论文/arXiv 2610.12073·20 天前

用于跨重力域机器人操作中基于视觉触觉旋转分类的最小光流表示

研究用模拟 GelSight Mini 的网格聚合稠密光流，在四种重力域下分类载荷诱发旋转。

AI 整理

• 数据与采集
• 端侧部署

原文链接：A Minimal Optical-Flow Representation for Vision-Based Tactile Rotation Classification in Robotic Manipulation Across Gravity Domains（arXiv 2610.12073 · 发布日期：2026-10-08）

A Minimal Optical-Flow Representation for Vision-Based Tactile Rotation Classification in Robotic Manipulation Across Gravity Domains

研究用模拟 GelSight Mini 的网格聚合稠密光流，在四种重力域下分类载荷诱发旋转。

核心要点

• 面向太空机器人等资源受限平台，探究紧凑触觉运动表示能否跨重力条件分类物体旋转。
• 方法将模拟 GelSight Mini 的稠密光流在 7x9 网格上聚合为 126 个特征。
• 重力导致特征小但显著偏移，仅用地球数据训练的 XGBoost 在轨道重力下精度下降。
• 跨四个重力域训练的单一模型总体精度达 96.3%，40 个特征仍保持 95.7% 精度。

验证范围与局限：验证限于模拟 GelSight Mini，在地球、火星、月球和轨道重力下的载荷诱发旋转分类。

英文摘要 (Abstract)

Vision-based tactile sensors provide rich contact information, but processing high-resolution images can be costly for resource-constrained platforms such as space robots. This work investigates whether a compact representation of tactile motion can classify object rotation across different gravity conditions. Dense optical flow from a simulated GelSight Mini is aggregated over a 7x9 grid into 126 features and used to classify the direction of load-induced rotation under Earth, Mars, Moon, and orbital gravity. Gravity causes a small but significant shift in these features, accounting for 1.6% of their variance (R2 = 0.016). Despite its small magnitude, this shift affects models trained only on Earth data: XGBoost accuracy decreases from 94.4% on Earth to 75.9% in orbit. In contrast, a single model trained across all four gravity domains achieves 96.3% overall accuracy and 95.1%-97.0% across individual domains, without using gravity as an input. The representation can also be reduced to 40 features while retaining 95.7% accuracy, with XGBoost requiring only 0.14 ms per inference. These findings show that Earth-gravity performance alone is insufficient to establish the transferability of tactile perception for space robotic manipulation, highlighting the need to account for gravity-induced domain shifts during training and validation.

作者：Oscar Martinez-Bernal, Mario Cavero-Vidal, Francesco Grella, Carol Martinez

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.12073：A Minimal Optical-Flow Representation for Vision-Based Tactile Rotation Classification in Robotic Manipulation Across Gravity Domains访问 2026-10-21