SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learning
This work addresses the problem of building general-purpose robots capable of diverse tasks in physical environments, representing an incremental advancement by integrating existing techniques like differentiable simulation and interactive perception into a systematic framework.
The authors tackled the challenge of enabling robots to perform diverse manipulation tasks efficiently by introducing the SAGCI-system, a learning framework that combines interactive perception and differentiable simulation to achieve sample-efficient, generalizable, compositional, and incremental learning, demonstrating effectiveness in articulated object manipulation tasks in both simulation and real-world experiments.
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. 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 https://sites.google.com/view/egci.