mlsanityData to 14 Oct 2026

STAGE: STyle-controllable Action GEneration for personalized autonomous driving

arXiv 2607.29517 ↗First posted 31 Jul 2026cs.RO cs.HCcited by 0

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

Abstract (arXiv)

Driving style refers to the behavioral preferences that drivers maintain during driving, shaped by their diverse experiences, habits, and needs, and is typically reflected in varying levels of aggressiveness. If humans choose to use autonomous driving systems, they would expect the driving style of the systems to closely resemble their own habit. However, this is challenging for current industrial autonomous driving systems. To address this, we developed a style controllable action generation method, STAGE, for driving tasks. Its training process is based on imitation learning, incorporating both style value and latent value action modality encoding. Preference learning is then used to identify the user's driving style as a continuous, monotonic style value. And to reduce the cost of human involvement in the preference training process, we also developed a set of rules to compare driving style in data pairs. Then, during inference, the user inputs the style value to control the generated action patterns, dynamically meeting the user's expectations. Using the STAGE method, we verified that the style-controlled action generation results in several typical road scenarios significantly align with human expectations. Furthermore, through comparisons between the STAGE method and various other approaches, we reveal the unique functionalities of STAGE, including its style controllability, style continuity, driving style alignment capability and driving safety. The code for this work is available at: https://github.com/CarlDegio/STAGE

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 15 of its 31 references that are in the map. First posted on arXiv 31 Jul 2026.

Builds on

15 of 31 references.

References · 15

  1. 2016Generative Adversarial Imitation Learningcited by 1,597
  2. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  3. 2022Planning-oriented Autonomous Drivingcited by 1,087
  4. 2018Behavioral Cloning from Observationcited by 492
  5. 2023DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Modelcited by 461
  6. 2021Implicit Behavioral Cloningcited by 452
  7. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 397
  8. 2021MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learningcited by 290
  9. 2018Baidu Apollo EM Motion Plannercited by 100
  10. 2020Modeling Human Driving Behavior through Generative Adversarial Imitation Learningcited by 45
  11. 2022Safe Real-World Autonomous Driving by Learning to Predict and Plan with a Mixture of Expertscited by 29
  12. 2020NewtonianVAE: Proportional Control and Goal Identification from Pixels via Physical Latent Spacescited by 15
3 more
  1. 2020A Learning-based Discretionary Lane-Change Decision-Making Model with Driving Style Awarenesscited by 9
  2. 2022Training Robots without Robots: Deep Imitation Learning for Master-to-Robot Policy Transfercited by 9
  3. 2021Optimal Vehicle Path Planning Using Quadratic Optimization for Baidu Apollo Open Platformcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Drive My Way: Preference Alignment of Vision-Language-Action Model for Personalized Driving
  2. 2026YOUDrive: Driving Style as a Composable Direction for End-to-End Autonomous Driving
  3. 2024From Words to Wheels: Automated Style-Customized Policy Generation for Autonomous Driving
  4. 2026Driving Like Yourself: A Benchmark for Closed-Loop Personalized End-to-End Autonomous Driving
  5. 2026PersonaDrive: Human-Style Retrieval-Augmented VLA Agents for Closed-Loop Driving Simulation
  6. 2025Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback
  7. 2025StyleDrive: Towards Driving-Style Aware Benchmarking of End-To-End Autonomous Driving
  8. 2025DriveCritic: Towards Context-Aware, Human-Aligned Evaluation for Autonomous Driving with Vision-Language Models