mlsanityData to 7 Oct 2026

Towards Learning Generalizable Driving Policies from Restricted Latent Representations

arXiv 2111.03688 ↗First posted 5 Nov 2021cs.ROcited by 4

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

Abstract (arXiv)

Training intelligent agents that can drive autonomously in various urban and highway scenarios has been a hot topic in the robotics society within the last decades. However, the diversity of driving environments in terms of road topology and positioning of the neighboring vehicles makes this problem very challenging. It goes without saying that although scenario-specific driving policies for autonomous driving are promising and can improve transportation safety and efficiency, they are clearly not a universal scalable solution. Instead, we seek decision-making schemes and driving policies that can generalize to novel and unseen environments. In this work, we capitalize on the key idea that human drivers learn abstract representations of their surroundings that are fairly similar among various driving scenarios and environments. Through these representations, human drivers are able to quickly adapt to novel environments and drive in unseen conditions. Formally, through imposing an information bottleneck, we extract a latent representation that minimizes the textitdistance -- a quantification that we introduce to gauge the similarity among different driving configurations -- between driving scenarios. This latent space is then employed as the input to a Q-learning module to learn generalizable driving policies. Our experiments revealed that, using this latent representation can reduce the number of crashes to about half.

Key facts. Cited by 4 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 29 of its 45 references that are in the map. First posted on arXiv 5 Nov 2021.

Builds on

29 of 45 references.

References · 29

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  2. 2017Cognitive Mapping and Planning for Visual Navigationcited by 209
  3. 2018Recent Advances in Autoencoder-Based Representation Learningcited by 130
  4. 2020Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learningcited by 99
  5. 2019Model-free Deep Reinforcement Learning for Urban Autonomous Drivingcited by 96
  6. 2020Learning Latent Representations to Influence Multi-Agent Interactioncited by 92
  7. 2020Reinforcement Learning for Autonomous Driving with Latent State Inference and Spatial-Temporal Relationshipscited by 36
  8. 2017Dynamic Occupancy Grid Prediction for Urban Autonomous Driving: A Deep Learning Approach with Fully Automatic Labelingcited by 30
  9. 2021Social Coordination and Altruism in Autonomous Drivingcited by 28
  10. 2019Optimization for Reinforcement Learning: From Single Agent to Cooperative Agentscited by 19
  11. 2017Formulation of Deep Reinforcement Learning Architecture Toward Autonomous Driving for On-Ramp Mergecited by 17
  12. 2021Cooperative Autonomous Vehicles that Sympathize with Human Driverscited by 17
17 more
  1. 2021Learning Latent Actions to Control Assistive Robotscited by 17
  2. 2019Controlling Steering Angle for Cooperative Self-driving Vehicles utilizing CNN and LSTM-based Deep Networkscited by 15
  3. 2021Learning Visually Guided Latent Actions for Assistive Teleoperationcited by 12
  4. 2020End-to-end Autonomous Driving Perception with Sequential Latent Representation Learningcited by 11
  5. 2021Altruistic Maneuver Planning for Cooperative Autonomous Vehicles Using Multi-agent Advantage Actor-Criticcited by 11
  6. 2019Approximate Robust Control of Uncertain Dynamical Systemscited by 9
  7. 2019Spatio-temporal Dynamics of Cellular V2X Communication in Dense Vehicular Networkscited by 8
  8. 2020A Maneuver-based Urban Driving Dataset and Model for Cooperative Vehicle Applicationscited by 8
  9. 2018Multiple Access in Cellular V2X: Performance Analysis in Highly Congested Vehicular Networkscited by 7
  10. 2019Real-Time Hardware-In-the-Loop Emulation Framework for DSRC-based Connected Vehicle Applicationscited by 7
  11. 2019V2X System Architecture Utilizing Hybrid Gaussian Process-based Model Structurescited by 6
  12. 2020On the Road with 16 Neurons: Mental Imagery with Bio-inspired Deep Neural Networkscited by 5
  13. 2017A Stochastic Hybrid Framework for Driver Behavior Modeling Based on Hierarchical Dirichlet Processcited by 4
  14. 2018A Driver Behavior Modeling Structure Based on Non-parametric Bayesian Stochastic Hybrid Architecturecited by 4
  15. 2019Analysis of Distributed Congestion Control in Cellular Vehicle-to-everything Networkscited by 4
  16. 2020Performance Analysis of Cellular-V2X with Adaptive and Selective Power Controlcited by 4
  17. 2020Efficient Latent Representations using Multiple Tasks for Autonomous Drivingcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 1.

4 papers.

  1. 2022Robustness and Adaptability of Reinforcement Learning based Cooperative Autonomous Driving in Mixed-autonomy Trafficcited by 15
  2. 2022Exploring the trade off between human driving imitation and safety for traffic simulationcited by 3
  3. 2023Deep Occupancy-Predictive Representations for Autonomous Drivingcited by 1
  4. 2022Context-Aware Target Classification with Hybrid Gaussian Process prediction for Cooperative Vehicle Safety systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021A Versatile and Efficient Reinforcement Learning Framework for Autonomous Driving
  2. 2026Latent World Models for Automated Driving: A Unified Taxonomy, Evaluation Framework, and Open Challenges
  3. 2022Driver Dojo: A Benchmark for Generalizable Reinforcement Learning for Autonomous Driving
  4. 2021Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients
  5. 2021Increasing the Efficiency of Policy Learning for Autonomous Vehicles by Multi-Task Representation Learning
  6. 2022Distribution-aware Goal Prediction and Conformant Model-based Planning for Safe Autonomous Driving
  7. 2025Discrete Contrastive Learning for Diffusion Policies in Autonomous Driving
  8. 2026Relationally Grounded Latent World Models for Autonomous Driving