mlsanityData to 7 Oct 2026

Disturbance Injection under Partial Automation: Robust Imitation Learning for Long-horizon Tasks

arXiv 2303.12375 ↗First posted 22 Mar 2023cs.RO cs.LGcited by 4

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

Partial Automation (PA) with intelligent support systems has been introduced in industrial machinery and advanced automobiles to reduce the burden of long hours of human operation. Under PA, operators perform manual operations (providing actions) and operations that switch to automatic/manual mode (mode-switching). Since PA reduces the total duration of manual operation, these two action and mode-switching operations can be replicated by imitation learning with high sample efficiency. To this end, this paper proposes Disturbance Injection under Partial Automation (DIPA) as a novel imitation learning framework. In DIPA, mode and actions (in the manual mode) are assumed to be observables in each state and are used to learn both action and mode-switching policies. The above learning is robustified by injecting disturbances into the operator's actions to optimize the disturbance's level for minimizing the covariate shift under PA. We experimentally validated the effectiveness of our method for long-horizon tasks in two simulations and a real robot environment and confirmed that our method outperformed the previous methods and reduced the demonstration burden.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 12 of its 25 references that are in the map. First posted on arXiv 22 Mar 2023.

Builds on

12 of 25 references.

Closest ancestors · 6

Same direction, newest first

  1. 2022Disturbance-Injected Robust Imitation Learning with Task Achievement9 May
  2. 2021ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning17 Sep
  3. 2021Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies25 Mar
  4. 2019Imitation Learning from Imperfect Demonstration27 Jan
  5. 2018An Algorithmic Perspective on Imitation Learning16 Nov
  6. 2018HG-DAgger: Interactive Imitation Learning with Human Experts5 Oct

Other references · 6

  1. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 286
  2. 2017DART: Noise Injection for Robust Imitation Learningcited by 187
  3. 2020Learning to Generalize Across Long-Horizon Tasks from Human Demonstrationscited by 114
  4. 2021Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstrationcited by 92
  5. 2018Hierarchical Imitation and Reinforcement Learningcited by 88
  6. 2020Intermittent Visual Servoing: Efficiently Learning Policies Robust to Instrument Changes for High-precision Surgical Manipulationcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Self-Augmented Robot Trajectory: Efficient Imitation Learning via Safe Self-augmentation with Demonstrator-annotated Precisioncited by 2
  2. 2025Feasibility-aware Imitation Learning from Observations through a Hand-mounted Demonstration Interfacecited by 1
  3. 2025BEAC: Imitating Complex Exploration and Task-oriented Behaviors for Invisible Object Nonprehensile Manipulationcited by 0
  4. 2026Feasibility-aware Imitation Learning from Observation with Multimodal Feedbackcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies for Robot Manipulation
  2. 2024Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overview
  3. 2025MILE: Model-based Intervention Learning
  4. 2022Imitation Learning by Estimating Expertise of Demonstrators
  5. 2022Robust Learning from Observation with Model Misspecification
  6. 2024Imitation Learning from Observations: An Autoregressive Mixture of Experts Approach
  7. 2025The Pitfalls of Imitation Learning when Actions are Continuous
  8. 2025Robust Offline Imitation Learning Through State-level Trajectory Stitching