GrOMP: Grasped Object Manifold Projection for Multimodal Imitation Learning of Manipulation
GrOMP:抓取物体流形投影用于多模态模仿学习的操控
机构 * Mechanical Engineering Department at the University of Michigan(密歇根大学机械工程系) ; Robotics & Automation Research Department at the Ford Motor Company(福特汽车公司机器人与自动化研究部) ; Robotics Department at the University of Michigan(密歇根大学机器人系)
AI总结 GrOMP通过抓取物体流形投影技术,提升多模态模仿学习中操控任务的精度和鲁棒性,基于累积误差界理论,利用触觉反馈在多个装配任务中验证其有效性。
Comments 8 pages, 8 figures, 2 tables