mlsanityData to 7 Oct 2026

CADRE: A Cascade Deep Reinforcement Learning Framework for Vision-based Autonomous Urban Driving

arXiv 2202.08557 ↗First posted 17 Feb 2022cs.CV cs.AIcited by 16

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

Abstract (arXiv)

Vision-based autonomous urban driving in dense traffic is quite challenging due to the complicated urban environment and the dynamics of the driving behaviors. Widely-applied methods either heavily rely on hand-crafted rules or learn from limited human experience, which makes them hard to generalize to rare but critical scenarios. In this paper, we present a novel CAscade Deep REinforcement learning framework, CADRE, to achieve model-free vision-based autonomous urban driving. In CADRE, to derive representative latent features from raw observations, we first offline train a Co-attention Perception Module (CoPM) that leverages the co-attention mechanism to learn the inter-relationships between the visual and control information from a pre-collected driving dataset. Cascaded by the frozen CoPM, we then present an efficient distributed proximal policy optimization framework to online learn the driving policy under the guidance of particularly designed reward functions. We perform a comprehensive empirical study with the CARLA NoCrash benchmark as well as specific obstacle avoidance scenarios in autonomous urban driving tasks. The experimental results well justify the effectiveness of CADRE and its superiority over the state-of-the-art by a wide margin.

Key facts. Cited by 16 papers 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 34 of its 48 references that are in the map. First posted on arXiv 17 Feb 2022.

Builds on

34 of 48 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  4. 2015Continuous control with deep reinforcement learningcited by 3,279
  5. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  6. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  7. 2017Non-local Neural Networkscited by 2,290
  8. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  9. 2015Spatial Transformer Networkscited by 1,423
  10. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  11. 2016End to End Learning for Self-Driving Carscited by 1,000
  12. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
22 more
  1. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 391
  2. 2017Residual Attention Network for Image Classificationcited by 385
  3. 2019Learning by Cheatingcited by 361
  4. 2014Recurrent Models of Visual Attentioncited by 344
  5. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
  6. 2016Hierarchical Question-Image Co-Attention for Visual Question Answeringcited by 278
  7. 2018Learning to Drive in a Daycited by 266
  8. 2015DeepDriving: Learning Affordance for Direct Perception in Autonomous Drivingcited by 229
  9. 2017Deep Reinforcement Learning framework for Autonomous Drivingcited by 224
  10. 2021End-to-End Urban Driving by Imitating a Reinforcement Learning Coachcited by 191
  11. 2019End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordancescited by 147
  12. 2020See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networkscited by 138
  13. 2021Learning to drive from a world on railscited by 114
  14. 2017Interpretable Learning for Self-Driving Cars by Visualizing Causal Attentioncited by 106
  15. 2018CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-drivingcited by 96
  16. 2019Model-free Deep Reinforcement Learning for Urban Autonomous Drivingcited by 96
  17. 2018Conditional Affordance Learning for Driving in Urban Environmentscited by 70
  18. 2018Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for Visual Question Answeringcited by 51
  19. 2019Simulation-based reinforcement learning for real-world autonomous drivingcited by 51
  20. 2020Explaining Autonomous Driving by Learning End-to-End Visual Attentioncited by 25
  21. 2017Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learningcited by 14
  22. 2017Brain Inspired Cognitive Model with Attention for Self-Driving Carscited by 10

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 7; 2024: 3; 2025: 5.

16 papers.

Sort:

By area:

  1. 2022Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baselinecited by 247
  2. 2023Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Surveycited by 101
  3. 2025RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learningcited by 76
  4. 2023Improve Robustness of Reinforcement Learning against Observation Perturbations via l_∞ Lipschitz Policy Networkscited by 7
  5. 2024ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learningcited by 5
  6. 2023RLAD: Reinforcement Learning from Pixels for Autonomous Driving in Urban Environmentscited by 4
  7. 2023Sequential Action-Induced Invariant Representation for Reinforcement Learningcited by 3
  8. 2023Addressing Limitations of State-Aware Imitation Learning for Autonomous Drivingcited by 3
  9. 2023Collaborative Route Planning of UAVs, Workers and Cars for Crowdsensing in Disaster Responsecited by 2
  10. 2024From Imitation to Exploration: End-to-end Autonomous Driving based on World Modelcited by 2
  11. 2023Target-point Attention Transformer: A novel trajectory predict network for end-to-end autonomous drivingcited by 1
  12. 2025Offline Reinforcement Learning using Human-Aligned Reward Labeling for Autonomous Emergency Braking in Occluded Pedestrian Crossingcited by 1
4 more
  1. 2025Action Robust Reinforcement Learning via Optimal Adversary Aware Policy Optimizationcited by 1
  2. 2025Advancing Autonomous Driving System Testing: Demands, Challenges, and Future Directionscited by 1
  3. 2024PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learningcited by 0
  4. 2025Autonomous Collaborative Scheduling of Time-dependent UAVs, Workers and Vehicles for Crowdsensing in Disaster Responsecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Evaluating the Robustness of Deep Reinforcement Learning for Autonomous Policies in a Multi-agent Urban Driving Environment
  2. 2021Affordance-based Reinforcement Learning for Urban Driving
  3. 2025A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator
  4. 2023Parameterized Decision-making with Multi-modal Perception for Autonomous Driving
  5. 2021A Versatile and Efficient Reinforcement Learning Framework for Autonomous Driving
  6. 2021Carl-Lead: Lidar-based End-to-End Autonomous Driving with Contrastive Deep Reinforcement Learning
  7. 2021Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients
  8. 2025ME3-BEV: Mamba-Enhanced Deep Reinforcement Learning for End-to-End Autonomous Driving with BEV-Perception