mlsanityData to 7 Oct 2026

Integrated Decision and Control: Towards Interpretable and Computationally Efficient Driving Intelligence

arXiv 2103.10290 ↗First posted 18 Mar 2021cs.LG cs.ROcited by 25

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

Abstract (arXiv)

Decision and control are core functionalities of high-level automated vehicles. Current mainstream methods, such as functionality decomposition and end-to-end reinforcement learning (RL), either suffer high time complexity or poor interpretability and adaptability on real-world autonomous driving tasks. In this paper, we present an interpretable and computationally efficient framework called integrated decision and control (IDC) for automated vehicles, which decomposes the driving task into static path planning and dynamic optimal tracking that are structured hierarchically. First, the static path planning generates several candidate paths only considering static traffic elements. Then, the dynamic optimal tracking is designed to track the optimal path while considering the dynamic obstacles. To that end, we formulate a constrained optimal control problem (OCP) for each candidate path, optimize them separately and follow the one with the best tracking performance. To unload the heavy online computation, we propose a model-based reinforcement learning (RL) algorithm that can be served as an approximate constrained OCP solver. Specifically, the OCPs for all paths are considered together to construct a single complete RL problem and then solved offline in the form of value and policy networks, for real-time online path selecting and tracking respectively. We verify our framework in both simulations and the real world. Results show that compared with baseline methods IDC has an order of magnitude higher online computing efficiency, as well as better driving performance including traffic efficiency and safety. In addition, it yields great interpretability and adaptability among different driving tasks. The effectiveness of the proposed method is also demonstrated in real road tests with complicated traffic conditions.

Key facts. Cited by 25 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 18 of its 54 references that are in the map. First posted on arXiv 18 Mar 2021.

Builds on

18 of 54 references.

References · 18

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2015Continuous control with deep reinforcement learningcited by 3,279
  4. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  5. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  6. 2018A Convergence Theory for Deep Learning via Over-Parameterizationcited by 784
  7. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
  8. 2016A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehiclescited by 251
  9. 2017Deep Reinforcement Learning framework for Autonomous Drivingcited by 224
  10. 2018Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applicationscited by 122
  11. 2019Model-free Deep Reinforcement Learning for Urban Autonomous Drivingcited by 96
  12. 2019Deep Reinforcement Learning for Multi-objective Optimizationcited by 87
6 more
  1. 2018Efficient representation and approximation of model predictive control laws via deep learningcited by 55
  2. 2018A Reinforcement Learning Based Approach for Automated Lane Change Maneuverscited by 44
  3. 2018Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learningcited by 28
  4. 2020Numerically Stable Dynamic Bicycle Model for Discrete-time Controlcited by 15
  5. 2021Mixed Policy Gradient: off-policy reinforcement learning driven jointly by data and modelcited by 8
  6. 2020Trajectory Generation by Chance Constrained Nonlinear MPC with Probabilistic Predictioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 10; 2024: 4; 2025: 2; 2026: 2.

25 papers.

Sort:

By area:

  1. 2023LanguageMPC: Large Language Models as Decision Makers for Autonomous Drivingcited by 188
  2. 2024Diffusion Actor-Critic with Entropy Regulatorcited by 81
  3. 2022Reachability Constrained Reinforcement Learningcited by 52
  4. 2022Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Modelcited by 44
  5. 2023Towards Knowledge-driven Autonomous Drivingcited by 29
  6. 2023SEPT: Towards Efficient Scene Representation Learning for Motion Predictioncited by 27
  7. 2022Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificatecited by 16
  8. 2023Safe Reinforcement Learning with Dual Robustnesscited by 10
  9. 2023Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimationcited by 10
  10. 2021Self-learned Intelligence for Integrated Decision and Control of Automated Vehicles at Signalized Intersectionscited by 5
  11. 2023Feasible Policy Iteration for Safe Reinforcement Learningcited by 4
  12. 2023Robust Safe Reinforcement Learning under Adversarial Disturbancescited by 4
13 more
  1. 2024Conformal Symplectic Optimization for Stable Reinforcement Learningcited by 4
  2. 2022Improve Generalization of Driving Policy at Signalized Intersections with Adversarial Learningcited by 2
  3. 2023Optimization Landscape of Policy Gradient Methods for Discrete-time Static Output Feedbackcited by 2
  4. 2023Learning Decentralized Traffic Signal Controllers with Multi-Agent Graph Reinforcement Learningcited by 2
  5. 2022Zeroth-Order Actor-Critic: An Evolutionary Framework for Sequential Decision Problemscited by 1
  6. 2024Policy Bifurcation in Safe Reinforcement Learningcited by 1
  7. 2024Q-learning-based Model-free Safety Filtercited by 1
  8. 2025A Driving Regime-Embedded Deep Learning Framework for Modeling Intra-Driver Heterogeneity in Multi-Scale Car-Following Dynamicscited by 1
  9. 2022Integrated Decision and Control for High-Level Automated Vehicles by Mixed Policy Gradient and Its Experiment Verificationcited by 0
  10. 2023Bridging the Gap between Newton-Raphson Method and Regularized Policy Iterationcited by 0
  11. 2025Distributional Soft Actor-Critic with Harmonic Gradient for Safe and Efficient Autonomous Driving in Multi-lane Scenarioscited by 0
  12. 2026NeuralParker: A Reinforcement Learning Planner for Irregular Parking Environmentscited by 0
  13. 2026Evaluation Is All You Need for Multi-Modal Autonomous Drivingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective
  2. 2025Scenario-Based Hierarchical Reinforcement Learning for Automated Driving Decision Making
  3. 2021UMBRELLA: Uncertainty-Aware Model-Based Offline Reinforcement Learning Leveraging Planning
  4. 2026PlanRL: A Trajectory Planning Architecture for Reinforcement Learning-based Driving Experts
  5. 2024Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey
  6. 2024Knowledge Transfer from Simple to Complex: A Safe and Efficient Reinforcement Learning Framework for Autonomous Driving Decision-Making
  7. 2025Multi-Timescale Hierarchical Reinforcement Learning for Unified Behavior and Control of Autonomous Driving
  8. 2024A Reinforcement Learning-Boosted Motion Planning Framework: Comprehensive Generalization Performance in Autonomous Driving