Few-Shot In-Context Imitation Learning via Implicit Graph Alignment
This addresses the challenge of robot adaptation to diverse objects in everyday tasks, representing an incremental advance in few-shot imitation learning.
The paper tackles the problem of enabling robots to perform tasks on new, unseen objects using only a few demonstrations, by formulating imitation learning as a conditional alignment between graph representations, allowing in-context learning without further training. It shows high effectiveness in few-shot learning for real-world tasks, outperforming baselines.
Consider the following problem: given a few demonstrations of a task across a few different objects, how can a robot learn to perform that same task on new, previously unseen objects? This is challenging because the large variety of objects within a class makes it difficult to infer the task-relevant relationship between the new objects and the objects in the demonstrations. We address this by formulating imitation learning as a conditional alignment problem between graph representations of objects. Consequently, we show that this conditioning allows for in-context learning, where a robot can perform a task on a set of new objects immediately after the demonstrations, without any prior knowledge about the object class or any further training. In our experiments, we explore and validate our design choices, and we show that our method is highly effective for few-shot learning of several real-world, everyday tasks, whilst outperforming baselines. Videos are available on our project webpage at https://www.robot-learning.uk/implicit-graph-alignment.