mlsanityData to 13 Oct 2026

Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervision

arXiv 2206.14349 ↗First posted 29 Jun 2022cs.RO cs.AIcited by 30

Not on the map. Why?

Abstract (arXiv)

Commercial and industrial deployments of robot fleets at Amazon, Nimble, Plus One, Waymo, and Zoox query remote human teleoperators when robots are at risk or unable to make task progress. With continual learning, interventions from the remote pool of humans can also be used to improve the robot fleet control policy over time. A central question is how to effectively allocate limited human attention. Prior work addresses this in the single-robot, single-human setting; we formalize the Interactive Fleet Learning (IFL) setting, in which multiple robots interactively query and learn from multiple human supervisors. We propose Return on Human Effort (ROHE) as a new metric and Fleet-DAgger, a family of IFL algorithms. We present an open-source IFL benchmark suite of GPU-accelerated Isaac Gym environments for standardized evaluation and development of IFL algorithms. We compare a novel Fleet-DAgger algorithm to 4 baselines with 100 robots in simulation. We also perform a physical block-pushing experiment with 4 ABB YuMi robot arms and 2 remote humans. Experiments suggest that the allocation of humans to robots significantly affects the performance of the fleet, and that the novel Fleet-DAgger algorithm can achieve up to 8.8x higher ROHE than baselines. See https://tinyurl.com/fleet-dagger for supplemental material.

Key facts. Cited by 30 papers in the map (data through 13 Oct 2026). Builds on 30 of its 75 references that are in the map. First posted on arXiv 29 Jun 2022.

Builds on

30 of 75 references.

References · 30

  1. 2017Proximal Policy Optimization Algorithmscited by 14,592
  2. 2016OpenAI Gymcited by 1,694
  3. 2016Generative Adversarial Imitation Learningcited by 1,577
  4. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,470
  5. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 890
  6. 2018Behavioral Cloning from Observationcited by 483
  7. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 399
  8. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
  9. 2018HG-DAgger: Interactive Imitation Learning with Human Expertscited by 247
  10. 2022Masked Visual Pre-training for Motor Controlcited by 246
  11. 2017DART: Noise Injection for Robust Imitation Learningcited by 188
  12. 2020Recovery RL: Safe Reinforcement Learning with Learned Recovery Zonescited by 157
18 more
  1. 2022Rapid Locomotion via Reinforcement Learningcited by 130
  2. 2020Human-in-the-Loop Imitation Learning using Remote Teleoperationcited by 106
  3. 2021ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learningcited by 101
  4. 2018EnsembleDAgger: A Bayesian Approach to Safe Imitation Learningcited by 98
  5. 2016Query-Efficient Imitation Learning for End-to-End Autonomous Drivingcited by 83
  6. 2022Adversarial Motion Priors Make Good Substitutes for Complex Reward Functionscited by 68
  7. 2021LazyDAgger: Reducing Context Switching in Interactive Imitation Learningcited by 50
  8. 2014Interactive Policy Learning through Confidence-Based Autonomycited by 29
  9. 2019AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teacherscited by 28
  10. 2020LaND: Learning to Navigate from Disengagementscited by 24
  11. 2019Scaled Autonomy: Enabling Human Operators to Control Robot Fleetscited by 16
  12. 2018Learning with Training Wheels: Speeding up Training with a Simple Controller for Deep Reinforcement Learningcited by 14
  13. 2018Intervention Aided Reinforcement Learning for Safe and Practical Policy Optimization in Navigationcited by 12
  14. 2020Interactive Imitation Learning in State-Spacecited by 10
  15. 2021Scalable Operator Allocation for Multi-Robot Assistance: A Restless Bandit Approachcited by 9
  16. 2022ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characterscited by 6
  17. 2022Synergistic Scheduling of Learning and Allocation of Tasks in Human-Robot Teamscited by 5
  18. 2022Traversing Supervisor Problem: An Approximately Optimal Approach to Multi-Robot Assistancecited by 3

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 9; 2025: 9; 2026: 7.

30 papers.

Sort:

By area:

  1. 2023Model-Based Runtime Monitoring with Interactive Imitation Learningcited by 38
  2. 2024Multi-Task Interactive Robot Fleet Learning with Visual World Modelscited by 35
  3. 2024Diff-DAgger: Uncertainty Estimation with Diffusion Policy for Robotic Manipulationcited by 31
  4. 2023Human-in-the-Loop Task and Motion Planning for Imitation Learningcited by 28
  5. 2024TeleMoMa: A Modular and Versatile Teleoperation System for Mobile Manipulationcited by 27
  6. 2023RLIF: Interactive Imitation Learning as Reinforcement Learningcited by 25
  7. 2024IntervenGen: Interventional Data Generation for Robust and Data-Efficient Robot Imitation Learningcited by 24
  8. 2026SOP: A Scalable Online Post-Training System for Vision-Language-Action Modelscited by 20
  9. 2024So You Think You Can Scale Up Autonomous Robot Data Collection?cited by 17
  10. 2025Human-assisted Robotic Policy Refinement via Action Preference Optimizationcited by 13
  11. 2024Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedbackcited by 11
  12. 2022Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learningcited by 10
18 more
  1. 2025MILE: Model-based Intervention Learningcited by 8
  2. 2025Uncertainty Comes for Free: Human-in-the-Loop Policies with Diffusion Modelscited by 8
  3. 2025Genie Centurion: Accelerating Scalable Real-World Robot Training with Human Rewind-and-Refine Guidancecited by 7
  4. 2024Leveraging Demonstrator-perceived Precision for Safe Interactive Imitation Learning of Clearance-limited Taskscited by 5
  5. 2026FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvementcited by 5
  6. 2026Data Pyramid for Embodied Manipulation: A Surveycited by 5
  7. 2023IIFL: Implicit Interactive Fleet Learning from Heterogeneous Human Supervisorscited by 4
  8. 2024NeRF-Aug: Data Augmentation for Robotics with Neural Radiance Fieldscited by 1
  9. 2024Robot See, Robot Do: Imitation Reward for Noisy Financial Environmentscited by 1
  10. 2025R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrationscited by 1
  11. 2025Continuous Vision-Language-Action Co-Learning with Semantic-Physical Alignment for Behavioral Cloningcited by 1
  12. 2025CubeDAgger: Interactive Imitation Learning for Dynamic Systems with Efficient yet Low-risk Interactioncited by 0
  13. 2025ASkDAgger: Active Skill-level Data Aggregation for Interactive Imitation Learningcited by 0
  14. 2025Sample-Efficient Expert Query Control in Active Imitation Learning via Conformal Predictioncited by 0
  15. 2026Easy-IIL: Reducing Human Operational Burden in Interactive Imitation Learning via Assistant Expertscited by 0
  16. 2026HIL-UMI: Bringing Human-in-the-Loop Post-Training of Vision-Language-Action Models to Universal Manipulation Interfacecited by 0
  17. 2026Convex AI Compositionality and the Governance of AI System Populationscited by 0
  18. 2026Reward-DAgger: Robot-Gated Interactive Imitation Learning with General-Purpose Progress-Based Reward Modelscited by 0