Skip to main navigation Skip to search Skip to main content

StableIDM: Robust Inverse Dynamics for Robot Manipulation Under Manipulator Truncation

  • Kerui Li
  • , Zhe Jing*
  • , Xiaofeng Wang
  • , Zheng Zhu
  • , Qingkai Yang
  • , Huaibo Huang
  • *Corresponding author for this work
  • University of Chinese Academy of Sciences
  • Beijing Institute of Technology
  • GigaAI

Research output: Contribution to journal › Article › peer-review

Abstract

Visual inverse dynamics models decode low-level robot actions from camera observations and are increasingly used for robot replay and visual-plan execution. However, in single-view manipulation, the robot arm often moves partly outside the camera field of view, making the inverse problem ill-posed and causing unstable action predictions. We present StableIDM, a causal spatio-temporal inverse dynamics model designed for manipulator truncation. StableIDM combines robotcentric masking to suppress non-robot shortcuts, Directional Feature Aggregation to preserve anisotropic evidence across fixed image-space directions, and Temporal Dynamics Refinement to aggregate evidence available in a short causal history and smooth the decoded action. Within the evaluated fixed-camera, sameembodiment setting, a single-seed matched comparison on the AgiBot truncation benchmark shows that StableIDM improves low-occupancy strict accuracy by 5.00 percentage points over a masked causal temporal baseline. In modest-scale physical studies, the same decoder achieves numerically higher openloop replay and visual-plan grasp success. Additional analyses characterize mask quality and deployment cost.

Original languageEnglish
JournalIEEE Robotics and Automation Letters
DOIs
Publication statusAccepted/In press - 2026
Externally publishedYes

Keywords

  • Deep Learning in Grasping and Manipulation
  • Machine Learning for Robot Control
  • Perception for Grasping and Manipulation

Fingerprint

Dive into the research topics of 'StableIDM: Robust Inverse Dynamics for Robot Manipulation Under Manipulator Truncation'. Together they form a unique fingerprint.

Cite this