Yubin Wang's Projects
[arXiv 2024] 3D Diffusion Policy
Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN
Source code of agile flight through a narrow window
Problem4 of Assignment1 for ROAS6000C
A virtual simulation platform for autonomous vehicle sensing, mapping, control and behaviour methods using ROS 2 and Gazebo.
A simple gym environment wrapping Carla, a simulator for autonomous driving research. The environment is designed for developing and comparing reinforcement learning algorithms. Trackable costs also enable the application of safe reinforcement learning algorithms.
Tools for dataset generation based on CARLA simulator. (Data Collector)
Source codes for the paper "Building Cooperative Embodied Agents Modularly with Large Language Models"
PyTorch implementation of Distribution Correction(DisCor) based on Soft Actor-Critic.
Algorithm Implementation of Distributed Potential iterative Linear Quadratic Regulator
Code for Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations
GPT4Tools is an intelligent system that can automatically decide, control, and utilize different visual foundation models, allowing the user to interact with images during a conversation.
A bug-fixed gym env for CARLA 0.9.12
Mobile manipulation in Habitat
A modular high-level library to train embodied AI agents across a variety of tasks and environments.
Policy Search for Model Predictive Control with Application to Agile Drone Flight
Mobile manipulation research tools for roboticists
Iterative Linear Quadratic Regulator with auto-differentiatiable dynamics models
Codebase for "Learning the References of Online Model Predictive Control for Urban Self-Driving""
Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation. Project website: http://moma-llm.cs.uni-freiburg.de
Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.