ROApr 7

HiPolicy: Hierarchical Multi-Frequency Action Chunking for Policy Learning

arXiv:2604.0606751.9
Predicted impact top 43% in RO · last 90 daysOriginality Incremental advance
AI Analysis

This addresses a fundamental challenge in robotic imitation learning, offering a method to enhance both planning and control, though it appears incremental as it builds on existing action chunking approaches.

The paper tackles the trade-off between long-horizon planning and fine-grained control in robotic imitation learning by proposing HiPolicy, a hierarchical multi-frequency action chunking framework, which improves performance and efficiency in simulated and real-world tasks.

Robotic imitation learning faces a fundamental trade-off between modeling long-horizon dependencies and enabling fine-grained closed-loop control. Existing fixed-frequency action chunking approaches struggle to achieve both. Building on this insight, we propose HiPolicy, a hierarchical multi-frequency action chunking framework that jointly predicts action sequences at different frequencies to capture both coarse high-level plans and precise reactive motions. We extract and fuse hierarchical features from history observations aligned to each frequency for multi-frequency chunk generation, and introduce an entropy-guided execution mechanism that adaptively balances long-horizon planning with fine-grained control based on action uncertainty. Experiments on diverse simulated benchmarks and real-world manipulation tasks show that HiPolicy can be seamlessly integrated into existing 2D and 3D generative policies, delivering consistent improvements in performance while significantly enhancing execution efficiency.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes