AgentWorld
An Interactive Simulation Platform for Scene Construction and Mobile Robotic Manipulation
Accepted by CoRL 2025
Tencent Robotics X, Senior Researcher
Robotics, Reinforcement Learning, Simulation
Email: zyz.robotics [at] gmail (dot) com
An Interactive Simulation Platform for Scene Construction and Mobile Robotic Manipulation
Accepted by CoRL 2025
Towards vision-language directed object rearrangement by physical humanoid
We introduce HumanVLA for general object rearrangement directed by practical vision and language. A teacher-student framework is utilized to develop HumanVLA. A state-based teacher policy is trained first using goal-conditioned reinforcement learning and adversarial motion prior. Then, it is distilled into a vision-language-action model via behavior cloning.
The competition was canceled due to the COVID-19.
Team BayesianBot, LIMA Lab, ShanghaiTech University
A simulator based on Gazebo and ROS which allows researchers to do Deep Reinforcement Learning Experiment about ICRA-RoboMaster AI Challenge.
STAR Center, ShanghaiTech University
A project of the 2019 Robotics Course of the School of Information Science and Technology (SIST) of ShanghaiTech University.
Montreal, Canada
Our team(BayesianBot) won the 2nd Prize at IEEE ICRA's Artificial Intelligence Challenge and receive 2000 dollars in awards.