# Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments

arXiv: https://arxiv.org/abs/2009.05429 · HTML: https://mlsanity.com/paper/2009.05429/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2020.

## Built on by (most cited first, 21 of 21)

- [Grid-guided Neural Radiance Fields for Large Urban Scenes](https://mlsanity.com/paper/2303.14001/) (2023)
- [POPGym: Benchmarking Partially Observable Reinforcement Learning](https://mlsanity.com/paper/2303.01859/) (2023)
- [Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems](https://mlsanity.com/paper/2111.04613/) (2021)
- [A Survey on Human-aware Robot Navigation](https://mlsanity.com/paper/2106.11650/) (2021)
- [Pay Self-Attention to Audio-Visual Navigation](https://mlsanity.com/paper/2210.01353/) (2022)
- [Focus on Impact: Indoor Exploration with Intrinsic Motivation](https://mlsanity.com/paper/2109.08521/) (2021)
- [A Platform-Agnostic Deep Reinforcement Learning Framework for Effective Sim2Real Transfer towards Autonomous Driving](https://mlsanity.com/paper/2304.08235/) (2023)
- [Autonomous Unmanned Aerial Vehicle Navigation using Reinforcement Learning: A Systematic Review](https://mlsanity.com/paper/2208.12328/) (2022)
- [Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning](https://mlsanity.com/paper/2403.05770/) (2024)
- [Benchmarking Visual Localization for Autonomous Navigation](https://mlsanity.com/paper/2203.13048/) (2022)
- [GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding](https://mlsanity.com/paper/2506.21188/) (2025)
- [Using Deep Reinforcement Learning with Automatic Curriculum Learning for Mapless Navigation in Intralogistics](https://mlsanity.com/paper/2202.11512/) (2022)
- [Aerial-NeRF: Adaptive Spatial Partitioning and Sampling for Large-Scale Aerial Rendering](https://mlsanity.com/paper/2405.06214/) (2024)
- [Social Learning through Interactions with Other Agents: A Survey](https://mlsanity.com/paper/2407.21713/) (2024)
- [Graph Convolutional Memory using Topological Priors](https://mlsanity.com/paper/2106.14117/) (2021)
- [Deep Learning for Embodied Vision Navigation: A Survey](https://mlsanity.com/paper/2108.04097/) (2021)
- [Image-based Navigation in Real-World Environments via Multiple Mid-level Representations: Fusion Models, Benchmark and Efficient Evaluation](https://mlsanity.com/paper/2202.01069/) (2022)
- [SpaAct: Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigation](https://mlsanity.com/paper/2604.27620/) (2026)
- [Aquatic Navigation: A Challenging Benchmark for Deep Reinforcement Learning](https://mlsanity.com/paper/2405.20534/) (2024)
- [120 Minutes and a Laptop: Minimalist Image-goal Navigation via Unsupervised Exploration and Offline RL](https://mlsanity.com/paper/2603.26441/) (2026)
- [From Failures to Learnable Worlds: Policy-Conditioned Environment Generation for Navigation Agents](https://mlsanity.com/paper/2610.19420/) (2026)

## Abstract (arXiv)

We present NavACL, a method of automatic curriculum learning tailored to the navigation task. NavACL is simple to train and efficiently selects relevant tasks using geometric features. In our experiments, deep reinforcement learning agents trained using NavACL significantly outperform state-of-the-art agents trained with uniform sampling -- the current standard. Furthermore, our agents can navigate through unknown cluttered indoor environments to semantically-specified targets using only RGB images. Obstacle-avoiding policies and frozen feature networks support transfer to unseen real-world environments, without any modification or retraining requirements. We evaluate our policies in simulation, and in the real world on a ground robot and a quadrotor drone. Videos of real-world results are available in the supplementary material.