Pith. sign in

REVIEW 6 cited by

ActionFlow: Equivariant, Accurate, and Efficient Policies with Spatially Symmetric Flow Matching

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.04576 v1 pith:DWSHYKXS submitted 2024-09-06 cs.RO cs.AI

classification cs.ROcs.AI
keywords actionflowspatialactionequivariantflowmatchingpoliciestasks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Spatial understanding is a critical aspect of most robotic tasks, particularly when generalization is important. Despite the impressive results of deep generative models in complex manipulation tasks, the absence of a representation that encodes intricate spatial relationships between observations and actions often limits spatial generalization, necessitating large amounts of demonstrations. To tackle this problem, we introduce a novel policy class, ActionFlow. ActionFlow integrates spatial symmetry inductive biases while generating expressive action sequences. On the representation level, ActionFlow introduces an SE(3) Invariant Transformer architecture, which enables informed spatial reasoning based on the relative SE(3) poses between observations and actions. For action generation, ActionFlow leverages Flow Matching, a state-of-the-art deep generative model known for generating high-quality samples with fast inference - an essential property for feedback control. In combination, ActionFlow policies exhibit strong spatial and locality biases and SE(3)-equivariant action generation. Our experiments demonstrate the effectiveness of ActionFlow and its two main components on several simulated and real-world robotic manipulation tasks and confirm that we can obtain equivariant, accurate, and efficient policies with spatially symmetric flow matching. Project website: https://flowbasedpolicies.github.io/

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. EquiBim: Learning Symmetry-Equivariant Policy for Bimanual Manipulation

    cs.RO 2026-03 conditional novelty 6.0 of 10

    Adding a loss that enforces left-right equivariance between observations and actions improves average bimanual imitation policy success by +2.7 to +9.5 points across four observation/action settings.

  2. FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies

    cs.RO 2025-09 conditional novelty 6.0 of 10

    A compact 950-million-parameter robot policy trained in about 200 GPU-hours matches or beats multi-billion-parameter baselines on most manipulation benchmarks, including a new best score on CALVIN ABC.

  3. FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulation

    cs.RO 2025-06 conditional novelty 6.0 of 10

    FlowRAM pairs a shrinking 3D attention region with flow-matching action generation and a Mamba fusion model, setting new RLBench state-of-the-art results.

  4. Temporal Policy: History-Initialized Action Generation for Robotic Learning from Demonstration

    cs.RO 2026-07 conditional novelty 5.0 of 10

    Starting generative action generation from a robot's recent state history instead of Gaussian noise reduces transport cost and enables fast, low-latency control without losing success rate.

  5. BridgeFlow: Fast and Robust SE(2)-Equivariant Motion Planning with Flow Matching

    cs.RO 2026-07 conditional novelty 5.0 of 10

    A flow-matching motion planner achieves SE(2) equivariance via task canonicalization, a Brownian-bridge prior, and context-aware optimal transport, reporting up to 15x faster inference and roughly 2x higher valid-traj...

  6. Time-Unified Diffusion Policy with Action Discrimination for Robotic Manipulation

    cs.RO 2025-06 conditional novelty 5.0 of 10

    TUDP removes timestep conditioning from diffusion policies and adds an action-discrimination signal to learn a time-unified velocity field, achieving SOTA RLBench success rates (82.6% multi-view, 83.8% single-view) an...

Pith tools