# Difference-Based Relational Learning for Zero-Shot Object-Goal Visual Navigation With Direct Sim-to-Real Transfer

arXiv: https://arxiv.org/abs/2607.15642 · HTML: https://mlsanity.com/paper/2607.15642/

## 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 17 of its 26 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## 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, 17 of 17)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016)
- [Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks](https://mlsanity.com/paper/1903.03878/) (2019)
- [Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning](https://mlsanity.com/paper/1812.00971/) (2018)
- [Learning Object Relation Graph and Tentative Policy for Visual Navigation](https://mlsanity.com/paper/2007.11018/) (2020)
- [VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model](https://mlsanity.com/paper/2401.02695/) (2024)
- [Zero-shot object goal visual navigation](https://mlsanity.com/paper/2206.07423/) (2022)
- [Object Memory Transformer for Object Goal Navigation](https://mlsanity.com/paper/2203.14708/) (2022)
- [BioSLAM: A Bio-inspired Lifelong Memory System for General Place Recognition](https://mlsanity.com/paper/2208.14543/) (2022)
- [Aligning Knowledge Graph with Visual Perception for Object-goal Navigation](https://mlsanity.com/paper/2402.18892/) (2024)
- [TDANet: Target-Directed Attention Network For Object-Goal Visual Navigation With Zero-Shot Ability](https://mlsanity.com/paper/2404.08353/) (2024)
- [osmAG-LLM: Zero-Shot Open-Vocabulary Object Navigation via Semantic Maps and Large Language Models Reasoning](https://mlsanity.com/paper/2507.12753/) (2025)
- [Image-Based Trajectory Tracking through Unknown Environments without Absolute Positioning](https://mlsanity.com/paper/2103.00055/) (2021)

## Abstract (arXiv)

End-to-end deep reinforcement learning (DRL) for zero-shot object-goal visual navigation remains challenged by the sim-to-real gap, particularly variations in object appearance and restricted camera field-of-view (FoV). This letter proposes a Temporal Difference-Relational Network (T-DRN) for robust zero-shot sim-to-real transfer. T-DRN combines a Siamese difference-based feature extractor, which computes relational difference between the target and observed objects to produce domain-independent representations, with a dual-frame temporal buffer that preserves short-term object continuity under narrow FoV. Extensive experiments in AI2-THOR demonstrate that T-DRN improves zero-shot generalization in terms of success rates over strong baselines. Furthermore, T-DRN is systematically validated on a physical wheeled robot, demonstrating robust performance under real sensing and actuation constraints and supporting the feasibility of direct sim-to-real transfer.