SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learning

Building general-purpose robots to perform a diverse range of tasks in a large variety of environments in the physical world at the human level is extremely challenging. According to [1], it requires the robot learning to be sample-efficient, generalizable, compositional, and incremental. In this work, we introduce a systematic learning framework called SAGCI-system towards achieving these above four requirements. Our system first takes the raw point clouds gathered by the camera mounted on the robot's wrist as the inputs and produces initial modeling of the surrounding environment represented as a file of Unified Robot Description Format (URDF). Our system adopts a learning-augmented differentiable simulation that loads the URDF. The robot then utilizes the interactive perception to interact with the environment to online verify and modify the URDF. Leveraging the differentiable simulation, we propose a model-based learning algorithm combining object-centric and robot-centric stages to efficiently produce policies to accomplish manipulation tasks. We apply our system to perform articulated object manipulation tasks, both in the simulation and the real world. Extensive experiments demonstrate the effectiveness of our proposed learning framework. Supplemental materials and videos are available on our project webpage https://sites.google.com/view/egci.

Authors

• Jun Lv
• Qiaojun Yu
• Lin Shao 0002
• Wenhai Liu
• Wenqiang Xu
• Cewu Lu

Keywords

• Wrist
• Point cloud compression
• Learning systems
• Systematics
• Robot vision systems
• Cameras
• Robot learning
• Incremental Learning
• Learning Framework
• Extensive Experiments
• Point Cloud
• Physical World
• Manipulation Tasks
• Model-based Algorithm
• Raw Point Cloud
• Neural Network
• Model Parameters
• Deep Learning
• Optimization Problem
• Artificial Neural Network
• Control Problem
• Environmental Model
• Model-based Approach
• Depth Camera
• Reward Function
• Real-world Experiments
• Linear Quadratic Regulator
• Model-based Reinforcement Learning
• Deep Reinforcement Learning
• Model-free Reinforcement Learning
• Joint Relationship
• Joint Velocity
• Physics Engine
• Robot Manipulator
• Simulated Robot
• Joint Position