Research Analyzer
← Back ICRA 2026

InvariantCloud: A Globally Invariant, Uniquely Indexed Point Cloud Framework for Robust 6-DoF Tactile Pose Tracking

Pengfei Ye, Yuxiang Ma, Yi Zhou, Wei Chen, Wenzhen Dong, Molong Duan

PDF

AI summary

Key figure (auto-extracted from paper)
InvariantCloud eliminates cumulative drift and improves yaw tracking by using a globally invariant, uniquely indexed point cloud for robust 6-DoF tactile pose estimation.
Tactile Pose Estimation 6-DoF Tracking Globally Invariant Point Cloud Tactile SLAM Vision-Tactile Sensing Drift Suppression

Problem

Current vision-tactile 6-DoF pose estimation methods struggle with cumulative drift, registration ambiguity, and unreliable yaw rotation, hindering precise robotic manipulation without external cameras or CAD models.

Approach

The framework builds a dense, globally invariant reference point cloud with unique IDs on the tactile sensor, enabling direct one-to-one ID matching for closed-form XY rotation and PCA-based silhouette analysis for robust Z-axis yaw estimation.

Key results

  • Eliminates cumulative drift in long-sequence tactile tracking
  • Achieves superior yaw (Z-axis) rotation accuracy and stability
  • Reduces repeatability error across multiple household objects
  • Enables robust inter-contact registration for long-horizon tactile SLAM

Why it matters

Provides a drift-free, high-precision tactile pose estimation framework essential for reliable robotic manipulation and tactile SLAM without external sensors or prior object models.

Abstract

Recent advances in imitation learning and vi- sion–language models highlight the need for high-fidelity tactile perception, with 6-DoF tactile object pose estimation providing a crucial foundation for precise robotic manipulation. We introduce InvariantCloud, a 6-DoF pose estimation frame- work that leverages the global invariance of surface marker constellations on vision-based tactile sensors. In contrast to recent approaches, our one-shot globally invariant point cloud registration suppresses cumulative drift and overcomes long- standing limitations in accurately estimating yaw (Z-axis) ro- tation. Experimental verifications show that InvariantCloud achieves superior yaw tracking accuracy and re-localization repeatability compared to existing benchmarks, demonstrating its precision and robustness in long-sequence manipulation tasks.

Index terms

Force and Tactile Sensing Contact Modeling Perception for Grasping and Manipulation

Related papers