# Transferable Active Grasping and Real Embodied Dataset

arXiv: https://arxiv.org/abs/2004.13358 · HTML: https://mlsanity.com/paper/2004.13358/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2020.

## Built on by (most cited first, 4 of 4)

- [A Tri-Layer Plugin to Improve Occluded Detection](https://mlsanity.com/paper/2210.10046/) (2022)
- [BFA: Best-Feature-Aware Fusion for Multi-View Fine-grained Manipulation](https://mlsanity.com/paper/2502.11161/) (2025)
- [Active Open-Vocabulary Recognition: Let Intelligent Moving Mitigate CLIP Limitations](https://mlsanity.com/paper/2311.17938/) (2023)
- [Observe Then Act: Asynchronous Active Vision-Action Model for Robotic Manipulation](https://mlsanity.com/paper/2409.14891/) (2024)

## Abstract (arXiv)

Grasping in cluttered scenes is challenging for robot vision systems, as detection accuracy can be hindered by partial occlusion of objects. We adopt a reinforcement learning (RL) framework and 3D vision architectures to search for feasible viewpoints for grasping by the use of hand-mounted RGB-D cameras. To overcome the disadvantages of photo-realistic environment simulation, we propose a large-scale dataset called Real Embodied Dataset (RED), which includes full-viewpoint real samples on the upper hemisphere with amodal annotation and enables a simulator that has real visual feedback. Based on this dataset, a practical 3-stage transferable active grasping pipeline is developed, that is adaptive to unseen clutter scenes. In our pipeline, we propose a novel mask-guided reward to overcome the sparse reward issue in grasping and ensure category-irrelevant behavior. The grasping pipeline and its possible variants are evaluated with extensive experiments both in simulation and on a real-world UR-5 robotic arm.