REVIEW 8 cited by
Gen-Drive: Enhancing Diffusion Generative Driving Policies with Reward Modeling and Reinforcement Learning Fine-tuning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Autonomous driving necessitates the ability to reason about future interactions between traffic agents and to make informed evaluations for planning. This paper introduces the \textit{Gen-Drive} framework, which shifts from the traditional prediction and deterministic planning framework to a generation-then-evaluation planning paradigm. The framework employs a behavior diffusion model as a scene generator to produce diverse possible future scenarios, thereby enhancing the capability for joint interaction reasoning. To facilitate decision-making, we propose a scene evaluator (reward) model, trained with pairwise preference data collected through VLM assistance, thereby reducing human workload and enhancing scalability. Furthermore, we utilize an RL fine-tuning framework to improve the generation quality of the diffusion model, rendering it more effective for planning tasks. We conduct training and closed-loop planning tests on the nuPlan dataset, and the results demonstrate that employing such a generation-then-evaluation strategy outperforms other learning-based approaches. Additionally, the fine-tuned generative driving policy shows significant enhancements in planning performance. We further demonstrate that utilizing our learned reward model for evaluation or RL fine-tuning leads to better planning performance compared to relying on human-designed rewards. Project website: https://mczhi.github.io/GenDrive.
Forward citations
Cited by 8 Pith papers
-
RDPO: Real Data Preference Optimization for Physics Consistency Video Generation
RDPO builds preference pairs by reverse-sampling real video latents with a pre-trained generator, then fine-tunes with Flow-DPO, improving physics consistency metrics on two video models.
-
Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs
Hiding future trajectory information until after a driving model forms its decision reduces rationalization and improves verifiable autonomous-driving reasoning in the proposed AD-MCQ and DEFT-RLVR framework.
-
Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving
R2SE refines pretrained end-to-end driving policies on hard cases via residual LoRA reinforcement learning and switches between specialist and generalist policies using GPD-based uncertainty.
-
Autoregressive Meta-Actions for Unified Controllable Trajectory Generation
Frame-level meta-actions, predicted and injected at every time step in an autoregressive trajectory model, improve alignment between high-level driving decisions and generated motion.
-
Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling
By replacing group normalization in GRPO with fixed scaling, Plan-R1 keeps safety violations dominant in the learning signal and achieves state-of-the-art reactive planning scores on nuPlan.
-
Pulse Breathing Dynamics in a Mode-Locked Laser measured via SHG autocorrelation
A statistical SHG-autocorrelation Fano analysis is claimed to expose pulse breathing and measure ~3 fs pulse-width fluctuations on two commercial mode-locked lasers.
-
DriveMRP: Enhancing Vision-Language Models with Synthetic Motion Data for Motion Risk Prediction
A synthetic dataset and visual prompting framework improve VLM-based driving risk prediction, with the main evidence coming from an unreleased private test set.
-
A Review of Learning-Based Motion Planning: Toward a Data-Driven Optimal Control Approach
A position/review paper argues data-driven model predictive control is the best route to safe, adaptive, human-like autonomous-driving motion planning, but provides no new derivation or experiment.
Discussion (0). Sign in to comment.