In-Context Imitation Learning via Next-Token Prediction
This addresses the problem of flexible, training-free robot task adaptation for robotics applications, representing a novel method for a known bottleneck.
The paper tackles the problem of enabling robots to perform new tasks through in-context imitation learning without policy updates, by proposing the In-Context Robot Transformer (ICRT) that uses sensorimotor trajectories for autoregressive prediction. Experiments on a Franka Emika robot show that ICRT significantly outperforms state-of-the-art models in generalizing to unseen tasks in multitask environments.
We explore how to enhance next-token prediction models to perform in-context imitation learning on a real robot, where the robot executes new tasks by interpreting contextual information provided during the input phase, without updating its underlying policy parameters. We propose In-Context Robot Transformer (ICRT), a causal transformer that performs autoregressive prediction on sensorimotor trajectories without relying on any linguistic data or reward function. This formulation enables flexible and training-free execution of new tasks at test time, achieved by prompting the model with sensorimotor trajectories of the new task composing of image observations, actions and states tuples, collected through human teleoperation. Experiments with a Franka Emika robot demonstrate that the ICRT can adapt to new tasks specified by prompts, even in environment configurations that differ from both the prompt and the training data. In a multitask environment setup, ICRT significantly outperforms current state-of-the-art next-token prediction models in robotics on generalizing to unseen tasks. Code, checkpoints and data are available on https://icrt.dev/