面向视觉导航的记忆代理地图（Memory Proxy Maps）
Memory Proxy Maps for Visual Navigation
AI总结：
该研究提出一种基于封建学习的三层视觉导航架构，核心是自监督学习的记忆代理地图作为简化记忆，搭配航点网络与动作分类器，实现无强化学习、无图、无里程计、无度量地图的导航，并在图像目标导航任务上达当前最优水平。
摘要：
视觉导航的灵感来源于人类——人类无需详细的环境地图，仅凭视觉就能在从未见过的环境中导航。受此启发，我们提出了一种全新的无强化学习（RL）、无图结构、无里程计的视觉导航方法，采用封建学习构建三层智能体架构。该方法的核心是记忆代理地图（MPM），它是由高层管理者智能体以自监督方式学习得到的环境中间表示，作为简化记忆来近似智能体已观测到的环境内容。我们证明，在这种学习到的潜在空间中记录观测结果是一种高效的记忆代理方案，能够消除视觉导航任务中对图结构和里程计的依赖。对于中层管理者智能体，我们开发了航点网络（WayNet），它可输出中间子目标即航点，模仿人类在局部导航中的航点选择行为。对于底层工作者智能体，我们在离散动作空间上学习了一个分类器，用于躲避局部障碍物并引导智能体向WayNet输出的航点移动。最终得到的封建导航网络提供了一种无RL、无图、无里程计、无度量地图的全新方法，同时在图像目标导航任务上取得了SOTA（当前最优）结果。
英文摘要：
Visual navigation takes inspiration from humans, who navigate in previously unseen environments using vision without detailed environment maps. Inspired by this, we introduce a novel no-RL, no-graph, no-odometry approach to visual navigation using feudal learning to build a three tiered agent. Key to our approach is a memory proxy map (MPM), an intermediate representation of the environment learned in a self-supervised manner by the high-level manager agent that serves as a simplified memory, approximating what the agent has seen. We demonstrate that recording observations in this learned latent space is an effective and efficient memory proxy that can remove the need for graphs and odometry in visual navigation tasks. For the mid-level manager agent, we develop a waypoint network (WayNet) that outputs intermediate subgoals, or waypoints, imitating human waypoint selection during local navigation. For the low-level worker agent, we learn a classifier over a discrete action space that avoids local obstacles and moves the agent towards the WayNet waypoint. The resulting feudal navigation network offers a novel approach with no RL, no graph, no odometry, and no metric map; all while achieving SOTA results on the image goal navigation task.
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。
