arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.38993cs.RO
收藏

基于元学习语义适配的开放世界物体运动预测

Open-World Object Motion Anticipation via Meta-Learned Semantic Adaptation

Amazon Fulfillment Technologies & Robotics(亚马逊履约技术与机器人部门);Massachusetts Institute of Technology(麻省理工学院);University of Iowa(爱荷华大学);Northeastern University(东北大学)

Mason Peterson, Gage MacLin, Camilla Tabasso, Jonathan P. How, Joshua Migdal, Tye Brady, Taskin Padir

AI总结:

该研究提出元学习图神经网络,利用物体多维度历史信息预测新环境物体运动,在仿真和硬件实验中均优于基线方法,可实现机器人无碰撞导航。

摘要:

预测附近物体的运动对机器人安全高效导航至关重要。若无法正确理解可能运动的物体,机器人要么会规划过于保守、低效的轨迹以保障安全,要么会过于冒险,导致不可接受的碰撞。尽管已知物体的运动跟踪与预测已取得显著进展,但很少有研究关注机器人应如何在线适应新物体,包括预测一个物体如何移动另一个物体(例如,人员操作叉车移动托盘)。为实现这一能力,我们提出一种元学习图神经网络,该网络利用物体的语义、几何及关系历史,从少量在线观测中准确预测新环境中物体何时开始运动。我们证明,仅在仿真中训练的该方法,能准确预测训练时未见过的物体的运动,无需任何微调即可迁移到硬件,且在仿真和硬件实验中均优于视觉语言模型和类频率基线。我们方法的准确预测能在闭环导航仿真中实现无碰撞通行,同时与最快的易碰撞规划器的时间差保持在4秒以内。

英文摘要:

Anticipating the motion of nearby objects is critical for safe and efficient robot navigation. Without a proper understanding of what may move, a robot may plan overly conservative, inefficient trajectories to guarantee safety, or it may be overly risky, resulting in unacceptable collisions. While tracking and predicting the motion of known objects has seen significant progress, little research addresses how a robot should adapt online to novel objects, including anticipating how one object may move another (e.g., a person operating a forklift to move a pallet). To enable this capability, we propose a meta-learned graph neural network that leverages a semantic, geometric, and relational history of objects to accurately predict, from a few online observations, when objects will begin to move in new environments. We demonstrate that our method, which is trained only in simulation, accurately anticipates the motion of objects unseen at training time, transfers to hardware without any fine-tuning, and outperforms a vision-language model and a class-frequency baseline in both simulation and hardware experiments. Our method's accurate prediction enables collision-free traversals in a closed-loop navigation simulation, while remaining within four seconds of the fastest, collision-prone planner.

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。

↑