# SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation

arXiv: https://arxiv.org/abs/1905.07512 · HTML: https://mlsanity.com/paper/1905.07512/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 May 2019.

## Built on by (most cited first, 29 of 29)

- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation](https://mlsanity.com/paper/2203.10421/) (2022)
- [HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes](https://mlsanity.com/paper/2210.09729/) (2022)
- [Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2204.09667/) (2022)
- [Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation](https://mlsanity.com/paper/2202.02440/) (2022)
- [GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving](https://mlsanity.com/paper/2111.08575/) (2021)
- [RobustNav: Towards Benchmarking Robustness in Embodied Navigation](https://mlsanity.com/paper/2106.04531/) (2021)
- [Learning Navigational Visual Representations with Semantic Map Supervision](https://mlsanity.com/paper/2307.12335/) (2023)
- [Towards Versatile Embodied Navigation](https://mlsanity.com/paper/2210.16822/) (2022)
- [Omnidirectional Information Gathering for Knowledge Transfer-based Audio-Visual Navigation](https://mlsanity.com/paper/2308.10306/) (2023)
- [Selective Visual Representations Improve Convergence and Generalization for Embodied AI](https://mlsanity.com/paper/2311.04193/) (2023)
- [XVO: Generalized Visual Odometry via Cross-Modal Self-Training](https://mlsanity.com/paper/2309.16772/) (2023)
- [Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learning](https://mlsanity.com/paper/2009.14509/) (2020)
- [Environment Predictive Coding for Embodied Agents](https://mlsanity.com/paper/2102.02337/) (2021)
- [From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning](https://mlsanity.com/paper/2507.22028/) (2025)
- [Structure-Encoding Auxiliary Tasks for Improved Visual Representation in Vision-and-Language Navigation](https://mlsanity.com/paper/2211.11116/) (2022)
- [Beyond Visual Field of View: Perceiving 3D Environment with Echoes and Vision](https://mlsanity.com/paper/2207.01136/) (2022)
- [Self-Supervised Domain Adaptation for Visual Navigation with Global Map Consistency](https://mlsanity.com/paper/2110.07184/) (2021)
- [A General Purpose Supervisory Signal for Embodied Agents](https://mlsanity.com/paper/2212.01186/) (2022)
- [Language-Based Augmentation to Address Shortcut Learning in Object Goal Navigation](https://mlsanity.com/paper/2402.05090/) (2024)
- [Generalization in Reinforcement Learning for Radio Access Networks](https://mlsanity.com/paper/2507.06602/) (2025)
- [Deep Learning for Embodied Vision Navigation: A Survey](https://mlsanity.com/paper/2108.04097/) (2021)
- [Interactive Semantic Map Representation for Skill-based Visual Object Navigation](https://mlsanity.com/paper/2311.04107/) (2023)
- [An A* Curriculum Approach to Reinforcement Learning for RGBD Indoor Robot Navigation](https://mlsanity.com/paper/2101.01774/) (2021)
- [ASC me to Do Anything: Multi-task Training for Embodied AI](https://mlsanity.com/paper/2202.06987/) (2022)
- [Towards self-attention based visual navigation in the real world](https://mlsanity.com/paper/2209.07043/) (2022)
- [VSGM -- Enhance robot task understanding ability through visual semantic graph](https://mlsanity.com/paper/2105.08959/) (2021)
- [Egocentric Activity Recognition and Localization on a 3D Map](https://mlsanity.com/paper/2105.09544/) (2021)
- [Model Adaptation for Time Constrained Embodied Control](https://mlsanity.com/paper/2406.11128/) (2024)

## Abstract (arXiv)

We propose SplitNet, a method for decoupling visual perception and policy learning. By incorporating auxiliary tasks and selective learning of portions of the model, we explicitly decompose the learning objectives for visual navigation into perceiving the world and acting on that perception. We show dramatic improvements over baseline models on transferring between simulators, an encouraging step towards Sim2Real. Additionally, SplitNet generalizes better to unseen environments from the same simulator and transfers faster and more effectively to novel embodied navigation tasks. Further, given only a small sample from a target domain, SplitNet can match the performance of traditional end-to-end pipelines which receive the entire dataset. Code is available https://github.com/facebookresearch/splitnet