mlsanityData to 14 Oct 2026

Multi-Abstractive Neural Controller: An Efficient Hierarchical Control Architecture for Interactive Driving

arXiv 2305.14797 ↗First posted 24 May 2023cs.ROcited by 0

On the map: End-to-end autonomous driving → Imitation-learning end-to-end planners

Abstract (arXiv)

As learning-based methods make their way from perception systems to planning/control stacks, robot control systems have started to enjoy the benefits that data-driven methods provide. Because control systems directly affect the motion of the robot, data-driven methods, especially black box approaches, need to be used with caution considering aspects such as stability and interpretability. In this paper, we describe a differentiable and hierarchical control architecture. The proposed representation, called textitmulti-abstractive neural controller, uses the input image to control the transitions within a novel discrete behavior planner (referred to as the visual automaton generative network, or textitvAGN). The output of a vAGN controls the parameters of a set of dynamic movement primitives which provides the system controls. We train this neural controller with real-world driving data via behavior cloning and show improved explainability, sample efficiency, and similarity to human driving.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving. Builds on 19 of its 29 references that are in the map. First posted on arXiv 24 May 2023.

Builds on

19 of 29 references.

References · 19

  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  2. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  3. 2016The Mythos of Model Interpretabilitycited by 721
  4. 2013Network In Networkcited by 605
  5. 2018Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networkscited by 289
  6. 2021End-to-end Interpretable Neural Motion Plannercited by 242
  7. 2021RvS: What is Essential for Offline RL via Supervised Learning?cited by 185
  8. 2022Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methodscited by 151
  9. 2019Learning by Abstraction: The Neural State Machinecited by 113
  10. 2018How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanationcited by 72
  11. 2017PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planningcited by 69
  12. 2022Learning to Induce Causal Structurecited by 68
7 more
  1. 2022Real-time Neural-MPC: Deep Learning Model Predictive Control for Quadrotors and Agile Robotic Platformscited by 41
  2. 2021Accelerating Quadratic Optimization with Reinforcement Learningcited by 30
  3. 2020Differentiable Weighted Finite-State Transducerscited by 22
  4. 2022Learning to Optimize in Model Predictive Controlcited by 11
  5. 2016VisualBackProp: efficient visualization of CNNscited by 10
  6. 2021Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitionscited by 7
  7. 2019Neural Autonomous Navigation with Riemannian Motion Policycited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Interpretable Motion Planner for Urban Driving via Hierarchical Imitation Learning
  2. 2024Hybrid Imitation-Learning Motion Planner for Urban Driving
  3. 2026MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving
  4. 2022Evaluation of MPC-based Imitation Learning for Human-like Autonomous Driving
  5. 2019Learning a Decision Module by Imitating Driver's Control Behaviors
  6. 2026Learning-Based Behavior Planning for Automated Driving: Real-World Integration and Deployment
  7. 2022SHAIL: Safety-Aware Hierarchical Adversarial Imitation Learning for Autonomous Driving in Urban Environments
  8. 2026DriveZero: End-to-End Driving Beyond Human Demonstrations