PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 4, 20240 citationsOpen Access

Hand-Object Interaction Controller (HOIC): Deep Reinforcement Learning for Reconstructing Interactions with Physics

View Full Paper
HHHaoyu HuXYXinyu YiZCZhe Cao

Key Points

Key points are not available for this paper at this time.

Abstract

Hand manipulating objects is an important interaction motion in our daily activities. We faithfully reconstruct this motion with a single RGBD camera by a novel deep reinforcement learning method to leverage physics. Firstly, we propose object compensation control which establishes direct object control to make the network training more stable. Meanwhile, by leveraging the compensation force and torque, we seamlessly upgrade the simple point contact model to a more physical-plausible surface contact model, further improving the reconstruction accuracy and physical correctness. Experiments indicate that without involving any heuristic physical rules, this work still successfully involves physics in the reconstruction of hand-object interactions which are complex motions hard to imitate with deep reinforcement learning. Our code and data are available at https://github.com/hu-hy17/HOIC.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Hu et al. (2024) studied this question.

synapsesocial.com/papers/68e6b92bb6db64358763a332https://doi.org/10.48550/arxiv.2405.02676
Ask AI
Helpful
Bookmark
Share
View Full Paper

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Kinematics-based 3D Human-Object Interaction Reconstruction from Single View2024
  2. 2Physically Plausible Full-Body Hand-Object Interaction Synthesis2024 · 23 citations
  3. 3Real-Time Dynamic Robot-Assisted Hand-Object Interaction via Motion Primitives2024
  4. 4HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction2024
  5. 5CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics2024