Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 15, 2025SmartBotOpen Access

Leveraging Part‐Based NeRF for Robot Self‐Modeling and Control

View Full Paper
Ask AI
Bookmark
Share

Authors

KHKejun HuYZYupeng ZhangYWYongxin Wu

Discussion

Loading...

Member takes

Overview

This framework enables robots to self-model their morphology and kinematics, improving planning and control in dynamic environments.

Key Points

  • The robot self-model can independently generate trajectories to achieve simple tasks effectively.
  • Neural radiance fields enhance the accuracy of part-level reconstruction for better robot modeling.
  • Dynamic environments challenge traditional modeling methods, which rely on extensive human input and can degrade over time.
  • Kinematic self-modeling supports real-time pose prediction across various joint configurations.

Cite This Study

Hu et al. (2025) studied this question.

synapsesocial.com/papers/6925198ec0ce034ddc3534fdhttps://doi.org/10.1002/smb2.70005
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. 1Benchmarking Neural Radiance Fields for Autonomous Robots: An Overview2024 · 2 citations
  2. 2Learning high-fidelity robot self-model with articulated 3D Gaussian splatting2025
  3. 3Reconfigurable Robot Identification from Motion Data2024
  4. 4RA-NeRF: Robust Neural Radiance Field Reconstruction with Accurate Camera Pose Estimation under Complex Trajectories2025
  5. 5SparsePose–NeRF: Robust Reconstruction Under Limited Observations and Uncalibrated Poses2025