Pith

open record

sign in

arxiv: 2412.09647 · v1 · pith:RD6HWTRA · submitted 2024-12-11 · cs.RO · cs.CV· cs.LG

Bench2Drive-R: Turning Real World Data into Reactive Closed-Loop Autonomous Driving Benchmark by Generative Model

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:RD6HWTRArecord.jsonopen to challenge →

classification cs.RO cs.CVcs.LG
keywords generativebench2drive-rclosed-loopevaluationexistingreactivesimulationagents
0
0 comments X
read the original abstract

For end-to-end autonomous driving (E2E-AD), the evaluation system remains an open problem. Existing closed-loop evaluation protocols usually rely on simulators like CARLA being less realistic; while NAVSIM using real-world vision data, yet is limited to fixed planning trajectories in short horizon and assumes other agents are not reactive. We introduce Bench2Drive-R, a generative framework that enables reactive closed-loop evaluation. Unlike existing video generative models for AD, the proposed designs are tailored for interactive simulation, where sensor rendering and behavior rollout are decoupled by applying a separate behavioral controller to simulate the reactions of surrounding agents. As a result, the renderer could focus on image fidelity, control adherence, and spatial-temporal coherence. For temporal consistency, due to the step-wise interaction nature of simulation, we design a noise modulating temporal encoder with Gaussian blurring to encourage long-horizon autoregressive rollout of image sequences without deteriorating distribution shifts. For spatial consistency, a retrieval mechanism, which takes the spatially nearest images as references, is introduced to to ensure scene-level rendering fidelity during the generation process. The spatial relations between target and reference are explicitly modeled with 3D relative position encodings and the potential over-reliance of reference images is mitigated with hierarchical sampling and classifier-free guidance. We compare the generation quality of Bench2Drive-R with existing generative models and achieve state-of-the-art performance. We further integrate Bench2Drive-R into nuPlan and evaluate the generative qualities with closed-loop simulation results. We will open source our code.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulation

    cs.CV 2026-07 conditional novelty 6.0

    Point-cloud skeleton conditions and a Reset-and-Roll inference scheme enable stable frame-wise autoregressive driving video generation for closed-loop autonomous driving simulation.

  2. Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous Driving

    cs.RO 2026-04 unverdicted novelty 6.0

    Sim2Real-AD enables zero-shot transfer of CARLA-trained VLM-guided RL policies to full-scale vehicles, reporting 75-90% success rates in car-following, obstacle avoidance, and stop-sign scenarios without real-world RL...

  3. SimScale: Learning to Drive via Real-World Simulation at Scale

    cs.CV 2025-11 conditional novelty 6.0

    SimScale synthesizes unseen driving states from real logs via neural rendering and reactive environments, generates pseudo-expert trajectories, and shows that co-training on real plus simulated data improves planning ...

  4. ReSim: Reliable World Simulation for Autonomous Driving

    cs.CV 2025-06 unverdicted novelty 6.0

    ReSim is a controllable video world model trained on heterogeneous real and simulated driving data that achieves higher fidelity and controllability for both expert and non-expert actions, plus a Video2Reward module f...

  5. DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving

    cs.CV 2025-05 unverdicted novelty 6.0

    DriveMoE applies scene-specialized Vision MoE and skill-specialized Action MoE to a VLA baseline to achieve SOTA closed-loop performance on Bench2Drive.

  6. Dreaming Across Towns: Semantic Rollout and Town-Adversarial Regularization for Zero-Shot Held-Out-Town Fixed-Route Driving in CARLA

    cs.RO 2026-04 unverdicted novelty 5.0

    Semantic rollout prediction plus town-adversarial regularization on a Dreamer agent raises mean zero-shot success rate for fixed-route driving across held-out CARLA towns under fixed weather and no traffic.

  7. Dreaming Across Towns: Semantic Rollout and Town-Adversarial Regularization for Zero-Shot Held-Out-Town Fixed-Route Driving in CARLA

    cs.RO 2026-04 unverdicted novelty 5.0

    Semantic rollout plus town-adversarial regularization raises zero-shot success in held-out CARLA towns to 36.6% and 85.6% versus matched DreamerV3 baselines.