AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Tabero: Learning Gentle Manipulation with Closed-Loop Force Feedback from Vision, Touch, and Language

Qiwei Wu, Rui Zhang, Xin Xiang, Tao Li, Weihua Zhang, Junjie Lai, Renjing Xu

ICML 2026 · Vision-language and multimodal › Robot action and navigation · approach: Memory and subgoal-based manipulation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add tactile input (force field, image or force MLP) to the VLA policy (ablation)Tabero-VTLA (Pi0 + LoRA) · Tabero object subset, gentle instructionsuccess rate: 0.00 -> 0.01 (gentle) and 0.00 -> 0.40 (firm) for FieldImproved
add force supervision loss to the field-based tactile model (ablation)Tabero-VTLA · Tabero object subset, gentle instructionsuccess rate: 0.01 -> 0.52Improved
add tactile marker field on top of force supervision (ablation)Tabero-VTLA · Tabero object subset, gentle instructionsuccess rate: 0.45 -> 0.52Improved
use marker field instead of tactile image as tactile representation (with force supervision) (ablation)Tabero-VTLA · Tabero object subset, gentle instructionsuccess rate: 0.48 -> 0.52No clear effect
inject force via decoder (TA-VLA style) instead of marker field with force supervision (ablation)Tabero-VTLA · Tabero object subset, gentle instructionsuccess rate: 0.52 -> 0.31Hurt
remove feedforward term from hybrid grip controller (ablation)hybrid grip force controller · Tabero Object task 1, 25% forcegrip force trackingHurt
remove admittance component from hybrid grip controller (ablation)hybrid grip force controller · Tabero Object task 1, 25% forcegrip force trackingHurt
replace tactile-enabled continuous control with vision-language only on binary gripper data (ablation)Tabero-VTLA · Tabero object subset, gentle instruction (10% force)average grip force (N): 3.7 -> 34.6Hurt
reduce gentle force target from 25% to 10% (ablation)Tabero-VTLA · Tabero object subset, gentle instructionsuccess rate: 0.79 -> 0.52Hurt
use tactile gripper with reduced force settings during data replay (ablation)data collection in Isaac Lab · LIBERO four-task averagesuccess rate: 0.85 -> 0.36Hurt
test unseen adverbs lightly and forcefullyTabero-VTLA · Tabero object subset (Dataset B)average grip force (N): lightly 14.5, forcefully 18.1Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy