May 13, 2025 · In this paper, we propose the Navigation Diffusion Policy (NavDP), an end-to-end framework trained solely in simulation and can zero-shot transfer to different embodiments in …

Jul 30, 2025 · Navigation Diffusion Policy (NavDP) is an end-to-end mapless navigation model that can achieves cross-embodiment generalization without any real-world robot data.

In this paper, we introduce a novel navigation diffusion policy (NavDP) that leverages a large-scale simulated navigation dataset and privileged simulation information to train a cross …

May 14, 2025 · In this paper, we propose the Navigation Diffusion Policy (NavDP), an end-to-end framework trained solely in simulation and can zero-shot transfer to different embodiments in …

In this paper, we propose the Navigation Diffusion Policy (NavDP), an end-to-end framework trained solely in simulation and can zero-shot transfer to different embodiments in diverse real …

In this paper, we propose the Navigation Diffusion Policy (NavDP), an end-to-end framework trained solely in simulation and can zero-shot transfer to different embodiments in diverse real …

NavDP uses a diffusion-based policy that learns from both privileged and observed information. The architecture includes specialized encoders for processing different types of input data and …

May 13, 2025 · In this paper, we propose the Navigation Diffusion Policy (NavDP), an end-to-end framework trained solely in simulation and can zero-shot transfer to different embodiments in …

This document provides a technical overview of the NavDP repository, which implements a navigation diffusion policy system for sim-to-real robot navigation with zero-shot transfer …

Jun 23, 2025 · Bibliographic details on NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance.

NavDP, an end-to-end diffusion policy framework trained in simulation, achieves state-of-the-art performance and generalization in diverse real-world environments through efficient data …