# Vision-Based Goal-Conditioned Policies for Underwater Navigation in the Presence of Obstacles

arXiv: https://arxiv.org/abs/2006.16235 · HTML: https://mlsanity.com/paper/2006.16235/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2020.

## Built on by (most cited first, 11 of 11)

- [Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robots](https://mlsanity.com/paper/2405.01792/) (2024)
- [CUREE: A Curious Underwater Robot for Ecosystem Exploration](https://mlsanity.com/paper/2303.03943/) (2023)
- [SM/VIO: Robust Underwater State Estimation Switching Between Model-based and Visual Inertial Odometry](https://mlsanity.com/paper/2304.01988/) (2023)
- [Deep Learning for Embodied Vision Navigation: A Survey](https://mlsanity.com/paper/2108.04097/) (2021)
- [Anomalies by Synthesis: Anomaly Detection using Generative Diffusion Models for Off-Road Navigation](https://mlsanity.com/paper/2505.22805/) (2025)
- [DUViN: Diffusion-Based Underwater Visual Navigation via Knowledge-Transferred Depth Features](https://mlsanity.com/paper/2509.02983/) (2025)
- [Rectified Schr"odinger Bridge Matching for Few-Step Visual Navigation](https://mlsanity.com/paper/2604.05673/) (2026)
- [Pseudo-Trilateral Adversarial Training for Domain Adaptive Traversability Prediction](https://mlsanity.com/paper/2306.14370/) (2023)
- [Deep Learning for Visual Navigation of Underwater Robots](https://mlsanity.com/paper/2310.19495/) (2023)
- [A comparison of RL-based and PID controllers for 6-DOF swimming robots: hybrid underwater object tracking](https://mlsanity.com/paper/2401.16618/) (2024)
- [CORL-AUV: CFD Oriented Reinforcement Learning for Autonomous Underwater Vehicles](https://mlsanity.com/paper/2607.09557/) (2026)

## Abstract (arXiv)

We present Nav2Goal, a data-efficient and end-to-end learning method for goal-conditioned visual navigation. Our technique is used to train a navigation policy that enables a robot to navigate close to sparse geographic waypoints provided by a user without any prior map, all while avoiding obstacles and choosing paths that cover user-informed regions of interest. Our approach is based on recent advances in conditional imitation learning. General-purpose, safe and informative actions are demonstrated by a human expert. The learned policy is subsequently extended to be goal-conditioned by training with hindsight relabelling, guided by the robot's relative localization system, which requires no additional manual annotation. We deployed our method on an underwater vehicle in the open ocean to collect scientifically relevant data of coral reefs, which allowed our robot to operate safely and autonomously, even at very close proximity to the coral. Our field deployments have demonstrated over a kilometer of autonomous visual navigation, where the robot reaches on the order of 40 waypoints, while collecting scientifically relevant data. This is done while travelling within 0.5 m altitude from sensitive corals and exhibiting significant learned agility to overcome turbulent ocean conditions and to actively avoid collisions.