Physical Time as a Missing Dimension of Robot Policy Memory Dynamics

Hugging Face Daily Papers Papers
robotics policy-memory diffusion-policy flow-matching manipulation temporal-dynamics imitation-learning

Summary

提出Temporal Flow Policy (TFP)，将物理时间作为机器人策略记忆的缺失维度，使记忆状态随实测时间间隔演化，从而在扩散策略与π₀.₅上实现更准确的时序控制与记忆读出，在LIBERO及真实机器人任务中优于循环与状态空间记忆基线。

Existing robot policy memories typically evolve with observation sequences, implicitly treating each update as the same amount of physical time. Yet identical observation histories can span different durations and require different actions, exposing physical time as a missing dimension of policy memory. We introduce Temporal Flow Policy (TFP), which learns memory dynamics to retain past events and evolve the memory state over measured time intervals. Observations and prior memory determine the content and time scales of each transition; elapsed time determines how far the state advances. TFP conditions diffusion and flow-matching policies through this memory state and is trained with their native imitation objectives. We evaluate TFP with Diffusion Policy and π_{0.5} through controlled comparisons of memory designs. These experiments show that successful timing depends on both measured intervals and retained history. TFP achieves higher average success than the recurrent and state-space memories we equip with the same intervals and than a variant that feeds the interval to a learned gate. Memory readouts recover the time since an event and motion information after occlusion. Changing the supplied intervals systematically delays or advances actions, linking time inputs to behavior. Real-robot tasks requiring timing or memory, together with LIBERO evaluations, demonstrate benefits in physical and general manipulation. These results suggest viewing robot memory not as stored observation history, but as a state that retains past events and evolves with physical time.
Original Article
View Cached Full Text

Cached at: 10/15/26, 07:04 AM

Paper page - Physical Time as a Missing Dimension of Robot Policy Memory Dynamics

Source: https://huggingface.co/papers/2610.20524

Abstract

Existingrobotpolicymemoriestypicallyevolvewithobservationsequences,implicitlytreatingeachupdateasthesameamountofphysicaltime.Yetidenticalobservationhistoriescanspandifferentdurationsandrequiredifferentactions,exposingphysicaltimeasamissingdimensionofpolicymemory.WeintroduceTemporalFlowPolicy(TFP),whichlearnsmemorydynamicstoretainpasteventsandevolvethememorystateovermeasuredtimeintervals.Observationsandpriormemorydeterminethecontentandtimescalesofeachtransition;elapsedtimedetermineshowfarthestateadvances.TFPconditionsdiffusionandflow-matchingpoliciesthroughthismemorystateandistrainedwiththeirnativeimitationobjectives.WeevaluateTFPwithDiffusionPolicyandπ_{0.5}throughcontrolledcomparisonsofmemorydesigns.Theseexperimentsshowthatsuccessfultimingdependsonbothmeasuredintervalsandretainedhistory.TFPachieveshigheraveragesuccessthantherecurrentandstate-spacememoriesweequipwiththesameintervalsandthanavariantthatfeedstheintervaltoalearnedgate.Memoryreadoutsrecoverthetimesinceaneventandmotioninformationafterocclusion.Changingthesuppliedintervalssystematicallydelaysoradvancesactions,linkingtimeinputstobehavior.Real-robottasksrequiringtimingormemory,togetherwithLIBEROevaluations,demonstratebenefitsinphysicalandgeneralmanipulation.Theseresultssuggestviewingrobotmemorynotasstoredobservationhistory,butasastatethatretainspasteventsandevolveswithphysicaltime.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2610\.20524

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.20524 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.20524 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.20524 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents

Hugging Face Daily Papers

This paper introduces a proactive memory agent that runs alongside an action agent to prevent behavioral state decay in long-horizon tasks, achieving significant improvements on Terminal-Bench2.0 and τ^2-Bench. The authors also train Qwen3.5-27B using SFT and GRPO as an early step toward open-weight memory policies.

πR^2: Reactive Real-time Flow Policies

Hugging Face Daily Papers

πR^2 introduces a reactive real-time flow policy for robot manipulation that splits conditioning into fast and slow channels and uses a latency-adaptive flow schedule, enabling closed-loop replanning ~4x faster than baseline policies and improving success rates by up to 30%.

AURA: Action-Gated Memory for Robot Policies at Constant VRAM

arXiv cs.AI

AURA-Mem proposes a constant-size memory for robot policies using a learned gate that writes only when current observations would change the next action. It matches baseline accuracy with significantly fewer writes and constant VRAM, addressing the memory bottleneck for long-horizon robot tasks.