用视觉实现复杂房间内的精准导航，无需真实定位信息。
Macro-Action Topological Navigation under Noisy Localization using Reinforcement Learning
- 通过视觉特征与运动模型融合，实时估算自身位置。
- 在真实感模拟环境中成功导航至目标物体，成功率超90%。
- 适合研究机器人自主导航、视觉定位的学者参考。
在纯视觉输入下，从原始像素中导航大型逼真3D公寓对传统强化学习而言极为困难。本文构建了一个仅依赖摄像头估计自身位姿的智能体，需按顺序抵达多个位置动态变化的目标物体。该智能体基于此前的对象中心拓扑控制器，但将真实位姿替换为自建的、以对象为中心的位姿估计。每个物体维护一组ORB特征，当再次观测到时可生成粗略位姿，再由最小扩展卡尔曼滤波器（EKF）与运动模型融合。由于执行动作存在噪声，位姿会漂移，但智能体与周围物体同步漂移，只需保持局部一致性即可沿短路径追踪并视觉锁定目标，从而用小型化模型替代完整SLAM，更贴近生物导航机制。在逼真感的Habitat模拟器中，该智能体仅凭视觉成功抵达目标，其位姿只需局部一致即可。
原文摘要 · Abstract (English)
Navigating large, photorealistic 3D apartments from raw pixels is widely considered infeasible for plain reinforcement learning. We build an agent that does it anyway, estimating its own pose from the camera alone. The agent has to reach several target objects in sequence, and their positions change between episodes, so it must explore to find them. It builds on our earlier object-centric topological controller, which still read the agent's true pose and its object detections from the simulator. Here we replace that true pose with an onboard, object-centric estimate. For each object we keep a bank of ORB features that, when the object is seen again, yield a rough pose measurement, which a minimal Extended Kalman Filter (EKF) fuses with a motion model. As on a real robot, the executed motions are noisy. The estimate drifts, but the agent and the nearby objects drift together, so a locally consistent pose is enough to follow each short edge and then home in visually on the target, which lets us replace full SLAM with a much smaller model, closer to how biological navigation appears to work. In the photorealistic Habitat simulator, the agent reaches its target objects from vision alone, with a pose that only needs to be locally consistent.
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。