mlsanityData to 7 Oct 2026

Uncertainty-Aware Data Aggregation for Deep Imitation Learning

arXiv 1905.02780 ↗First posted 7 May 2019cs.LG cs.RO stat.MLcited by 19

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

Abstract (arXiv)

Estimating statistical uncertainties allows autonomous agents to communicate their confidence during task execution and is important for applications in safety-critical domains such as autonomous driving. In this work, we present the uncertainty-aware imitation learning (UAIL) algorithm for improving end-to-end control systems via data aggregation. UAIL applies Monte Carlo Dropout to estimate uncertainty in the control output of end-to-end systems, using states where it is uncertain to selectively acquire new training data. In contrast to prior data aggregation algorithms that force human experts to visit sub-optimal states at random, UAIL can anticipate its own mistakes and switch control to the expert in order to prevent visiting a series of sub-optimal states. Our experimental results from simulated driving tasks demonstrate that our proposed uncertainty estimation method can be leveraged to reliably predict infractions. Our analysis shows that UAIL outperforms existing data aggregation algorithms on a series of benchmark tasks.

Key facts. Cited by 19 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 19 of its 33 references that are in the map. First posted on arXiv 7 May 2019.

Builds on

19 of 33 references.

Closest ancestors · 1

Same direction, newest first

  1. 2018Safe end-to-end imitation learning for model predictive control27 Mar

Other references · 18

  1. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  3. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  5. 2016End to End Learning for Self-Driving Carscited by 1,000
  6. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  7. 2017Deep Bayesian Active Learning with Image Datacited by 812
  8. 2016Deep Exploration via Bootstrapped DQNcited by 518
  9. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
  10. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 287
  11. 2016Adversarial Training Methods for Semi-Supervised Text Classificationcited by 280
  12. 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
6 more
  1. 2015Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inferencecited by 159
  2. 2018The Best of Both Worlds: Combining Recent Advances in Neural Machine Translationcited by 101
  3. 2016Query-Efficient Imitation Learning for End-to-End Autonomous Drivingcited by 83
  4. 2017Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Carcited by 65
  5. 2014Interactive Policy Learning through Confidence-Based Autonomycited by 29
  6. 2017Learning Robust Bed Making using Deep Imitation Learning with DARTcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 2; 2022: 0; 2023: 5; 2024: 3; 2025: 5; 2026: 3.

19 papers.

Sort:

By area:

  1. 2023Data Quality in Imitation Learningcited by 72
  2. 2021A Survey of Deep RL and IL for Autonomous Driving Policy Learningcited by 59
  3. 2021Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworkscited by 56
  4. 2023HYDRA: Hybrid Robot Actions for Imitation Learningcited by 54
  5. 2025Failure Prediction at Runtime for Generative Robot Policiescited by 36
  6. 2025CUPID: Curating Data your Robot Loves with Influence Functionscited by 21
  7. 2024Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedbackcited by 11
  8. 2020Driving Through Ghosts: Behavioral Cloning with False Positivescited by 8
  9. 2026ReconVLA: An Uncertainty-Guided and Failure-Aware Vision-Language-Action Framework for Robotic Controlcited by 5
  10. 2023Get Back Here: Robust Imitation by Return-to-Distribution Planningcited by 4
  11. 2026Uncertainty Quantification for Flow-Based Vision-Language-Action Modelscited by 4
  12. 2026RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Modelscited by 2
7 more
  1. 2024COIN: Chance-Constrained Imitation Learning for Uncertainty-aware Adaptive Resource Oversubscription Policycited by 1
  2. 2024Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloningcited by 1
  3. 2025CARIL: Confidence-Aware Regression in Imitation Learning for Autonomous Drivingcited by 1
  4. 2023Specification-Guided Data Aggregation for Semantically Aware Imitation Learningcited by 0
  5. 2023Agnostic Interactive Imitation Learning: New Theory and Practical Algorithmscited by 0
  6. 2025CubeDAgger: Interactive Imitation Learning for Dynamic Systems with Efficient yet Low-risk Interactioncited by 0
  7. 2025ASkDAgger: Active Skill-level Data Aggregation for Interactive Imitation Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Uncertainty-Aware Model-Based Reinforcement Learning with Application to Autonomous Driving
  2. 2022SHAIL: Safety-Aware Hierarchical Adversarial Imitation Learning for Autonomous Driving in Urban Environments
  3. 2026Distributionally Robust and Safe Imitation Learning
  4. 2025RISE: Robust Imitation through Stochastic Encoding
  5. 2019Visual-based Autonomous Driving Deployment from a Stochastic and Uncertainty-aware Perspective
  6. 2018EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning
  7. 2024Uncertainty-Aware Deployment of Pre-trained Language-Conditioned Imitation Learning Policies
  8. 2025From Imitation to Optimization: A Comparative Study of Offline Learning for Autonomous Driving