论文标题
使用元学习的一些视觉导航技巧对新观察的改编
A Few Shot Adaptation of Visual Navigation Skills to New Observations using Meta-Learning
论文作者
论文摘要
目标驱动的视觉导航是一个具有挑战性的问题，需要机器人仅使用视觉输入来找到目标。许多研究人员在各种机器人平台上使用深度加固学习（DEEP RL）表现出了令人鼓舞的结果，但是典型的端到端学习以其对新场景的外推能力不佳而闻名。因此，学习具有新的传感器配置或新目标的新机器人的导航策略仍然是一个具有挑战性的问题。在本文中，我们介绍了一种学习算法，该算法可以快速适应新的传感器配置或带有几张镜头的目标对象。我们设计了一个在感知和推理网络之间具有潜在特征的策略体系结构，并在冻结推理网络的同时，通过元学习快速调整感知网络。我们的实验表明，我们的算法仅用三枪适应了学习的导航策略，即具有不同传感器配置或不同目标颜色的看不见情况。我们还通过研究各种超参数来分析提出的算法。
Target-driven visual navigation is a challenging problem that requires a robot to find the goal using only visual inputs. Many researchers have demonstrated promising results using deep reinforcement learning (deep RL) on various robotic platforms, but typical end-to-end learning is known for its poor extrapolation capability to new scenarios. Therefore, learning a navigation policy for a new robot with a new sensor configuration or a new target still remains a challenging problem. In this paper, we introduce a learning algorithm that enables rapid adaptation to new sensor configurations or target objects with a few shots. We design a policy architecture with latent features between perception and inference networks and quickly adapt the perception network via meta-learning while freezing the inference network. Our experiments show that our algorithm adapts the learned navigation policy with only three shots for unseen situations with different sensor configurations or different target colors. We also analyze the proposed algorithm by investigating various hyperparameters.
