pith. sign in

arxiv: 2405.01533 · v2 · pith:VQKJLIF2new · submitted 2024-05-02 · 💻 cs.CV

OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning

classification 💻 cs.CV
keywords reasoningvision-languagedatasetdrivingautonomouscapabilitiescounterfactualholistic
0
0 comments X
read the original abstract

The advances in vision-language models (VLMs) have led to a growing interest in autonomous driving to leverage their strong reasoning capabilities. However, extending these capabilities from 2D to full 3D understanding is crucial for real-world applications. To address this challenge, we propose OmniDrive, a holistic vision-language dataset that aligns agent models with 3D driving tasks through counterfactual reasoning. This approach enhances decision-making by evaluating potential scenarios and their outcomes, similar to human drivers considering alternative actions. Our counterfactual-based synthetic data annotation process generates large-scale, high-quality datasets, providing denser supervision signals that bridge planning trajectories and language-based reasoning. Futher, we explore two advanced OmniDrive-Agent frameworks, namely Omni-L and Omni-Q, to assess the importance of vision-language alignment versus 3D perception, revealing critical insights into designing effective LLM-agents. Significant improvements on the DriveLM Q\&A benchmark and nuScenes open-loop planning demonstrate the effectiveness of our dataset and methods.

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 21 Pith papers

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

  1. Steadily moving semi-infinite fracture in plane poroelasticity

    physics.geo-ph 2026-04 unverdicted novelty 7.0

    A new coupled boundary integral method models steadily moving semi-infinite fractures in plane poroelasticity, solving for mechanical deformation and fluid exchange with verification on analytical test cases.

  2. NuRisk: A Visual Question Answering Dataset for Agent-Level Risk Assessment in Autonomous Driving

    cs.AI 2025-09 conditional novelty 7.0

    NuRisk is a new VQA dataset for agent-level risk assessment in autonomous driving that benchmarks VLMs at 33% peak accuracy and shows a fine-tuned 7B model reaching 41% with 75% lower latency.

  3. AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning

    cs.CV 2025-03 unverdicted novelty 7.0

    AlphaDrive uses GRPO-based RL rewards and two-stage SFT+RL training on VLMs to improve autonomous driving planning performance and efficiency while producing emergent multimodal capabilities.

  4. Teaching Vision-Language-Action Models What to See and Where to Look

    cs.CV 2026-07 unverdicted novelty 6.0

    DriveTeach-VLA adds Driving-aware Vision Distillation pretraining and 2D Trajectory-Guided Prompts to VLA models, then reports state-of-the-art results on NAVSIM and nuScenes.

  5. What's Hidden Matters: Identifying Planning-Critical Occluded Agents using Vision-Language Models

    cs.RO 2026-07 unverdicted novelty 6.0

    Introduces PKL to rank planning-critical occluded agents, creates a VLM-annotated benchmark on nuScenes, and shows fine-tuning on this data improves performance ~30% over random selection with smaller models outperfor...

  6. Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents

    cs.PL 2026-06 unverdicted novelty 6.0

    FCGraft synthesizes code policies for embodied agents by grafting KV caches from a library of validated functions, claiming 18.31% higher success rate and 2.3x faster synthesis than prompt-level caching.

  7. Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Driving

    cs.CV 2026-06 unverdicted novelty 6.0

    Envision4D presents a feed-forward 4D Gaussian Splatting framework with future pose prediction, temporal attention, and conditioned motion lifting for pose-free extrapolation in autonomous driving scenes.

  8. OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models

    cs.CV 2026-04 unverdicted novelty 6.0

    OneDrive unifies heterogeneous decoding in a single VLM transformer decoder for end-to-end driving, achieving 0.28 L2 error and 0.18 collision rate on nuScenes plus 86.8 PDMS on NAVSIM.

