# UAS Visual Navigation in Large and Unseen Environments via a Meta Agent

arXiv: https://arxiv.org/abs/2503.15781 · HTML: https://mlsanity.com/paper/2503.15781/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods.
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

## Builds on (most cited first, 21 of 21)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [Meta-Learning with Differentiable Convex Optimization](https://mlsanity.com/paper/1904.03758/) (2019)
- [Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation](https://mlsanity.com/paper/1811.10092/) (2018)
- [A Recurrent Vision-and-Language BERT for Navigation](https://mlsanity.com/paper/2011.13922/) (2020)
- [Learning to Navigate in Complex Environments](https://mlsanity.com/paper/1611.03673/) (2016)
- [Task-Agnostic Meta-Learning for Few-shot Learning](https://mlsanity.com/paper/1805.07722/) (2018)
- [One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning](https://mlsanity.com/paper/1802.01557/) (2018)
- [Meta Learning Shared Hierarchies](https://mlsanity.com/paper/1710.09767/) (2017)
- [Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning](https://mlsanity.com/paper/1812.00971/) (2018)
- [Meta-Learning without Memorization](https://mlsanity.com/paper/1912.03820/) (2019)
- [Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation](https://mlsanity.com/paper/1803.07729/) (2018)
- [Bayesian Relational Memory for Semantic Visual Navigation](https://mlsanity.com/paper/1909.04306/) (2019)
- [Visual Navigation with Spatial Attention](https://mlsanity.com/paper/2104.09807/) (2021)
- [Situational Fusion of Visual Representation for Visual Navigation](https://mlsanity.com/paper/1908.09073/) (2019)
- [Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learning](https://mlsanity.com/paper/2009.14509/) (2020)
- [A Few Shot Adaptation of Visual Navigation Skills to New Observations using Meta-Learning](https://mlsanity.com/paper/2011.03609/) (2020)
- [Graph Attention Memory for Visual Navigation](https://mlsanity.com/paper/1905.13315/) (2019)

## Abstract (arXiv)

The aim of this work is to develop an approach that enables Unmanned Aerial System (UAS) to efficiently learn to navigate in large-scale urban environments and transfer their acquired expertise to novel environments. To achieve this, we propose a meta-curriculum training scheme. First, meta-training allows the agent to learn a master policy to generalize across tasks. The resulting model is then fine-tuned on the downstream tasks. We organize the training curriculum in a hierarchical manner such that the agent is guided from coarse to fine towards the target task. In addition, we introduce Incremental Self-Adaptive Reinforcement learning (ISAR), an algorithm that combines the ideas of incremental learning and meta-reinforcement learning (MRL). In contrast to traditional reinforcement learning (RL), which focuses on acquiring a policy for a specific task, MRL aims to learn a policy with fast transfer ability to novel tasks. However, the MRL training process is time consuming, whereas our proposed ISAR algorithm achieves faster convergence than the conventional MRL algorithm. We evaluate the proposed methodologies in simulated environments and demonstrate that using this training philosophy in conjunction with the ISAR algorithm significantly improves the convergence speed for navigation in large-scale cities and the adaptation proficiency in novel environments.