ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learning
By: Zihan Zhou , Animesh Garg , Ajay Mandlekar and more
Long-horizon manipulation has been a long-standing challenge in the robotics community. We propose ReinforceGen, a system that combines task decomposition, data generation, imitation learning, and motion planning to form an initial solution, and improves each component through reinforcement-learning-based fine-tuning. ReinforceGen first segments the task into multiple localized skills, which are connected through motion planning. The skills and motion planning targets are trained with imitation learning on a dataset generated from 10 human demonstrations, and then fine-tuned through online adaptation and reinforcement learning. When benchmarked on the Robosuite dataset, ReinforceGen reaches 80% success rate on all tasks with visuomotor controls in the highest reset range setting. Additional ablation studies show that our fine-tuning approaches contributes to an 89% average performance increase. More results and videos available in https://reinforcegen.github.io/
Similar Papers
DynaMimicGen: A Data Generation Framework for Robot Learning of Dynamic Tasks
Robotics
Teaches robots to learn new tasks from few examples.
From Generated Human Videos to Physically Plausible Robot Trajectories
Robotics
Robots copy human moves from fake videos.
FieldGen: From Teleoperated Pre-Manipulation Trajectories to Field-Guided Data Generation
Robotics
Robots learn to do tasks with less human help.