Robot parkour learning
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 …
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
Learning contact-rich manipulation skills is essential. Such skills require the robots to
interact with the environment with feasible manipulation trajectories and suitable compliance …
interact with the environment with feasible manipulation trajectories and suitable compliance …
Neural contact fields: Tracking extrinsic contact with tactile sensing
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 …
sensing to address the problem of tracking extrinsic contact between object and …
Enhancing dexterity in robotic manipulation via hierarchical contact exploration
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 …
intricate fine motions, and ever-changing scenarios. We present a hierarchical planning …
Synthesizing dexterous nonprehensile pregrasp for ungraspable objects
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 …
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 …
contact mode transitions and the use of environmental contacts to successfully manipulate …
Learning generalizable pivoting skills
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 …
act on the system, mainly given by contact interaction. The complexity increases when the …
Arraybot: Reinforcement learning for generalizable distributed manipulation through touch
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 …
vertically sliding pillars integrated with tactile sensors. Functionally, ArrayBot is designed to …
Herd: Continuous human-to-robot evolution for learning from human demonstration
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 …
various tasks. However, directly learning from human demonstration is challenging since the …
Learning preconditions of hybrid force-velocity controllers for contact-rich manipulation
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 …
when assisting humans in everyday settings like homes and offices. These constraints make …