让四足机器人像摔跤手一样灵活搬运重物，无需重新训练
Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation
- 用预训练策略+实时规划实现动态全身操控
- 能搬动比自身重的轮胎和超大围栏，无需调参
- 适合需要灵活应对复杂任务的机器人研究者
本文提出一种从仿真到现实的全身体态操控方法，使四足机器人能够动态地操作大型重型物体。核心思路是在测试时通过基于采样的规划器对预训练的全身控制策略进行实时引导，从而解决多种动态移动-操作任务。有趣的是，该方法在未经过任何额外调优或训练的情况下，即可泛化至多样化的物体与任务，并可通过灵活调整成本函数进一步增强性能。我们在真实世界中对 Spot 四足机器人进行了多项挑战性实验，包括抬起重量超过机器人额定负载能力的轮胎，以及拖拽高度和尺寸均大于机器人自身的警戒屏障。此外，我们还在仿真中展示了该方法可推广至人形机器人，如开门和推桌子等任务。项目代码与视频见 https://sumo.rai-inst.com/。
原文摘要 · Abstract (English)
This paper presents a sim-to-real approach that enables legged robots to dynamically manipulate large and heavy objects with whole-body dexterity. Our key insight is that by performing test-time steering of a pre-trained whole-body control policy with a sample-based planner, we can enable these robots to solve a variety of dynamic loco-manipulation tasks. Interestingly, we find our method generalizes to a diverse set of objects and tasks with no additional tuning or training, and can be further enhanced by flexibly adjusting the cost function at test time. We demonstrate the capabilities of our approach through a variety of challenging loco-manipulation tasks on a Spot quadruped robot in the real world, including uprighting a tire heavier than the robot's nominal lifting capacity and dragging a crowd-control barrier larger and taller than the robot itself. Additionally, we show that the same approach can be generalized to humanoid loco-manipulation tasks, such as opening a door and pushing a table, in simulation. Project code and videos are available at https://sumo.rai-inst.com/.
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。