# Learning Object Relation Graph and Tentative Policy for Visual Navigation

arXiv: https://arxiv.org/abs/2007.11018 · HTML: https://mlsanity.com/paper/2007.11018/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jul 2020.

## Built on by (most cited first, 30 of 64)

- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [Diffusion-based Generation, Optimization, and Planning in 3D Scenes](https://mlsanity.com/paper/2301.06015/) (2023)
- [PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning](https://mlsanity.com/paper/2201.10029/) (2022)
- [How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontiers](https://mlsanity.com/paper/2305.16925/) (2023)
- [Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks](https://mlsanity.com/paper/2108.01176/) (2021)
- [VTNet: Visual Transformer Network for Object Goal Navigation](https://mlsanity.com/paper/2105.09447/) (2021)
- [RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation](https://mlsanity.com/paper/2402.15487/) (2024)
- [Visual Navigation with Spatial Attention](https://mlsanity.com/paper/2104.09807/) (2021)
- [Continuous Scene Representations for Embodied AI](https://mlsanity.com/paper/2203.17251/) (2022)
- [Hierarchical Object-to-Zone Graph for Object Navigation](https://mlsanity.com/paper/2109.02066/) (2021)
- [PEANUT: Predicting and Navigating to Unseen Targets](https://mlsanity.com/paper/2212.02497/) (2022)
- [Object Memory Transformer for Object Goal Navigation](https://mlsanity.com/paper/2203.14708/) (2022)
- [Search for or Navigate to? Dual Adaptive Thinking for Object Navigation](https://mlsanity.com/paper/2208.00553/) (2022)
- [Selective Visual Representations Improve Convergence and Generalization for Embodied AI](https://mlsanity.com/paper/2311.04193/) (2023)
- [ThinkBot: Embodied Instruction Following with Thought Chain Reasoning](https://mlsanity.com/paper/2312.07062/) (2023)
- [Unbiased Directed Object Attention Graph for Object Navigation](https://mlsanity.com/paper/2204.04421/) (2022)
- [Find What You Want: Learning Demand-conditioned Object Attribute Space for Demand-driven Navigation](https://mlsanity.com/paper/2309.08138/) (2023)
- [Pushing it out of the Way: Interactive Visual Navigation](https://mlsanity.com/paper/2104.14040/) (2021)
- [Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation](https://mlsanity.com/paper/2402.17587/) (2024)
- [DOPE: Dual Object Perception-Enhancement Network for Vision-and-Language Navigation](https://mlsanity.com/paper/2505.00743/) (2025)
- [Personalized Instance-based Navigation Toward User-Specific Objects in Realistic Environments](https://mlsanity.com/paper/2410.18195/) (2024)
- [Agent-Centric Relation Graph for Object Visual Navigation](https://mlsanity.com/paper/2111.14422/) (2021)
- [Graph based Environment Representation for Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2301.04352/) (2023)
- [Aligning Knowledge Graph with Visual Perception for Object-goal Navigation](https://mlsanity.com/paper/2402.18892/) (2024)
- [What do navigation agents learn about their environment?](https://mlsanity.com/paper/2206.08500/) (2022)
- [Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation](https://mlsanity.com/paper/2302.01520/) (2023)
- [Leveraging Predicate and Triplet Learning for Scene Graph Generation](https://mlsanity.com/paper/2406.02038/) (2024)
- [Multi-Level Compositional Reasoning for Interactive Instruction Following](https://mlsanity.com/paper/2308.09387/) (2023)
- [TDANet: Target-Directed Attention Network For Object-Goal Visual Navigation With Zero-Shot Ability](https://mlsanity.com/paper/2404.08353/) (2024)
- [ObjectReact: Learning Object-Relative Control for Visual Navigation](https://mlsanity.com/paper/2509.09594/) (2025)

## Abstract (arXiv)

Target-driven visual navigation aims at navigating an agent towards a given target based on the observation of the agent. In this task, it is critical to learn informative visual representation and robust navigation policy. Aiming to improve these two components, this paper proposes three complementary techniques, object relation graph (ORG), trial-driven imitation learning (IL), and a memory-augmented tentative policy network (TPN). ORG improves visual representation learning by integrating object relationships, including category closeness and spatial correlations, e.g., a TV usually co-occurs with a remote spatially. Both Trial-driven IL and TPN underlie robust navigation policy, instructing the agent to escape from deadlock states, such as looping or being stuck. Specifically, trial-driven IL is a type of supervision used in policy network training, while TPN, mimicking the IL supervision in unseen environment, is applied in testing. Experiment in the artificial environment AI2-Thor validates that each of the techniques is effective. When combined, the techniques bring significantly improvement over baseline methods in navigation effectiveness and efficiency in unseen environments. We report 22.8% and 23.5% increase in success rate and Success weighted by Path Length (SPL), respectively. The code is available at https://github.com/xiaobaishu0097/ECCV-VN.git.