The data-driven approach to robot control has been gathering pace rapidly, yet generalization to unseen task domains remains a critical challenge. We argue that the key to generalization is representations that are (i) rich enough to capture all task-relevant information and (ii) invariant to superfluous variability between the training and the test domains. We experimentally study such a representation -- containing both depth and semantic information -- for visual navigation and show that it enables a control policy trained entirely in simulated indoor scenes to generalize to diverse real-world environments, both indoors and outdoors. Further, we show that our representation reduces the A-distance between the training and test domains, improving the generalization error bound as a result. Our proposed approach is scalable: the learned policy improves continuously, as the foundation models that it exploits absorb more diverse data during pre-training.

数据驱动方法在机器人控制领域迅速发展，然而对未知任务领域的泛化仍然是一个关键挑战。我们认为泛化的关键在于具备足够丰富的表示以捕捉所有任务相关信息，并且对于训练与测试领域之间的无关变异具有不变性。我们实验研究了这样一种富含深度和语义信息的表示，用于视觉导航，并证明它使得完全在模拟室内场景中训练的控制策略能够泛化到多样的现实环境，包括室内和室外。此外，我们还展示了我们的表示减小了训练和测试领域之间的A-距离，从而改善了泛化误差的上界。我们提出的方法是可扩展的：随着基础模型在预训练期间吸收更多多样数据，学习策略会持续改进。

不变性是泛化的关键：探究表征在视觉导航的从模拟到实际转移中的作用