Kaixin Bai
Github
Sim-to-Real Transfer; 6D Pose Estimation; Object Detection; Semantic/Instance Segmentation;
Close the Sim2real Gap via Physically-based Structured Light Synthetic Data Simulation
Under Review
We proposed a novel method to simulate structured light camera and generated realistic dataset for object detection, segmentation, robotic grasping tasks.
Keywords: Structured-light Simulation for Generation of Realistic Data; Data Generation for Perception; Reduce Sim2Real Gap.
Webpage •
PDF •
Demo •
Dataset
Deep Learning-Based Collision-Aware Cable Grasping in Cluttered Environment
Under Review
Keywords: Collision Awareness; Grasping from Clutter Scenes with Complicated Objects; Sim-to-Real Tranfer (Training in Simulation and Validating in Real World).
Webpage •
PDF •
Demo •
Dataset
Learning of 6D Object Poses with Multi-task Point-wise Regression Deep Networks
Kaixin Bai, Lei Zhang, Zhaopeng Chen, Jianwei Zhang
2022 IEEE International Conference on Robotics and Biomimetics (IEEE ROBIO 2022).
Keywords: Deep Learning-based 6D Pose Estimation; 6D Rotation Representation; 6D Pose Estimation-based Robotic Grasping.
WebPage •
Towards Precise Model-free Robotic Grasping with Sim-to-Real Transfer Learning
Lei Zhang, Kaixin Bai, Zhaopeng Chen, Yunlei Shi, Jianwei Zhang
2022 IEEE International Conference on Robotics and Biomimetics (IEEE ROBIO 2022).
★ Best Conference Paper Award Finalist, ROBIO ★
Keywords: Data augmentation for Generation of Dense Grasping Labels; Sim-to-Real Transfer; Model-free Grasping Dataset.
Webpage •
PDF •
Demo