for probabilistic prediction