mlsanityData to 14 Oct 2026

Learning by Cheating

arXiv 1912.12294 ↗First posted 27 Dec 2019cs.RO cs.AI cs.CVcited by 383

Not on the map. Why?

Cited by 159 in End-to-end autonomous driving, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Vision-based urban driving is hard. The autonomous system needs to learn to perceive the world and act in it. We show that this challenging learning problem can be simplified by decomposing it into two stages. We first train an agent that has access to privileged information. This privileged agent cheats by observing the ground-truth layout of the environment and the positions of all traffic participants. In the second stage, the privileged agent acts as a teacher that trains a purely vision-based sensorimotor agent. The resulting sensorimotor agent does not have access to any privileged information and does not cheat. This two-stage training procedure is counter-intuitive at first, but has a number of important advantages that we analyze and empirically demonstrate. We use the presented approach to train a vision-based autonomous driving system that substantially outperforms the state of the art on the CARLA benchmark and the recent NoCrash benchmark. Our approach achieves, for the first time, 100% success rate on all tasks in the original CARLA benchmark, sets a new record on the NoCrash benchmark, and reduces the frequency of infractions by an order of magnitude compared to the prior state of the art. For the video that summarizes this work, see https://youtu.be/u9ZCxxD-UUw

Key facts. Cited by 383 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 3; 2021: 50; 2022: 55; 2023: 63; 2024: 85; 2025: 57; 2026: 70.

383 papers.

Sort:

By area:

  1. 2022Planning-oriented Autonomous Drivingcited by 1,087
  2. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 622
  3. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 490
  4. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 485
  5. 2021Multi-Modal Fusion Transformer for End-to-End Autonomous Drivingcited by 377
  6. 2022ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learningcited by 368
  7. 2024NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarkingcited by 354
  8. 2024Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllabilitycited by 347
  9. 2023LMDrive: Closed-Loop End-to-End Driving with Large Language Modelscited by 305
  10. 2024VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planningcited by 289
  11. 2024Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Drivingcited by 252
  12. 2022Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baselinecited by 248
38 more
  1. 2023Parting with Misconceptions about Learning-based Vehicle Motion Planningcited by 242
  2. 2023DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Drivingcited by 233
  3. 2024EMMA: End-to-End Multimodal Model for Autonomous Drivingcited by 231
  4. 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 213
  5. 2022Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformercited by 212
  6. 2021End-to-End Urban Driving by Imitating a Reinforcement Learning Coachcited by 194
  7. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 174
  8. 2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Drivingcited by 169
  9. 2022Rapid Locomotion via Reinforcement Learningcited by 168
  10. 2024Enhancing End-to-End Autonomous Driving with Latent World Modelcited by 166
  11. 2021A System for General In-Hand Object Re-Orientationcited by 165
  12. 2023Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Researchcited by 160
  13. 2022Legged Locomotion in Challenging Terrains using Egocentric Visioncited by 151
  14. 2025End-to-End Driving with Online Trajectory Evaluation via BEV World Modelcited by 151
  15. 2022Model-Based Imitation Learning for Urban Drivingcited by 150
  16. 2025Pseudo-Simulation for Autonomous Drivingcited by 150
  17. 2023Robot Parkour Learningcited by 149
  18. 2023DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Drivingcited by 144
  19. 2024Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulationcited by 144
  20. 2022Learning from All Vehiclescited by 135
  21. 2021Learning High-Speed Flight in the Wildcited by 128
  22. 2025DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Drivingcited by 126
  23. 2023UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policycited by 124
  24. 2021Learning to drive from a world on railscited by 114
  25. 2022PlanT: Explainable Planning Transformers via Object-Level Representationscited by 105
  26. 2024Towards learning-based planning:The nuPlan benchmark for real-world autonomous drivingcited by 104
  27. 2023Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Surveycited by 103
  28. 2022Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapescited by 101
  29. 2023General In-Hand Object Rotation with Vision and Touchcited by 99
  30. 2021Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Imagescited by 98
  31. 2022KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradientscited by 96
  32. 2023Hidden Biases of End-to-End Driving Modelscited by 96
  33. 2022COOPERNAUT: End-to-End Driving with Cooperative Perception for Networked Vehiclescited by 95
  34. 2025DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planningcited by 94
  35. 2023ReasonNet: End-to-End Driving with Temporal and Global Reasoningcited by 93
  36. 2024RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Modelcited by 92
  37. 2023The Waymo Open Sim Agents Challengecited by 86
  38. 2024VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervisioncited by 86

50 most cited of 383 All 383 (JSON)