  9. FeaXDrive: Feasibility-aware Trajectory-Centric Diffusion Planning for End-to-End Autonomous Driving

    cs.RO 2026-04 unverdicted novelty 6.0

    FeaXDrive improves end-to-end autonomous driving by shifting diffusion planning to a trajectory-centric formulation with curvature-constrained training, drivable-area guidance, and GRPO post-training, yielding stronge...

  10. AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning

    cs.CV 2025-06 unverdicted novelty 6.0

    AutoVLA unifies semantic reasoning and trajectory planning in one autoregressive VLA model for end-to-end autonomous driving by tokenizing trajectories into discrete actions and using GRPO reinforcement fine-tuning to...

  11. VERDI: VLM-Embedded Reasoning for Autonomous Driving

    cs.RO 2025-05 conditional novelty 6.0

    VERDI aligns perception, prediction, and planning outputs of end-to-end AD models with VLM-generated text features at training time to embed structured reasoning, yielding up to 11% better l2 distance and 10% higher n...

  12. EMMA: End-to-End Multimodal Model for Autonomous Driving

    cs.CV 2024-10 unverdicted novelty 6.0

    EMMA is an end-to-end multimodal LLM that converts camera data into trajectories, objects, and road graphs via text prompts and reports state-of-the-art motion planning on nuScenes plus competitive detection results on Waymo.

  13. Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving

    cs.CV 2024-10 conditional novelty 6.0

    Senna decouples language-based high-level planning from an LVLM with low-level trajectory prediction from an E2E model, reporting 27% lower planning error and 33% lower collisions after pre-training on DriveX and fine...

  14. Enhancing End-to-End Autonomous Driving with Latent World Model

    cs.CV 2024-06 accept novelty 6.0

    LAW introduces a self-supervised prediction task on latent scene features that boosts end-to-end driving performance on nuScenes, NAVSIM, and CARLA benchmarks.

  15. MAGNIFIED: RL Fine-tuning of Multimodal Large Language Models for Motion Planning

    cs.RO 2026-06 unverdicted novelty 5.0

    MAGNIFIED applies RL fine-tuning to MLLMs for autonomous driving motion planning, yielding over 10.5% lower overlap rate and 38.9% lower off-road rate than SFT baseline on Waymo Open Motion Dataset.

  16. Pedestrian-Aware LLM-Driven Behavioral Planning for Autonomous Vehicles

    cs.RO 2026-05 unverdicted novelty 5.0

    LLM-driven behavioral planning for AVs reaches 68% zero-shot collision-free success in pedestrian scenarios, outperforming deep RL baselines at 17.7% and improving to 96% with few-shot memory.

  17. SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model

    cs.CV 2026-04 unverdicted novelty 5.0

    SpanVLA reduces action generation latency via flow-matching conditioned on history and improves robustness by training on negative-recovery samples with GRPO and a dedicated reasoning dataset.

  18. Steadily moving semi-infinite fracture in plane poroelasticity

    physics.geo-ph 2026-04 conditional novelty 5.0

    XEmbodied achieves SOTA on 18 embodied VQA benchmarks by fusing 3D geometric tokens and distilled physical cues into a 30B VLM with progressive curriculum training.

  19. DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving

    cs.CV 2026-05 unverdicted novelty 4.0

    DeepSight uses parallel latent feature prediction in BEV for long-horizon world modeling and adaptive text reasoning to reach state-of-the-art closed-loop performance on the Bench2drive benchmark.

  20. XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments

    cs.CV 2026-04 unverdicted novelty 4.0

    XEmbodied is a foundation model that integrates 3D geometric and physical signals into VLMs using a 3D Adapter and Efficient Image-Embodied Adapter, plus progressive curriculum and RL post-training, to improve spatial...

  21. Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey

    cs.CV 2025-03 unverdicted novelty 2.0

    The paper provides the first comprehensive survey of multimodal chain-of-thought reasoning, including foundational concepts, a taxonomy of methodologies, application analyses, challenges, and future directions.