# CE-Nav: Flow-Guided Reinforcement Refinement for Cross-Embodiment Local Navigation

arXiv: https://arxiv.org/abs/2509.23203 · HTML: https://mlsanity.com/paper/2509.23203/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2025.

## Built on by (most cited first, 10 of 10)

- [ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation](https://mlsanity.com/paper/2602.11598/) (2026)
- [AstraNav-World: World Model for Foresight Control and Consistency](https://mlsanity.com/paper/2512.21714/) (2025)
- [SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation](https://mlsanity.com/paper/2511.21135/) (2025)
- [ABot-N1: Toward a General Visual Language Navigation Foundation Model](https://mlsanity.com/paper/2607.10383/) (2026)
- [Explore Like Humans: Autonomous Exploration with Online SG-Memo Construction for Embodied Agents](https://mlsanity.com/paper/2604.19034/) (2026)
- [AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation](https://mlsanity.com/paper/2604.24086/) (2026)
- [LookStep: Efficient Vision-Language Navigation with Linguistic Foresight and Event Driven Memory](https://mlsanity.com/paper/2609.02350/) (2026)
- [ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory](https://mlsanity.com/paper/2607.10350/) (2026)
- [EA-Nav: Learning Safe Visual Navigation Policies with Embodiment Awareness](https://mlsanity.com/paper/2607.19880/) (2026)
- [CrossTracer: Cross-Embodiment Navigation via VLA Model Reasoning and Trace Residuals Adapting](https://mlsanity.com/paper/2608.06688/) (2026)

## Abstract (arXiv)

Generalizing local navigation policies across diverse robot morphologies is a critical challenge. Progress is often hindered by the need for costly and embodiment-specific data, the tight coupling of planning and control, and the "disastrous averaging" problem where deterministic models fail to capture multi-modal decisions (e.g., turning left or right). We introduce CE-Nav, a novel two-stage (IL-then-RL) framework that systematically decouples universal geometric reasoning from embodiment-specific dynamic adaptation. First, we train an embodiment-agnostic General Expert offline using imitation learning. This expert, a conditional normalizing flow model named VelFlow, learns the full distribution of kinematically-sound actions from a large-scale dataset generated by a classical planner, completely avoiding real robot data and resolving the multi-modality issue. Second, for a new robot, we freeze the expert and use it as a guiding prior to train a lightweight, Dynamics-Aware Refiner via online reinforcement learning. This refiner rapidly learns to compensate for the target robot's specific dynamics and controller imperfections with minimal environmental interaction. Extensive experiments on quadrupeds, bipeds, and quadrotors show that CE-Nav achieves state-of-the-art performance while drastically reducing adaptation cost. Successful real-world deployments further validate our approach as an efficient and scalable solution for building generalizable navigation systems. Code is available at https://github.com/amap-cvlab/CE-Nav.