PersonaDrive: Controllable Trajectory Prediction with Multi-Dimensional Driving Personas

• URL: http://arxiv.org/abs/2608.15230v1
• Date: Sat, 15 Aug 2026 13:37:40 GMT
• Title: PersonaDrive: Controllable Trajectory Prediction with Multi-Dimensional Driving Personas
• Abstract summary: We present the Persona-Conditioned Trajectory dataset, which decomposes driving personas along two axes, Temporal Urgency and Ride Comfort.<n>We also present PersonaDrive, a framework that can learn driving personas from language and can generate persona-specific trajectories.<n>Tests show that PersonaDrive consistently improves over the compared baselines across multi-dimensional scenarios.
• Score: 24.951167128527477
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although recent trajectory prediction and end-to-end autonomous driving methods improve robustness in urban environments, they still lack meaningful controllability. Existing benchmarks either provide no persona-conditioned annotations or support only a single urgency spectrum (i.e., emergency, normal, relaxed), which cannot distinguish personas that share the same urgency level but require different driving dynamics. To address this, we propose (i) the Persona-Conditioned Trajectory (PCT) dataset, which decomposes driving personas along two axes, Temporal Urgency and Ride Comfort, and combines three levels of each to form a grid of nine personas, each paired with natural-language descriptions and trajectories, and (ii) PersonaDrive, a framework that can learn driving personas from language and can generate persona-specific trajectories. PersonaDrive incorporates Persona-Conditioned Anchor Transform (PCAT), which hierarchically reshapes anchors along both axes, and Persona-Conditioned Multi-Modal Fusion (PCMF) for BEV-level persona fusion. Training is supervised by a Hierarchical Guide Loss enforcing axis-aligned physical orderings and an Axis-Decomposed Diversity Loss preventing diagonal mode collapse. Experimental results show that PersonaDrive consistently improves over the compared baselines across multi-dimensional scenarios. The code and PCT dataset are available at https://github.com/VisualAIKHU/PersonaDrive

Related papers

• PersonaDrive: Human-Style Retrieval-Augmented VLA Agents for Closed-Loop Driving Simulation [9.651475921652052]
  We introduce PersonaDrive, a pipeline that conditions a vision--action driving agent on retrieved demonstrations from a style-instructed human driving dataset.<n>The pipeline has three stages: offline triplet mining over per-style human driving data using a combined image-text similarity score; training a lightweight retrieval head that fuses frozen visual features with a small control encoder over per-style databases; and fine-tuning a single VLA backbone to treat retrieved context points as behavioral demonstrations.
  arXiv  Detail & Related papers  (2026-06-10T19:16:31Z)
• CLEAR: Cognition and Latent Evaluation for Adaptive Routing in End-to-End Autonomous Driving [19.474428775260034]
  We propose CLEAR, a framework that combines ultra-fast generative planning with deep semantic reasoning.<n> CLEAR employs Drive-JEPA as the visual encoder and replaces the multi-step denoising chain with a single-step conditional drift in a VAE latent space.<n>On the NAVSIM v1 benchmark, CLEAR achieves a state-of-the-art PDMS of 93.7.
  arXiv  Detail & Related papers  (2026-06-04T14:32:10Z)
• MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving [62.43744546817599]
  Vision-language--action (VLA) models are effective as end-to-end motion planners, but can be brittle when evaluated in closed-loop settings.<n>We propose MAPLE, a novel framework for reactive, multi-agent rollout of a dynamic driving scenario in the latent space of the VLA model.<n> MAPLE achieves state-of-the-art driving performance on Bench2Drive and demonstrates scalable, closed-loop multi-agent play for robust E2E autonomous driving systems.
  arXiv  Detail & Related papers  (2026-05-13T23:35:14Z)
• Driving with A Thousand Faces: A Benchmark for Closed-Loop Personalized End-to-End Autonomous Driving [39.31712441721641]
  Person2Drive is a comprehensive personalized E2E-AD platform and benchmark.<n>It includes an open-source, flexible data collection system that simulates realistic scenarios to generate personalized driving datasets.<n>Our dataset and code will be released after acceptance.
  arXiv  Detail & Related papers  (2026-02-21T08:42:32Z)
• ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving [49.07731497951963]
  ReCogDrive is a novel Reinforced Cognitive framework for end-to-end autonomous driving.<n>We introduce a hierarchical data pipeline that mimics the sequential cognitive process of human drivers.<n>We then address the language-action mismatch by injecting the VLM's learned driving priors into a diffusion planner.
  arXiv  Detail & Related papers  (2025-06-09T03:14:04Z)
• Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback [37.78654159363553]
  We introduce TrajHF, a human feedback-driven finetuning framework for generative trajectory models.<n>TrajHF incorporates multi-conditional denoiser and reinforcement learning with human feedback to refine multi-modal trajectory generation.<n>TrajHF achieves performance comparable to the state-of-the-art on NavSim benchmark.
  arXiv  Detail & Related papers  (2025-03-13T14:56:17Z)
• DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving [62.62464518137153]
  DriveTransformer is a simplified E2E-AD framework for the ease of scaling up.<n>It is composed of three unified operations: task self-attention, sensor cross-attention, temporal cross-attention.<n>It achieves state-of-the-art performance in both simulated closed-loop benchmark Bench2Drive and real world open-loop benchmark nuScenes with high FPS.
  arXiv  Detail & Related papers  (2025-03-07T11:41:18Z)
• GPD-1: Generative Pre-training for Driving [77.06803277735132]
  We propose a unified Generative Pre-training for Driving (GPD-1) model to accomplish all these tasks.<n>We represent each scene with ego, agent, and map tokens and formulate autonomous driving as a unified token generation problem.<n>Our GPD-1 successfully generalizes to various tasks without finetuning, including scene generation, traffic simulation, closed-loop simulation, map prediction, and motion planning.
  arXiv  Detail & Related papers  (2024-12-11T18:59:51Z)
• ComDrive: Comfort-Oriented End-to-End Autonomous Driving [29.635377468912534]
  ComDrive is a comfort-oriented end-to-end autonomous driving system.<n>It generates temporally consistent and comfortable trajectories.<n>ComDrive achieves state-of-the-art performance in both comfort and safety.
  arXiv  Detail & Related papers  (2024-10-07T14:06:16Z)
• DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving [55.53171248839489]
  We propose an ego-centric fully sparse paradigm, named DiFSD, for end-to-end self-driving.<n>Specifically, DiFSD mainly consists of sparse perception, hierarchical interaction and iterative motion planner.<n>Experiments conducted on nuScenes and Bench2Drive datasets demonstrate the superior planning performance and great efficiency of DiFSD.
  arXiv  Detail & Related papers  (2024-09-15T15:55:24Z)
• Policy Pre-training for End-to-end Autonomous Driving via Self-supervised Geometric Modeling [96.31941517446859]
  We propose PPGeo (Policy Pre-training via Geometric modeling), an intuitive and straightforward fully self-supervised framework curated for the policy pretraining in visuomotor driving. We aim at learning policy representations as a powerful abstraction by modeling 3D geometric scenes on large-scale unlabeled and uncalibrated YouTube driving videos. In the first stage, the geometric modeling framework generates pose and depth predictions simultaneously, with two consecutive frames as input. In the second stage, the visual encoder learns driving policy representation by predicting the future ego-motion and optimizing with the photometric error based on current visual observation only.
  arXiv  Detail & Related papers  (2023-01-03T08:52:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.