Name: Yaoxian(Aaron) Song
Type: User
Company: Zhejiang University Research Fellow | PhD Fudan University & Westlake University
Bio: Research Fellow , research on NLP+X in Robotic Manipulation for Cognitive Decision, Underwater grasping
Location: Hangzhou, Zhejiang, China
Yaoxian(Aaron) Song's Projects
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
Steps to reproduce training results for the paper Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?
Atari-DRQN (keras ver.)
Deep recurrent Q Learning using Tensorflow, openai/gym and openai/retro
Dataset proposed in "Self-supervised Monocular Underwater Depth Recovery, Image Restoration, and a Real-sea Video Dataset", ICCV 2023
Simple, straighforward ROS library for hand-eye calibration
An implementation of Emergence of Grounded Compositional Language in Multi-Agent Populations by Igor Mordatch and Pieter Abbeel
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
Transformer-based image captioning extension for pytorch/fairseq
Fast R-CNN
Fully Convolutional Networks for Semantic Segmentation by Jonathan Long*, Evan Shelhamer*, and Trevor Darrell. CVPR 2015 and PAMI 2016.
Codes of CVPR2022 paper: Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction
Frustum PointNets for 3D Object Detection from RGB-D Data
Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving (ICCV, 2019)
GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation
Generative Grasping CNN from "Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach" (RSS 2018)
GGCNN-ROS Wrapper
Generative Grasping CNN from "Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach" (RSS 2018)
Must-read papers on graph neural networks (GNN)
Detect 6-DOF grasp poses in point clouds
Python modules for GQ-CNN training and deployment, with ROS integration
Pytorch code for our ECCV 2018 paper "Graph R-CNN for Scene Graph Generation" and other papers
Graph Sampling is a python package containing various approaches which samples the original graph according to different sample sizes.
a simple Matlab gui for annotating rotated grasping bounding box
An implementation of our RA-L work 'Real-world Multi-object, Multi-grasp Detection'
Repository where I have gumbel-softmax code samples