AI Paper Atlas

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

Obstruction Reasoning for Robotic Grasping

Runyu Jiao, Matteo Bortolon, Francesco Giuliari, Alice Fasoli, Sergio Povoli, Guofeng Mei, Yiming Wang, Fabio Poiesi

CVPR 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 obstruction cue: occlusion ratio (ablation)UNOGrasp SFT · UNOBench synthetic (Overall)SR-F1: 74.7 -> 76.4Improved
add obstruction cue: contact point (ablation)UNOGrasp SFT · UNOBench synthetic (Overall)SR-F1: 74.7 -> 75.3Improved
add obstruction cue: degree word (ablation)UNOGrasp SFT · UNOBench synthetic (Overall)SR-F1: 74.7 -> 75.1No clear effect
add RFT with set-level IoU reward (ablation)UNOGrasp · UNOBench synthetic (Overall)SR-F1: 76.4 -> 78.2Improved
add RFT with IoU reward on hard scenes (ablation)UNOGrasp · UNOBench synthetic (Hard)SR-F1: 50.1 -> 54.5Improved
add reasoning chain and RFT vs SFT-only answerUNOGrasp vs Qwen2.5-VL SFT · UNOBench synthetic Oracle (Hard)SR-F1: 34.3 -> 54.5Improved
add reasoning chain and RFT vs SFT-only answerUNOGrasp vs Qwen2.5-VL SFT · UNOBench real Oracle (Hard)SR-F1: 25.9 -> 63.9Improved
in-context examples for Gemini (ablation)Gemini Robotics-ER 1.5 · UNOBench synthetic Oracle (No obstruction)SR: 68.7 -> 54.6Hurt
in-context examples for Gemini (ablation)Gemini Robotics-ER 1.5 · UNOBench synthetic Oracle (Hard)SR-F1: 5.4 -> 13.8Improved
UNOGrasp vs Gemini in real robot trialsUNOGrasp · Real robot UR5e (Hard)success rate: 10% -> 40%Improved
UNOGrasp vs Gemini in real robot trialsUNOGrasp · Real robot UR5e (Easy and Medium)success rate: 80% vs 80%, 30% vs 30%No clear effect
UNOGrasp NL prompting vs Oracle SoM groundingUNOGrasp · UNOBench synthetic (Hard)SR-F1: 54.5 -> 37.2Hurt

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