# Vision-based Navigation Using Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/1908.03627 · HTML: https://mlsanity.com/paper/1908.03627/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Aug 2019.

## Built on by (most cited first, 13 of 13)

- [Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks](https://mlsanity.com/paper/2503.21696/) (2025)
- [Causal Policy Gradient for Whole-Body Mobile Manipulation](https://mlsanity.com/paper/2305.04866/) (2023)
- [Constrained Reinforcement Learning for Robotics via Scenario-Based Programming](https://mlsanity.com/paper/2206.09603/) (2022)
- [Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence](https://mlsanity.com/paper/2402.02701/) (2024)
- [Unlocking Pixels for Reinforcement Learning via Implicit Attention](https://mlsanity.com/paper/2102.04353/) (2021)
- [Using Deep Reinforcement Learning with Automatic Curriculum Learning for Mapless Navigation in Intralogistics](https://mlsanity.com/paper/2202.11512/) (2022)
- [Robust Navigation with Cross-Modal Fusion and Knowledge Transfer](https://mlsanity.com/paper/2309.13266/) (2023)
- [Vision-driven UAV River Following: Benchmarking with Safe Reinforcement Learning](https://mlsanity.com/paper/2409.08511/) (2024)
- [Transformers for Image-Goal Navigation](https://mlsanity.com/paper/2405.14128/) (2024)
- [Mobile Robots through Task-Based Human Instructions using Incremental Curriculum Learning](https://mlsanity.com/paper/2412.19159/) (2024)
- [Covy: An AI-powered Robot with a Compound Vision System for Detecting Breaches in Social Distancing](https://mlsanity.com/paper/2207.06847/) (2022)
- [Navigation of micro-robot swarms for targeted delivery using reinforcement learning](https://mlsanity.com/paper/2306.17598/) (2023)
- [Causality-Based Reinforcement Learning Method for Multi-Stage Robotic Tasks](https://mlsanity.com/paper/2503.03145/) (2025)

## Abstract (arXiv)

Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning architecture capable of navigating an agent, e.g. a mobile robot, to a target given by an image. To achieve this, we have extended the batched A2C algorithm with auxiliary tasks designed to improve visual navigation performance. We propose three additional auxiliary tasks: predicting the segmentation of the observation image and of the target image and predicting the depth-map. These tasks enable the use of supervised learning to pre-train a large part of the network and to reduce the number of training steps substantially. The training performance has been further improved by increasing the environment complexity gradually over time. An efficient neural network structure is proposed, which is capable of learning for multiple targets in multiple environments. Our method navigates in continuous state spaces and on the AI2-THOR environment simulator outperforms state-of-the-art goal-oriented visual navigation methods from the literature.