mlsanityData to 7 Oct 2026

BlenDAgger: Blended Shared Control for Interactive Imitation Learning

arXiv 2609.37599 ↗First posted 29 Sep 2026cs.RO cs.LGcited by 0

On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning

Abstract (arXiv)

Robot policies are frequently trained from human corrections, yet teleoperating a robot to provide corrections is burdensome, and human demonstrators are not always optimal. We propose Blended DAgger (BlenDAgger), an approach for collecting data to train imitation learning policies by using shared control to blend the policy's and demonstrator's actions during interventions. By blending human and policy actions, we aim to improve the autonomous performance of manipulation policies. We validate our approach across five manipulation tasks, two in the real world and three in simulation. Our approach achieves higher autonomous performance by 30 or more percentage points on two real-world tasks compared to a typical human-gated correction approach (HG-DAgger). We also investigate the advantages of BlenDAgger that allow for higher autonomous performance, finding that BlenDAgger results in 57% smoother transitions between policy control and human interventions, and 14% higher trajectory similarity to the training data. In a user study (n=14) on two real-world tasks, we find that BlenDAgger results in faster data collection (BF=13.32), and we do not find a difference in subjective perceptions. These results show that blended shared control leads to higher autonomous performance compared to typical methods for fine-tuning robot policies from fully teleoperated interventions.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 28 of its 39 references that are in the map. First posted on arXiv 29 Sep 2026.

Builds on

28 of 39 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025RoboCopilot: Human-in-the-loop Interactive Imitation Learning for Robot Manipulation10 Mar
  2. 2024TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot Learning11 Dec
  3. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation4 Jan
  4. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware23 Apr
  5. 2021LazyDAgger: Reducing Context Switching in Interactive Imitation Learning31 Mar
  6. 2020Human-in-the-Loop Imitation Learning using Remote Teleoperation12 Dec

Other references · 22

  1. 2020Denoising Diffusion Implicit Modelscited by 9,655
  2. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  3. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
  4. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  5. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 391
  6. 2018HG-DAgger: Interactive Imitation Learning with Human Expertscited by 245
  7. 2022Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deploymentcited by 101
  8. 2021ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learningcited by 98
  9. 2018EnsembleDAgger: A Bayesian Approach to Safe Imitation Learningcited by 96
  10. 2024TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correctioncited by 50
  11. 2017Shared Autonomy via Hindsight Optimization for Teleoperation and Teamingcited by 39
  12. 2025Compliant Residual DAgger: Improving Real-World Contact-Rich Manipulation with Human Correctionscited by 25
10 more
  1. 2021Situational Confidence Assistance for Lifelong Shared Autonomycited by 15
  2. 2025The Sense of Agency in Assistive Robotics Using Shared Autonomycited by 8
  3. 2025End-to-End Dexterous Arm-Hand VLA Policies via Shared Autonomy: VR Teleoperation Augmented by Autonomous Hand VLA Policy for Efficient Data Collectioncited by 8
  4. 2015Autonomy Infused Teleoperation with Application to BCI Manipulationcited by 6
  5. 2024Consistency Matters: Defining Demonstration Data Quality Metrics in Robot Learning from Demonstrationcited by 6
  6. 2025HACTS: a Human-As-Copilot Teleoperation System for Robot Learningcited by 6
  7. 2022SARI: Shared Autonomy across Repeated Interactioncited by 5
  8. 2024Incremental Learning for Robot Shared Autonomycited by 3
  9. 2026Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Interventioncited by 2
  10. 2018A Blended Human-Robot Shared Control Framework to Handle Drift and Latencycited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Eliciting Compatible Demonstrations for Multi-Human Imitation Learning
  2. 2026EgoSpeedUp: Transferring Human Manipulation Tempo to Robot Policies
  3. 2025Learning a Thousand Tasks in a Day
  4. 2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Play
  5. 2025RoboManipBaselines: A Unified Framework for Imitation Learning in Robotic Manipulation across Real and Simulation Environments
  6. 2024VITAL: Interactive Few-Shot Imitation Learning via Visual Human-in-the-Loop Corrections
  7. 2026AutoIntervene: Calibrated Intervention for Action-Chunking Imitation Learning Policies
  8. 2026Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through Corrections