# NavFormer: A Transformer Architecture for Robot Target-Driven Navigation in Unknown and Dynamic Environments

arXiv: https://arxiv.org/abs/2402.06838 · HTML: https://mlsanity.com/paper/2402.06838/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Feb 2024.

## Built on by (most cited first, 20 of 20)

- [SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model](https://mlsanity.com/paper/2604.19710/) (2026)
- [Transformers Can Navigate Mazes With Multi-Step Prediction](https://mlsanity.com/paper/2412.05117/) (2024)
- [VANP: Learning Where to See for Navigation with Self-Supervised Vision-Action Pre-Training](https://mlsanity.com/paper/2403.08109/) (2024)
- [Mobile Robot Navigation Using Hand-Drawn Maps: A Vision Language Model Approach](https://mlsanity.com/paper/2502.00114/) (2025)
- [Find Everything: A General Vision Language Model Approach to Multi-Object Search](https://mlsanity.com/paper/2410.00388/) (2024)
- [MLLM-Search: A Zero-Shot Approach to Finding People using Multimodal Large Language Models](https://mlsanity.com/paper/2412.00103/) (2024)
- [4CNet: A Diffusion Approach to Map Prediction for Decentralized Multi-Robot Exploration](https://mlsanity.com/paper/2402.17904/) (2024)
- [Causality-Aware Transformer Networks for Robotic Navigation](https://mlsanity.com/paper/2409.02669/) (2024)
- [Narrate2Nav: Real-Time Visual Navigation with Implicit Language Reasoning in Human-Centric Environments](https://mlsanity.com/paper/2506.14233/) (2025)
- [SplatSearch: Instance Image Goal Navigation for Mobile Robots using 3D Gaussian Splatting and Diffusion Models](https://mlsanity.com/paper/2511.12972/) (2025)
- [AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation](https://mlsanity.com/paper/2604.24086/) (2026)
- [RAVEN: Long-Horizon Reasoning & Navigation with a Visuo-Spatio-Temporal Memory](https://mlsanity.com/paper/2606.25206/) (2026)
- [Deep Active Inference with Diffusion Policy and Multiple Timescale World Model for Real-World Exploration and Navigation](https://mlsanity.com/paper/2510.23258/) (2025)
- [Deep Learning Perspective of Scene Understanding in Autonomous Robots](https://mlsanity.com/paper/2512.14020/) (2025)
- [Train-Small Deploy-Large: Leveraging Diffusion-Based Multi-Robot Planning](https://mlsanity.com/paper/2604.06598/) (2026)
- [VISTA: Scale-Aware Visual Navigation via Action History Conditioning](https://mlsanity.com/paper/2606.17294/) (2026)
- [HyperDCM: Dynamic Cluster Memory Replay in Hyperbolic Space for Continual Robotic Navigation Across Scenes](https://mlsanity.com/paper/2607.16267/) (2026)
- [Navigating the Proximity-Safety Balance: Constraint Decomposition for Human Following in Pedestrian Crowds](https://mlsanity.com/paper/2608.10056/) (2026)
- [Temporal Logic Guided Universal Task Representations for Reinforcement Learning](https://mlsanity.com/paper/2608.15509/) (2026)
- [SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control](https://mlsanity.com/paper/2608.21175/) (2026)

## Abstract (arXiv)

In unknown cluttered and dynamic environments such as disaster scenes, mobile robots need to perform target-driven navigation in order to find people or objects of interest, while being solely guided by images of the targets. In this paper, we introduce NavFormer, a novel end-to-end transformer architecture developed for robot target-driven navigation in unknown and dynamic environments. NavFormer leverages the strengths of both 1) transformers for sequential data processing and 2) self-supervised learning (SSL) for visual representation to reason about spatial layouts and to perform collision-avoidance in dynamic settings. The architecture uniquely combines dual-visual encoders consisting of a static encoder for extracting invariant environment features for spatial reasoning, and a general encoder for dynamic obstacle avoidance. The primary robot navigation task is decomposed into two sub-tasks for training: single robot exploration and multi-robot collision avoidance. We perform cross-task training to enable the transfer of learned skills to the complex primary navigation task without the need for task-specific fine-tuning. Simulated experiments demonstrate that NavFormer can effectively navigate a mobile robot in diverse unknown environments, outperforming existing state-of-the-art methods in terms of success rate and success weighted by (normalized inverse) path length. Furthermore, a comprehensive ablation study is performed to evaluate the impact of the main design choices of the structure and training of NavFormer, further validating their effectiveness in the overall system.