# SA-GCS: Semantic-Aware Gaussian Curriculum Scheduling for UAV Vision-Language Navigation

arXiv: https://arxiv.org/abs/2508.00390 · HTML: https://mlsanity.com/paper/2508.00390/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 22 references that are in the map.
- First posted on arXiv 1 Aug 2025.

## Builds on (most cited first, 16 of 16)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)
- [Reverse Curriculum Generation for Reinforcement Learning](https://mlsanity.com/paper/1707.05300/) (2017)
- [Acquisition of Localization Confidence for Accurate Object Detection](https://mlsanity.com/paper/1807.11590/) (2018)
- [AerialVLN: Vision-and-Language Navigation for UAVs](https://mlsanity.com/paper/2308.06735/) (2023)
- [Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology](https://mlsanity.com/paper/2410.07087/) (2024)
- [Efficient Reinforcement Finetuning via Adaptive Curriculum Learning](https://mlsanity.com/paper/2504.05520/) (2025)
- [Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning](https://mlsanity.com/paper/2506.06632/) (2025)
- [CityNav: A Large-Scale Dataset for Real-World Aerial Navigation](https://mlsanity.com/paper/2406.14240/) (2024)
- [SkyVLN: Vision-and-Language Navigation and NMPC Control for UAVs in Urban Environments](https://mlsanity.com/paper/2507.06564/) (2025)
- [Guided Curriculum Learning for Walking Over Complex Terrain](https://mlsanity.com/paper/2010.03848/) (2020)
- [LogisticsVLN: Vision-Language Navigation For Low-Altitude Terminal Delivery Based on Agentic UAVs](https://mlsanity.com/paper/2505.03460/) (2025)
- [Multimodal Large Language Models-Enabled UAV Swarm: Towards Efficient and Intelligent Autonomous Aerial Systems](https://mlsanity.com/paper/2506.12710/) (2025)
- [Q-GroundCAM: Quantifying Grounding in Vision Language Models via GradCAM](https://mlsanity.com/paper/2404.19128/) (2024)

## Built on by (most cited first, 3 of 3)

- [LongFly: Long-Horizon UAV Vision-and-Language Navigation with Spatiotemporal Context Integration](https://mlsanity.com/paper/2512.22010/) (2025)
- [HTNav: A Hybrid Navigation Framework with Tiered Structure for Urban Aerial Vision-and-Language Navigation](https://mlsanity.com/paper/2604.08883/) (2026)
- [A Comprehensive Survey and Systematic Real-World Evaluation of Embodied Vision-and-Language Navigation](https://mlsanity.com/paper/2607.09792/) (2026)

## Abstract (arXiv)

Unmanned Aerial Vehicle (UAV) Vision-Language Navigation (VLN) aims to enable agents to accurately localize targets and plan flight paths in complex environments based on natural language instructions, with broad applications in intelligent inspection, disaster rescue, and urban monitoring. Recent progress in Vision-Language Models (VLMs) has provided strong semantic understanding for this task, while reinforcement learning (RL) has emerged as a promising post-training strategy to further improve generalization. However, existing RL methods often suffer from inefficient use of training data, slow convergence, and insufficient consideration of the difficulty variation among training samples, which limits further performance improvement. To address these challenges, we propose Semantic-Aware Gaussian Curriculum Scheduling (SA-GCS), a novel training framework that systematically integrates Curriculum Learning (CL) into RL. SA-GCS employs a Semantic-Aware Difficulty Estimator (SA-DE) to quantify the complexity of training samples and a Gaussian Curriculum Scheduler (GCS) to dynamically adjust the sampling distribution, enabling a smooth progression from easy to challenging tasks. This design significantly improves training efficiency, accelerates convergence, and enhances overall model performance. Extensive experiments on the CityNav benchmark demonstrate that SA-GCS consistently outperforms strong baselines across all metrics, achieves faster and more stable convergence, and generalizes well across models of different scales, highlighting its robustness and scalability. The implementation of our approach is publicly available.