mlsanityData to 7 Oct 2026

Bridging Sim2Real Gap Using Image Gradients for the Task of End-to-End Autonomous Driving

arXiv 2205.07481 ↗First posted 16 May 2022cs.ROcited by 1

On the map: End-to-end autonomous driving → Reinforcement learning for driving

Abstract (arXiv)

We present the first prize solution to NeurIPS 2021 - AWS Deepracer Challenge. In this competition, the task was to train a reinforcement learning agent (i.e. an autonomous car), that learns to drive by interacting with its environment, a simulated track, by taking an action in a given state to maximize the expected reward. This model was then tested on a real-world track with a miniature AWS Deepracer car. Our goal is to train a model that can complete a lap as fast as possible without going off the track. The Deepracer challenge is a part of a series of embodied intelligence competitions in the field of autonomous vehicles, called The AI Driving Olympics (AI-DO). The overall objective of the AI-DO is to provide accessible mechanisms for benchmarking progress in autonomy applied to the task of autonomous driving. The tricky section of this challenge was the sim2real transfer of the learned skills. To reduce the domain gap in the observation space we did a canny edge detection in addition to cropping out of the unnecessary background information. We modeled the problem as a behavioral cloning task and used MLP-MIXER to optimize for runtime. We made sure our model was capable of handling control noise by careful filtration of the training data and that gave us a robust model capable of completing the track even when 50% of the commands were randomly changed. The overall runtime of the model was only 2-3ms on a modern CPU.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving. Builds on 8 of its 14 references that are in the map. First posted on arXiv 16 May 2022.

Builds on

8 of 14 references.

References · 8

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  2. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  3. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  4. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
  5. 2021End-to-end Interpretable Neural Motion Plannercited by 240
  6. 2018Driving Policy Transfer via Modularity and Abstractioncited by 91
  7. 2016Query-Efficient Imitation Learning for End-to-End Autonomous Drivingcited by 83
  8. 2021Pre-training of Deep RL Agents for Improved Learning under Domain Randomizationcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1.

1 paper.

  1. 2022Sim-to-Real via Sim-to-Seg: End-to-end Off-road Autonomous Driving Without Real Datacited by 9

Similar, not cited

Close in wording, no citation either way

  1. 2021Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning
  2. 2021Autonomous Racing using a Hybrid Imitation-Reinforcement Learning Architecture
  3. 2022Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle Racing
  4. 2025Imitation Learning for Autonomous Driving: Insights from Real-World Testing
  5. 2020Imitation Learning Approach for AI Driving Olympics Trained on Real-world and Simulation Data Simultaneously
  6. 2024Towards an Autonomous Test Driver: High-Performance Driver Modeling via Reinforcement Learning
  7. 2024Deep Reinforcement Learning for Local Path Following of an Autonomous Formula SAE Vehicle
  8. 2024Self-Driving Car Racing: Application of Deep Reinforcement Learning