Institution profile

MAN Truck & Bus SE

Industry researcheurope · de
Official website
Research library2linked papers
Opportunities0open roles
Selected work

Representative Papers

Multi-View In-Cabin Monitoring System for Public Transport Vehicles

Jun 10, 2026

This work addresses the lack of synchronized, well-annotated multi-view RGB-D and LiDAR datasets in public transit cabins, which has hindered research on occupant state understanding and 3D perception. To bridge this gap, we present the first multimodal, synchronized dataset specifically designed for bus interiors, integrating four RGB-D cameras and a rotating LiDAR sensor. The dataset comprises 9,136 meticulously annotated samples and is accompanied by a complete pipeline including sensor calibration, end-to-end pseudo-label generation, and conversion to the nuScenes format. It enables training and evaluation of state-of-the-art multi-view 3D detection models such as Lift-Splat-Shoot and BEVFusion, significantly advancing research and applications in high-precision 3D human pose estimation and oriented bounding box prediction within cabin environments.

0 citationsRead paper

Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design

May 19, 2026

This work addresses the frequent lack of physical plausibility in CAD designs generated by large language models, which often fail to meet engineering reliability standards. To overcome this limitation, the authors propose a hybrid agent-physical architecture that, for the first time, deeply integrates explicit physics-based validation into the decision-making loop of generative CAD agents. The approach employs an iterative pipeline of planning, generation, evaluation, and revision, combining a large language model–driven multi-agent system with knowledge engineering tools to enable structural simulation and verification. Experimental results demonstrate that the proposed method yields designs with 4.2× higher structural complexity and a 3.5% improvement in compilation success rate. The authors have open-sourced the code, prompts, and dataset to support reproducible research.

0 citationsRead paper
Recent publications

Latest Papers

Multi-View In-Cabin Monitoring System for Public Transport Vehicles

Jun 10, 2026

This work addresses the lack of synchronized, well-annotated multi-view RGB-D and LiDAR datasets in public transit cabins, which has hindered research on occupant state understanding and 3D perception. To bridge this gap, we present the first multimodal, synchronized dataset specifically designed for bus interiors, integrating four RGB-D cameras and a rotating LiDAR sensor. The dataset comprises 9,136 meticulously annotated samples and is accompanied by a complete pipeline including sensor calibration, end-to-end pseudo-label generation, and conversion to the nuScenes format. It enables training and evaluation of state-of-the-art multi-view 3D detection models such as Lift-Splat-Shoot and BEVFusion, significantly advancing research and applications in high-precision 3D human pose estimation and oriented bounding box prediction within cabin environments.

0 citationsRead paper

Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design

May 19, 2026

This work addresses the frequent lack of physical plausibility in CAD designs generated by large language models, which often fail to meet engineering reliability standards. To overcome this limitation, the authors propose a hybrid agent-physical architecture that, for the first time, deeply integrates explicit physics-based validation into the decision-making loop of generative CAD agents. The approach employs an iterative pipeline of planning, generation, evaluation, and revision, combining a large language model–driven multi-agent system with knowledge engineering tools to enable structural simulation and verification. Experimental results demonstrate that the proposed method yields designs with 4.2× higher structural complexity and a 3.5% improvement in compilation success rate. The authors have open-sourced the code, prompts, and dataset to support reproducible research.

0 citationsRead paper