Robot Learning with Sensorimotor Pre-training
This addresses the challenge of data-efficient robot learning for real-world applications, though it is incremental as it builds on existing pre-training and Transformer methods.
The paper tackles the problem of enabling robots to learn effective models of the physical world by introducing a self-supervised sensorimotor pre-training approach using a Transformer, which consistently outperforms training from scratch and allows transfer across tasks, environments, and robots.
We present a self-supervised sensorimotor pre-training approach for robotics. Our model, called RPT, is a Transformer that operates on sequences of sensorimotor tokens. Given a sequence of camera images, proprioceptive robot states, and actions, we encode the sequence into tokens, mask out a subset, and train a model to predict the missing content from the rest. We hypothesize that if a robot can predict the masked-out content it will have acquired a good model of the physical world that can enable it to act. RPT is designed to operate on latent visual representations which makes prediction tractable, enables scaling to larger models, and allows fast inference on a real robot. To evaluate our approach, we collected a dataset of 20,000 real-world trajectories over 9 months using a combination of motion planning and grasping algorithms. We find that sensorimotor pre-training consistently outperforms training from scratch, has favorable scaling properties, and enables transfer across different tasks, environments, and robots.