TY - CHAP
T1 - DexSkills
T2 - 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2024
AU - Mao, Xiaofeng
AU - Giudici, Gabriele
AU - Coppola, Claudio
AU - Althoefer, Kaspar
AU - Farkhatdinov, Ildar
AU - Li, Zhibin
AU - Jamone, Lorenzo
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Effective execution of long-horizon tasks with dexterous robotic hands remains a significant challenge in real-world problems. While learning from human demonstrations has shown encouraging results, they require extensive data collection for training. Hence, decomposing long-horizon tasks into reusable primitive skills is a more efficient approach. To achieve so, we developed DexSkills, a novel supervised learning framework that addresses long-horizon dexterous manipulation tasks using primitive skills. DexSkills is trained to recognize and replicate a select set of skills using human demonstration data, which can then segment a demonstrated long-horizon dexterous manipulation task into a sequence of primitive skills to achieve one-shot execution by the robot directly. Significantly, DexSkills operates solely on proprioceptive and tactile data, i.e., haptic data. Our real-world robotic experiments show that DexSkills can accurately segment skills, thereby enabling autonomous robot execution of a diverse range of tasks.
AB - Effective execution of long-horizon tasks with dexterous robotic hands remains a significant challenge in real-world problems. While learning from human demonstrations has shown encouraging results, they require extensive data collection for training. Hence, decomposing long-horizon tasks into reusable primitive skills is a more efficient approach. To achieve so, we developed DexSkills, a novel supervised learning framework that addresses long-horizon dexterous manipulation tasks using primitive skills. DexSkills is trained to recognize and replicate a select set of skills using human demonstration data, which can then segment a demonstrated long-horizon dexterous manipulation task into a sequence of primitive skills to achieve one-shot execution by the robot directly. Significantly, DexSkills operates solely on proprioceptive and tactile data, i.e., haptic data. Our real-world robotic experiments show that DexSkills can accurately segment skills, thereby enabling autonomous robot execution of a diverse range of tasks.
UR - http://www.scopus.com/inward/record.url?scp=85216492828&partnerID=8YFLogxK
U2 - 10.1109/IROS58592.2024.10802807
DO - 10.1109/IROS58592.2024.10802807
M3 - Conference paper
AN - SCOPUS:85216492828
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 5104
EP - 5111
BT - 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2024
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 14 October 2024 through 18 October 2024
ER -