A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics

TL;DR

This paper introduces a hierarchical spatiotemporal action tokenizer, HiST-AT, that improves in-context imitation learning for robotics by multi-level clustering of actions and timestamps, achieving state-of-the-art results.

Contribution

The paper proposes a novel hierarchical spatiotemporal action tokenizer with multi-level clustering, enhancing imitation learning performance in robotics.

Findings

Outperforms non-hierarchical methods in action reconstruction.

Utilizes both spatial and temporal cues for better action understanding.

Achieves new state-of-the-art results on multiple benchmarks.

Abstract

We present a novel hierarchical spatiotemporal action tokenizer for in-context imitation learning. We first propose a hierarchical approach, which consists of two successive levels of vector quantization. In particular, the lower level assigns input actions to fine-grained subclusters, while the higher level further maps fine-grained subclusters to clusters. Our hierarchical approach outperforms the non-hierarchical counterpart, while mainly exploiting spatial information by reconstructing input actions. Furthermore, we extend our approach by utilizing both spatial and temporal cues, forming a hierarchical spatiotemporal action tokenizer, namely HiST-AT. Specifically, our hierarchical spatiotemporal approach conducts multi-level clustering, while simultaneously recovering input actions and their associated timestamps. Finally, extensive evaluations on multiple simulation and real robotic manipulation benchmarks show that our approach establishes a new state-of-the-art performance in in-context imitation learning.