Newest papers

GPT-6-Astra Understands Touch and Outperform Vision--Tactile--Language--Action Models

Ziyong Wang, Yue Lin, Runxuan Huang, Liang Lin, Dongyu Zhang, Guangrun Wang · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28457 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

Los modelos multimodales corregidos de propósito general han mostrado promesa como políticas de acción directa de robots, sin embargo, si comprenden la física subyacente a las interacciones del mundo real y pueden aplicar ese entendimiento para guiar la acción sigue siendo inexplorado. Investigamos esta cuestión utilizando la manipulación rica en contacto como un centro de pruebas representativo, examinando la comprensión táctil como una instancia concreta de esta capacidad más amplia. La manipulación rica en contacto requiere la interpretación de los comentarios táctiles y las referencias táctiles para la evaluación y la acción correctiva después de la obstrucción. Las políticas táctiles aprendidas existentes adquieren estas capacidades a través de la pre-entrenamiento especializada y la optimización por tareas, con datos sustanciales y costos de entrenamiento. Presentamos los datos y los ajustes a través de

Machine translation (Meta M2M100); the English original follows.

Abstract

General-purpose multimodal models have shown promise as direct robot action policies, yet whether they grasp the physics underlying real-world interactions and can apply that understanding to guide action remains underexplored. We investigate this question using contact-rich manipulation as a representative testbed, examining tactile understanding as a concrete instance of this broader capability. Contact-rich manipulation requires interpreting tactile feedback and adjusting actions after obstruction. Existing learned tactile policies acquire these capabilities through specialized pretraining and per-task optimization, with substantial data and training costs. We present GPT-as-Tactile-Policy, which summarizes expert demonstrations into task guidance and tactile references for contact assessment and corrective action. GPT-6-Astra combines this context with multimodal observations and interaction history to generate control commands and adjust actions through contact feedback. Without additional robotics-specific pretraining or per-task policy fine-tuning, our method achieves 93.8\% mean success across five UniVTAC tasks. Overall performance is comparable to state-of-the-art policies, with higher success on selected tasks. On Insert Hole, tactile feedback improves success from 31\% to 99\%. Execution analysis further demonstrates contact-guided probing and correction, supporting manipulation progress through explicit expert experience and online feedback.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Task (project management), GRASP, Action (physics), Computer science, Human–computer interaction, Context (archaeology)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange