AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

RoboTron-Sim: Improving Real-World Driving via Simulated Hard-Case

Baihui Xiao, Chengjian Feng, Zhijian Huang, Feng Yan, Yujie Zhong, Lin Ma

ICCV 2025 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Data-driven traffic simulation · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Scenario-aware Prompt Engineering (SPE) (ablation)LLaVA-OneVision driving baseline · nuScenes planning ablation (no ego pose)collision rate (%): 0.94 -> 0.79Improved
add Scenario-aware Prompt Engineering (SPE) (ablation)LLaVA-OneVision driving baseline · nuScenes planning ablation (no ego pose)boundary violation rate (%): 3.22 -> 2.68Improved
add Scenario-aware Prompt Engineering (SPE) (ablation)LLaVA-OneVision driving baseline · nuScenes planning ablation (no ego pose)L2 (m): 0.91 -> 0.86Improved
add Image-to-Ego (I2E) Encoder (ablation)RoboTron-Sim with SPE · nuScenes planning ablation (no ego pose)L2 (m): 0.86 -> 0.56Improved
add Image-to-Ego (I2E) Encoder (ablation)RoboTron-Sim with SPE · nuScenes planning ablation (no ego pose)collision rate (%): 0.79 -> 0.58Improved
add Image-to-Ego (I2E) Encoder (ablation)RoboTron-Sim with SPE · nuScenes planning ablation (no ego pose)boundary violation rate (%): 2.68 -> 3.02Hurt
add HASS simulated data to nuScenesRoboTron-Sim · H2D scenarios (L2)L2 (m) turn: 1.32 -> 0.64Improved
add HASS simulated data to nuScenesRoboTron-Sim · H2D scenarios (night)collision rate (%): 2.71 -> 1.56Improved
add HASS simulated data to nuScenesVAD · E2D and H2D scenariosL2 (m): 0.94 -> 0.93No clear effect
add HASS simulated data to nuScenesMLLM baseline · H2D scenariosL2 (m) rainy: 1.15 -> 0.90Improved
use hard-case HASS instead of distribution-matched GASS synthetic data (ablation)RoboTron-Sim · H2D scenariosL2 (m) night: 1.00 -> 0.81Improved
use hard-case HASS instead of distribution-matched GASS synthetic data (ablation)RoboTron-Sim · H2D scenariosL2 (m) turn: 1.21 -> 0.64Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy