2020/04/28 by Xiangyu Chen, Chen, Xiangyu, Zelin Ye +11 · 1 citation
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition #Reinforcement Learning in Robotics #Robot Manipulation and Learning #Robotics (cs.RO)
paper · pdf · doi:10.48550/arxiv.2004.13358
openalex publication_date 2020/04/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.