Data-Efficient Learning from Human Interventions for Mobile Robots

Mobile robots are essential in applications such as autonomous delivery and hospitality services. Applying learning-based methods to address mobile robot tasks has gained popularity due to its robustness and generalizability. Traditional methods such as Imitation Learning (IL) and Reinforcement Learning (RL) offer adaptability but require large datasets, carefully crafted reward functions, and face sim-to-real gaps, making them challenging for efficient and safe real-world deployment. We propose an online human-in-the-loop learning method PVP4Real that combines IL and RL to address these issues. PVP4Real enables efficient real-time policy learning from online human intervention and demonstration, without reward or any pretraining, significantly improving data efficiency and training safety. We validate our method by training two different robots—a legged quadruped, and a wheeled delivery robot—in two mobile robot tasks, one of which even uses raw RGBD image as observation. The training finishes within 15 minutes. Our experiments show the promising future of human-in-the-loop learning in addressing the data efficiency issue in real-world robotic tasks. More information is available at https://metadriverse.github.io/pvp4real/.

Authors

• Zhenghao Peng
• Zhizheng Liu
• Bolei Zhou

Keywords

• Training
• Learning systems
• Legged locomotion
• Imitation learning
• Reinforcement learning
• Human in the loop
• Robustness
• Real-time systems
• Safety
• Quadrupedal robots
• Human Intervention
• Mobile Robot
• Data-efficient Learning
• Reward Function
• Policy Learning
• Real-world Tasks
• Mobility Tasks
• Human Subjects
• Human Behavior
• Human Data
• Environment Interactions
• Bounding Box
• Depth Images
• Real-world Experiments
• Markov Decision Process
• Obstacle Avoidance
• Policy Network
• Learning Agent
• Human Preferences
• Safe Navigation
• Temporal Difference Learning
• Sudden Stop
• Sharp Turn
• Robotic Training
• Static Obstacles
• Expert Intervention
• Person Walking
• Simulation Environment
• RGB Images