用仿真数据训练的导航模型能超越真实数据训练，关键在视觉表征预训练和实时推理架构。
Synthetic vs. Real Training Data for Visual Navigation
- 采用预训练视觉编码器增强仿真与真实图像的匹配度，实现跨域泛化。
- 仿真训练模型在导航成功率上比真实数据训练模型高31点，超当前最优50点。
- 适合关注仿真训练效率与真实部署性能的研究者或机器人开发者。
本文研究了在仿真中训练的视觉导航策略与真实世界数据训练策略的性能对比。尽管仿真训练策略在真实环境中常出现显著性能下降，但本文证明，通过合理设计，仿真训练的策略可达到甚至超过真实数据训练的水平。核心方法是一种利用预训练视觉表示来弥合仿真与真实视觉差异的导航策略架构，可在机器人硬件上实时运行。在轮式移动机器人上的评估表明，该策略在仿真中训练时，导航成功率达31分更高于真实数据训练版本，并比现有最先进方法高出50分。通过在同一模型部署于无人机上验证了其泛化能力。结果强调了多样化图像编码器预训练对仿真到真实泛化的重要性，并指出基于策略的学习是仿真训练相对于真实数据训练的关键优势。代码、模型检查点及多媒体资料见https://lasuomela.github.io/faint/
原文摘要 · Abstract (English)
This paper investigates how the performance of visual navigation policies trained in simulation compares to policies trained with real-world data. Performance degradation of simulator-trained policies is often significant when they are evaluated in the real world. However, despite this well-known sim-to-real gap, we demonstrate that simulator-trained policies can match the performance of their real-world-trained counterparts. Central to our approach is a navigation policy architecture that bridges the sim-to-real appearance gap by leveraging pretrained visual representations and runs real-time on robot hardware. Evaluations on a wheeled mobile robot show that the proposed policy, when trained in simulation, outperforms its real-world-trained version by 31 and the prior state-of-the-art methods by 50 points in navigation success rate. Policy generalization is verified by deploying the same model onboard a drone. Our results highlight the importance of diverse image encoder pretraining for sim-to-real generalization, and identify on-policy learning as a key advantage of simulated training over training with real data. Code, model checkpoints and multimedia materials are available at https://lasuomela.github.io/faint/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。