Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 14, 2025The International Journal of Robotics ResearchOpen Access

Learning high-fidelity robot self-model with articulated 3D Gaussian splatting

View Full Paper
Ask AI
Bookmark
Share

Authors

HKHu KejunYPYu PengTNTan Ning

Discussion

Loading...

Member takes

Overview

Observational analysis demonstrates high-fidelity robot self-modeling using transformation matrices and data-driven technology, indicating improvements in morphology and kinematics.

Key Points

  • High-fidelity modeling enables better robotic morphology and kinematics.
  • Demonstrated improvements in modeling using transformation matrices and kinematic networks in robot design.
  • The approach includes utilizing 3D Gaussians to accurately represent robot features.
  • The model enhances capabilities like motion planning and inverse kinematics for robots.

Cite This Study

Kejun et al. (2025) studied this question.

synapsesocial.com/papers/692519acc0ce034ddc354159https://doi.org/10.1177/02783649251396980
View Full Paper
Ask AI
Bookmark
Share

Also Consider

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

  1. 1Leveraging Part‐Based NeRF for Robot Self‐Modeling and Control2025
  2. 2Robust Visual Embodiment: How Robots Discover Their Bodies in Real Environments2025
  3. 3ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting2025
  4. 4Reconfigurable Robot Identification from Motion Data2024
  5. 5A high-fidelity digital twin for robotic manipulation based on 3D Gaussian Splatting2026 · 1 citations