GRaD-Nav：利用高斯辐射场与可微动力学高效学习视觉无人机导航
GRaD-Nav: Efficiently Learning Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamics
AI总结：
针对无人机视觉导航现有强化学习方法样本效率低、仿真到真实迁移差、泛化能力弱的问题，提出融合3DGS与可微深度强化学习的GRaD-Nav框架，搭配CENet与课程训练，实现高效训练、零样本实机部署与任务内泛化。
摘要：
自主视觉导航是机器人自主能力的核心要素。强化学习（RL）提供了一种颇具前景的策略训练范式，但现有强化学习方法存在样本复杂度高、仿真到真实迁移效果差、对训练中未见过的导航场景运行时适应能力有限的问题。这些问题在无人机场景中尤为棘手，因为无人机具有复杂的非线性不稳定动力学特性，且控制与感知之间存在强动态耦合。\n本文提出一种新型框架，将三维高斯泼溅（3D Gaussian Splatting，3DGS）与可微深度强化学习（Differentiable Deep Reinforcement Learning，DDRL）相结合，用于训练基于视觉的无人机导航策略。通过利用高保真三维场景表示与可微仿真，该方法提升了样本效率与仿真到真实的迁移效果。此外，我们引入了上下文辅助估计网络（Context-aided Estimator Network，CENet），以在运行时适应环境变化。另外，通过在多种不同周边环境的混合场景中开展课程训练，我们实现了任务内泛化，即解决训练中未见过的同任务新实例的能力。\n无人机硬件实验表明，与前沿强化学习方法相比，该方法训练效率更高，可在无需微调的情况下实现真实机器人部署的零样本仿真到真实迁移，还能适应同一任务类别内的新实例（例如在环境中存在不同干扰物的情况下，飞过不同位置的门）。我们的仿真器与训练框架已开源，地址为：https://github.com/Qianzhong-Chen/grad_nav。
英文摘要：
Autonomous visual navigation is an essential element in robot autonomy. Reinforcement learning (RL) offers a promising policy training paradigm. However existing RL methods suffer from high sample complexity, poor sim-to-real transfer, and limited runtime adaptability to navigation scenarios not seen during training. These problems are particularly challenging for drones, with complex nonlinear and unstable dynamics, and strong dynamic coupling between control and perception. In this paper, we propose a novel framework that integrates 3D Gaussian Splatting (3DGS) with differentiable deep reinforcement learning (DDRL) to train vision-based drone navigation policies. By leveraging high-fidelity 3D scene representations and differentiable simulation, our method improves sample efficiency and sim-to-real transfer. Additionally, we incorporate a Context-aided Estimator Network (CENet) to adapt to environmental variations at runtime. Moreover, by curriculum training in a mixture of different surrounding environments, we achieve in-task generalization, the ability to solve new instances of a task not seen during training. Drone hardware experiments demonstrate our method's high training efficiency compared to state-of-the-art RL methods, zero shot sim-to-real transfer for real robot deployment without fine tuning, and ability to adapt to new instances within the same task class (e.g. to fly through a gate at different locations with different distractors in the environment). Our simulator and training framework are open-sourced at: https://github.com/Qianzhong-Chen/grad_nav.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
