Learning complex dexterous manipulation with deep reinforcement learning and demonstrations

A Rajeswaran, V Kumar, A Gupta, G Vezzani… - ar** via dynamic representation of gripper-object interaction
Q She, R Hu, J Xu, M Liu, K Xu, H Huang - ar** via learning joint planning of
grasp and motion with deep reinforcement learning. To resolve the sample efficiency issue …

Manipnet: neural manipulation synthesis with a hand-object spatial representation

H Zhang, Y Ye, T Shiratori, T Komura - ACM Transactions on Graphics …, 2021 - dl.acm.org
Natural hand manipulations exhibit complex finger maneuvers adaptive to object shapes
and the tasks at hand. Learning dexterous manipulation from data in a brute force way …

Contactgen: Generative contact modeling for grasp generation

S Liu, Y Zhou, J Yang, S Gupta… - Proceedings of the …, 2023 - openaccess.thecvf.com
This paper presents a novel object-centric contact representation ContactGen for hand-
object interaction. The ContactGen comprises 3 components: a contact map indicates the …

State of the art in hand and finger modeling and animation

N Wheatland, Y Wang, H Song, M Neff… - Computer Graphics …, 2015 - Wiley Online Library
The human hand is a complex biological system able to perform numerous tasks with
impressive accuracy and dexterity. Gestures furthermore play an important role in our daily …

Cpf: Learning a contact potential field to model the hand-object interaction

L Yang, X Zhan, K Li, W Xu, J Li… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Modeling the hand-object (HO) interaction not only requires estimation of the HO pose, but
also pays attention to the contact due to their interaction. Significant progress has been …

Discovery of complex behaviors through contact-invariant optimization

I Mordatch, E Todorov, Z Popović - ACM Transactions on Graphics (ToG), 2012 - dl.acm.org
We present a motion synthesis framework capable of producing a wide variety of important
human behaviors that have rarely been studied, including getting up from the ground …

Learning basketball dribbling skills using trajectory optimization and deep reinforcement learning

L Liu, J Hodgins - ACM Transactions on Graphics (TOG), 2018 - dl.acm.org
Basketball is one of the world's most popular sports because of the agility and speed
demonstrated by the players. This agility and speed makes designing controllers to realize …

Toch: Spatio-temporal object-to-hand correspondence for motion refinement

K Zhou, BL Bhatnagar, JE Lenssen… - European Conference on …, 2022 - Springer
We present TOCH, a method for refining incorrect 3D hand-object interaction sequences
using a correspondence based prior learnt directly from data. Existing hand trackers …

Dynamics based 3D skeletal hand tracking

S Melax, L Keselman, S Orsten - … of the ACM SIGGRAPH Symposium on …, 2013 - dl.acm.org
Natural human computer interaction motivates hand tracking research, preferably without
requiring the user to wear special hardware or markers. Ideally, a hand tracking solution …