以场景图扩展机器人模仿学习的时空上下文
Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs
把动态场景图当作显式结构化记忆，为部分可观测下的长时序操作策略提供历史上下文；做视觉模仿学习或具身策略时，可复用这种以物体为中心的关系图记忆来替代隐式循环状态。
原文依据 we propose using scene graphs as an explicit and structured memory mechanism in imitation learning
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论模仿学习使机器人能够通过观察学习如何执行任务。然而，家庭和办公室等真实环境由于空间尺度较大，往往存在严重的部分观测问题。此外，许多任务涉及执行一系列子任务，要求自主机器人能够在较长的时间跨度上进行推理。为应对这些挑战，我们提出在模仿学习中使用场景图作为显式且结构化的记忆机制。通过维护一个动态场景图来捕捉以物体为中心的关系及其随时间的演化，我们的方法使智能体能够在任务执行过程中保留相关的历史上下文，从而对逐步累积的场景信息进行高效推理。在仿真移动操作和真实桌面操作上的实验表明，我们的方法显著提升了策略性能，尤其是在需要长期推理以及在部分可观测条件下要求稳健泛化的场景中。
英文原文摘要 1006 字符
Imitation learning enables robots to learn how to execute tasks via observation. However, real-world environments like homes and offices are often severely partially observed due to their large spatial scales. In addition, many tasks involve executing a series of subtasks requiring autonomous robots to reason over extended time horizons. To address these challenges, we propose using scene graphs as an explicit and structured memory mechanism in imitation learning. By maintaining a dynamic scene graph that captures object-centric relationships and their evolution over time, our method allows the agent to retain relevant historical context during task execution to efficiently reason over incrementally accrued scene information. Our experiments on simulated mobile manipulation and real-world tabletop manipulation demonstrate that our approach substantially improves policy performance, particularly in settings that demand long-term reasoning and robust generalization under partial observability.