TacMan-Turbo: Proactive Tactile Control for Robust and Efficient Articulated Object Manipulation
TacMan-Turbo:主动触觉控制用于稳健高效的机械臂物体操控
机构 * Peking University(北京大学) ; State Key Lab of General AI at Peking University(北京大学通用人工智能国家重点实验室) ; PKU-BingJi Joint Laboratory for Artificial Intelligence(北京大学-百度智云人工智能联合实验室) ; Wuhan Major Scientific and Technological Special Program(武汉重大科技专项) ; Hubei Embodied Intelligence Foundation Model Research and Development Program(湖北省具身智能基础模型研发计划) ; National Comprehensive Experimental Base for Governance of Intelligent Society(智能社会治理国家综合实验基地) ; LeapZenith AI Research(LeapZenith人工智能研究) ; Tsinghua University(清华大学) ; Embodied Intelligence Lab(具身智能实验室) ; PKU-Wuhan Institute for Artificial Intelligence(北京大学-武汉人工智能研究院) ; University of Chinese Academy of Sciences(中国科学院大学)
AI总结 本文提出TacMan-Turbo框架,通过主动触觉控制解决机械臂物体操控中有效性与效率的平衡问题,在200种模拟和真实物体上实现100%成功率,显著提升时间效率、动作效率和轨迹平滑度。
Comments Accepted for publication in the IEEE Transactions on Automation Science and Engineering (T-ASE)