Robot parkour learning

Z Zhuang, Z Fu, J Wang, C Atkeson… - arXiv preprint arXiv …, 2023 - arxiv.org
Parkour is a grand challenge for legged locomotion that requires robots to overcome various
obstacles rapidly in complex environments. Existing methods can generate either diverse …

Efficient sim-to-real transfer of contact-rich manipulation skills with online admittance residual learning

X Zhang, C Wang, L Sun, Z Wu… - … on Robot Learning, 2023 - proceedings.mlr.press
Learning contact-rich manipulation skills is essential. Such skills require the robots to
interact with the environment with feasible manipulation trajectories and suitable compliance …

Neural contact fields: Tracking extrinsic contact with tactile sensing

C Higuera, S Dong, B Boots… - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
We present Neural Contact Fields, a method that brings together neural fields and tactile
sensing to address the problem of tracking extrinsic contact between object and …

Enhancing dexterity in robotic manipulation via hierarchical contact exploration

X Cheng, S Patil, Z Temel, O Kroemer… - IEEE Robotics and …, 2023 - ieeexplore.ieee.org
Planning robot dexterity is challenging due to the non-smoothness introduced by contacts,
intricate fine motions, and ever-changing scenarios. We present a hierarchical planning …

Synthesizing dexterous nonprehensile pregrasp for ungraspable objects

S Chen, A Wu, CK Liu - ACM SIGGRAPH 2023 Conference Proceedings, 2023 - dl.acm.org
Daily objects embedded in a contextual environment are often ungraspable initially.
Whether it is a book sandwiched by other books on a fully packed bookshelf or a piece of …

Pre-and post-contact policy decomposition for non-prehensile manipulation with zero-shot sim-to-real transfer

M Kim, J Han, J Kim, B Kim - 2023 IEEE/RSJ International …, 2023 - ieeexplore.ieee.org
We present a system for non-prehensile manipulation that require a significant number of
contact mode transitions and the use of environmental contacts to successfully manipulate …

Learning generalizable pivoting skills

X Zhang, S Jain, B Huang, M Tomizuka… - … on Robotics and …, 2023 - ieeexplore.ieee.org
The skill of pivoting an object with a robotic system is challenging for the external forces that
act on the system, mainly given by contact interaction. The complexity increases when the …

Arraybot: Reinforcement learning for generalizable distributed manipulation through touch

Z Xue, H Zhang, J Cheng, Z He, Y Ju… - … on Robotics and …, 2024 - ieeexplore.ieee.org
We present ArrayBot, a distributed manipulation system consisting of a 16× 16 array of
vertically sliding pillars integrated with tactile sensors. Functionally, ArrayBot is designed to …

Herd: Continuous human-to-robot evolution for learning from human demonstration

X Liu, D Pathak, KM Kitani - arXiv preprint arXiv:2212.04359, 2022 - arxiv.org
The ability to learn from human demonstration endows robots with the ability to automate
various tasks. However, directly learning from human demonstration is challenging since the …

Learning preconditions of hybrid force-velocity controllers for contact-rich manipulation

J Liang, X Cheng, O Kroemer - arXiv preprint arXiv:2206.12728, 2022 - arxiv.org
Robots need to manipulate objects in constrained environments like shelves and cabinets
when assisting humans in everyday settings like homes and offices. These constraints make …