AI & ML
TARGO and TARGO-Net: Benchmarking Target-driven Object Grasping under Occlusions
arXiv cs.RO0 views
arXiv:2407.06168v2 Announce Type: replace Abstract: Predicting 6-DoF grasp poses from a single RGB-D frame has recently achieved impressive accuracy, yet performance can degrade significantly when the target object is heavily occluded by clutter. In this paper, we establish TARGO, the first benchmark dataset for TARget-driven Grasping under Occlusions, and introduce TARGO-Net, a grasp prediction model designed for visual occlusion. Our main contributions are fourfold: 1) We identify the visual occlusion challenge in single-view RGB-D 6-DoF grasping and show that current state-of-the-art models still suffer under severe occlusion. 2) We propose the TARGO dataset, which supports training and testing 6-DoF grasp models across different visual occlusion levels and enables robustness evaluation in real-world scenarios. 3) We devise TARGO-Net, a transformer-based grasping model with a target completion module and target-scene cross-attention, which achieves the most robust performance across all visual occlusion levels. 4) We show that target completion, number of occluders, and target minimum dimension also relate to grasp success in addition to visual occlusion.
Source:https://arxiv.org/abs/2407.06168PreviousData-Driven Predictive Control for Autonomous Vehicle Racing under Varying FrictionNextTraining-free Task-oriented Grasp Generation
Related posts

Elon Musk tries to explain what’s going on with Ukraine and Starlink
0The Verge

Gemini 4 Neon ออก API แล้ว ราคาถูกกว่า Opus 5.5 ถึง 25% คุ้มไหม
0dev.to
🎮 RIFTFIRE Is Now "Null Point" — Live on Playgama
0dev.to
GPT-6.2 Astra vs. Sol: Benchmarks and API Pricing
0dev.to
Building Smarter Manufacturing Systems: How AI, IoT, and Physical AI Work Together
0dev.to
Scale the Model, Scale the Harness: Unlocking a 2 Leap in Mathematical Reasoning
0dev.to