# DRAMA-X: A Fine-grained Intent Prediction and Risk Reasoning Benchmark For Driving

arXiv: https://arxiv.org/abs/2506.17590 · HTML: https://mlsanity.com/paper/2506.17590/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Chain-of-thought reasoning for driving, one of 17 directions in LLM reasoning.
- Builds on 21 of its 66 references that are in the map.
- First posted on arXiv 21 Jun 2025.

## Placed in

- LLM reasoning / [Chain-of-thought reasoning for driving](https://mlsanity.com/lr/chain-of-thought-reasoning-for-driving/)
- End-to-end autonomous driving / [VLMs for autonomous driving](https://mlsanity.com/driving/vlms-for-autonomous-driving/)

## Builds on (most cited first, 21 of 21)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [GPT-Driver: Learning to Drive with GPT](https://mlsanity.com/paper/2310.01415/) (2023)
- [Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models](https://mlsanity.com/paper/2409.17146/) (2024)
- [BoT-SORT: Robust Associations Multi-Pedestrian Tracking](https://mlsanity.com/paper/2206.14651/) (2022)
- [Compositional Chain-of-Thought Prompting for Large Multimodal Models](https://mlsanity.com/paper/2311.17076/) (2023)
- [Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving](https://mlsanity.com/paper/2410.22313/) (2024)
- [NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples](https://mlsanity.com/paper/2410.14669/) (2024)
- [V2X-VLM: End-to-End V2X Cooperative Autonomous Driving Through Large Vision-Language Models](https://mlsanity.com/paper/2408.09251/) (2024)
- [AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving](https://mlsanity.com/paper/2412.15206/) (2024)
- [WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving](https://mlsanity.com/paper/2407.04281/) (2024)
- [SimpleLLM4AD: An End-to-End Vision-Language Model with Graph Visual Question Answering for Autonomous Driving](https://mlsanity.com/paper/2407.21293/) (2024)
- [V2X-UniPool: Unifying Multimodal Perception and Knowledge Reasoning for Autonomous Driving](https://mlsanity.com/paper/2506.02580/) (2025)
- [Using Multimodal Large Language Models for Automated Detection of Traffic Safety Critical Events](https://mlsanity.com/paper/2406.13894/) (2024)
- [Generative AI for Autonomous Driving: Frontiers and Opportunities](https://mlsanity.com/paper/2505.08854/) (2025)
- [PRISM-0: A Predicate-Rich Scene Graph Generation Framework for Zero-Shot Open-Vocabulary Tasks](https://mlsanity.com/paper/2504.00844/) (2025)
- [Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happen](https://mlsanity.com/paper/2505.21743/) (2025)
- [End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting](https://mlsanity.com/paper/2409.12499/) (2024)
- [IRS-Assisted Active Device Detection](https://mlsanity.com/paper/2105.04149/) (2021)

## Built on by (most cited first, 5 of 5)

- [Bench2Drive-VL: Benchmarks for Closed-Loop Autonomous Driving with Vision-Language Models](https://mlsanity.com/paper/2604.01259/) (2026)
- [Automated Vehicles Should be Connected with Natural Language](https://mlsanity.com/paper/2507.01059/) (2025)
- [A knowledge-augmented dataset of high-risk driving scenarios with LLM annotations for autonomous driving](https://mlsanity.com/paper/2607.07103/) (2026)
- [SafeCoop: Unravelling Full Stack Safety in Agentic Collaborative Driving](https://mlsanity.com/paper/2510.18123/) (2025)
- [Neuro-Symbolic Drive: Rule-Grounded Faithful Reasoning for Driving VLAs](https://mlsanity.com/paper/2606.23938/) (2026)

## Abstract (arXiv)

Understanding the short-term motion of vulnerable road users (VRUs) like pedestrians and cyclists is critical for safe autonomous driving, especially in urban scenarios with ambiguous or high-risk behaviors. While vision-language models (VLMs) have enabled open-vocabulary perception, their utility for fine-grained intent reasoning remains underexplored. Notably, no existing benchmark evaluates multi-class intent prediction in safety-critical situations, To address this gap, we introduce DRAMA-X, a fine-grained benchmark constructed from the DRAMA dataset via an automated annotation pipeline. DRAMA-X contains 5,686 accident-prone frames labeled with object bounding boxes, a nine-class directional intent taxonomy, binary risk scores, expert-generated action suggestions for the ego vehicle, and descriptive motion summaries. These annotations enable a structured evaluation of four interrelated tasks central to autonomous decision-making: object detection, intent prediction, risk assessment, and action suggestion. As a reference baseline, we propose SGG-Intent, a lightweight, training-free framework that mirrors the ego vehicle's reasoning pipeline. It sequentially generates a scene graph from visual input using VLM-backed detectors, infers intent, assesses risk, and recommends an action using a compositional reasoning stage powered by a large language model. We evaluate a range of recent VLMs, comparing performance across all four DRAMA-X tasks. Our experiments demonstrate that scene-graph-based reasoning enhances intent prediction and risk assessment, especially when contextual cues are explicitly modeled.