Action Chunk Scheduling for Batched Robot Policy Serving

• URL: http://arxiv.org/abs/2608.00337v1
• Date: Fri, 31 Jul 2026 22:58:59 GMT
• Title: Action Chunk Scheduling for Batched Robot Policy Serving
• Abstract summary: We introduce the problem of serving a robot policy to multiple robots from a remote GPU and formulate it as a scheduling problem.<n>We build Armory, a serving system validated on fleets of both simulated and real robots.<n>Our experiments show that naive schedulings perform well when all robots are the same, but fall short when robots consume action chunks at different rates.
• Score: 7.138711572751692
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deploying robot foundation models at scale is the next step towards realizing the potential of general-purpose robots. However, Vision-Language-Action (VLA) and other foundation models are computationally demanding, and on-device compute is constrained by power and space. In this paper, we introduce the problem of serving a robot policy to multiple robots from a remote GPU and formulate it as a scheduling problem. We build Armory, a serving system validated on fleets of both simulated and real robots. Our experiments show that naive scheduling heuristics perform well when all robots are the same, but fall short when robots consume action chunks at different rates, uncovering a mismatch between conventional batching methods and the closed-loop requirements of robot policy execution. To address this, we propose a scheduling algorithm that accounts for this heterogeneity and improves overall system throughput by up to $18\%$ in real-world experiments. Additional details are available at https://gatech-rl2.github.io/actionchunkscheduling.

Related papers

• Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data [60.94418315274988]
  Ego2Robot supports both curated and in-the-wild videos, producing 18,561 hours of robot training data spanning 15 robot morphologies.<n>Joint pretraining on Ego2Robot-synthesized and robot data consistently improves out-of-distribution generalization across multiple types.
  arXiv  Detail & Related papers  (2026-08-03T17:52:26Z)
• Generalizable Humanoid Manipulation with 3D Diffusion Policies [66.78220965526732]
  We build a real-world robotic system to address the problem of autonomous manipulation by humanoid robots.<n>Our system is mainly an integration of 1) a whole-upper-body robotic teleoperation system to acquire human-like robot data, and 2) a 25-DoF humanoid robot platform with a height-adjustable cart and a 3D LiDAR sensor.<n>We show that using only data collected in one scene and with only onboard computing, a full-sized humanoid robot can autonomously perform skills in diverse real-world scenarios.
  arXiv  Detail & Related papers  (2024-10-14T17:59:00Z)
• RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulation [77.41969287400977]
  This paper presents textbfRobotScript, a platform for a deployable robot manipulation pipeline powered by code generation. We also present a benchmark for a code generation benchmark for robot manipulation tasks in free-form natural language. We demonstrate the adaptability of our code generation framework across multiple robot embodiments, including the Franka and UR5 robot arms.
  arXiv  Detail & Related papers  (2024-02-22T15:12:00Z)
• Real-time Holistic Robot Pose Estimation with Unknown States [30.41806081818826]
  Estimating robot pose from RGB images is a crucial problem in computer vision and robotics. Previous methods presume full knowledge of robot internal states, e.g. ground-truth robot joint angles. This work introduces an efficient framework for real-time robot pose estimation from RGB images without requiring known robot states.
  arXiv  Detail & Related papers  (2024-02-08T13:12:50Z)
• ImitationNet: Unsupervised Human-to-Robot Motion Retargeting via Shared Latent Space [9.806227900768926]
  This paper introduces a novel deep-learning approach for human-to-robot motion. Our method does not require paired human-to-robot data, which facilitates its translation to new robots. Our model outperforms existing works regarding human-to-robot similarity in terms of efficiency and precision.
  arXiv  Detail & Related papers  (2023-09-11T08:55:04Z)
• Decentralised construction of a global coordinate system in a large swarm of minimalistic robots [0.8701566919381223]
  In this study, we present an algorithm to enable positional self-awareness in a swarm of minimalistic error-prone robots. Despite being unable to measure the bearing of incoming messages, the robots running our algorithm can calculate their position within a swarm deployed in a regular formation. Our solution has fewer requirements than state-of-the-art algorithms and contains collective noise-filtering mechanisms.
  arXiv  Detail & Related papers  (2023-02-28T14:14:17Z)
• GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots [87.32145104894754]
  We introduce a framework for training generalized locomotion (GenLoco) controllers for quadrupedal robots. Our framework synthesizes general-purpose locomotion controllers that can be deployed on a large variety of quadrupedal robots. We show that our models acquire more general control strategies that can be directly transferred to novel simulated and real-world robots.
  arXiv  Detail & Related papers  (2022-09-12T15:14:32Z)
• Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervision [72.4735163268491]
  Commercial and industrial deployments of robot fleets often fall back on remote human teleoperators during execution. We formalize the Interactive Fleet Learning (IFL) setting, in which multiple robots interactively query and learn from multiple human supervisors. We propose Fleet-DAgger, a family of IFL algorithms, and compare a novel Fleet-DAgger algorithm to 4 baselines in simulation.
  arXiv  Detail & Related papers  (2022-06-29T01:23:57Z)
• REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer [57.045140028275036]
  We consider the problem of transferring a policy across two different robots with significantly different parameters such as kinematics and morphology. Existing approaches that train a new policy by matching the action or state transition distribution, including imitation learning methods, fail due to optimal action and/or state distribution being mismatched in different robots. We propose a novel method named $REvolveR$ of using continuous evolutionary models for robotic policy transfer implemented in a physics simulator.
  arXiv  Detail & Related papers  (2022-02-10T18:50:25Z)
• Know Thyself: Transferable Visuomotor Control Through Robot-Awareness [22.405839096833937]
  Training visuomotor robot controllers from scratch on a new robot typically requires generating large amounts of robot-specific data. We propose a "robot-aware" solution paradigm that exploits readily available robot "self-knowledge" Our experiments on tabletop manipulation tasks in simulation and on real robots demonstrate that these plug-in improvements dramatically boost the transferability of visuomotor controllers.
  arXiv  Detail & Related papers  (2021-07-19T17:56:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.