Precise Pick-and-Place using Score-Based Diffusion Networks

In this paper, we propose a novel coarse-to-fine continuous pose diffusion method to enhance the precision of pick-and-place operations within robotic manipulation tasks. Leveraging the capabilities of diffusion networks, we facilitate the accurate perception of object poses. This accurate perception enhances both pick-and-place success rates and overall manipulation precision. Our methodology utilizes a top-down RGB image projected from an RGB-D camera and adopts a coarse-to-fine architecture. This architecture enables efficient learning of coarse and fine models. A distinguishing feature of our approach is its focus on continuous pose estimation, which enables more precise object manipulation, particularly concerning rotational angles. In addition, we employ pose and color augmentation techniques to enable effective training with limited data. Through extensive experiments in simulated and real-world scenarios, as well as an ablation study, we comprehensively evaluate our proposed methodology. Taken together, the findings validate its effectiveness in achieving high-precision pick-and-place tasks.

Authors

• Shih-Wei Guo
• Tsu-Ching Hsiao
• Yu-Lun Liu 0001
• Chun-Yi Lee

Keywords

• Training
• Accuracy
• Three-dimensional displays
• Image color analysis
• Pose estimation
• Robot vision systems
• Cameras
• Intelligent robots
• Network Diffusion
• Final Model
• Real-world Scenarios
• RGB Images
• Depth Camera
• Augmentation Techniques
• Robot Manipulator
• Precise Manipulation
• Coarse Model
• Deep Learning
• Denoising
• Workspace
• Point Cloud
• Simulation Environment
• Reversible Process
• Diffusion Model
• Transportation Network
• Equivalency
• Robotic Arm
• Translation Error
• Number Of Demonstrations
• Human Pose Estimation
• Self-supervised Learning
• Pose Error
• Rotation Error
• Lie Group
• Deep Reinforcement Learning
• Suction Cup
• Object Position