Yu Hou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yu Hou has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Lucio Soibelman
University of Southern California
4 shared publications - Rebekka Volk
Institute for Industrial Production (IIP), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany
4 shared publications - Baixiao Huang
Independent Researcher 7200 Bollinger Rd Apt 516 95129 CA
2 shared publications - Baiyu Huang
Independent Researcher 16506 82nd Pl NE 98028 Kenmore WA
2 shared publications - James Kahn
Helmholtz AI, Scientific Computing Centre, Karlsruhe Institute of Technology, Karlsruhe, Germany
2 shared publications Mario Bergés
2 shared publications
Latest Publications
- Open Access
- 22 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 374-384
Scan2UBEM: An AI-driven End-to-End Pipeline Towards Automated Urban Building Energy Modeling from 3D Scans
- 22 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 374-384
Open AccessScan2UBEM: An AI-driven End-to-End Pipeline Towards Automated Urban Building Energy Modeling from 3D Scans
- Open Access
Learning Transferability: A Two-Stage Reinforcement Learning Approach for Enhancing Quadruped Robots' Performance in U-Shaped Stair Climbing
Quadruped robots are employed in various scenarios in building construction. However, autonomous stair climbing across different indoor staircases remains a major challenge for robot dogs to complete building construction tasks. In this project, we employed a two-stage end-to-end deep reinforcement learning (RL) approach to optimize a robot's performance on U-shaped stairs. The training robot-dog modality, Unitree Go2, was first trained to climb stairs on Isaac Lab's pyramid-stair terrain, and then to climb a U-shaped indoor staircase using the learned policies. This project explores end-to-end RL methods that enable robot dogs to autonomously climb stairs. The results showed (1) the successful goal reached for robot dogs climbing U-shaped stairs with a stall penalty, and (2) the transferability from the policy trained on U-shaped stairs to deployment on straight, L-shaped, and spiral stair terrains, and transferability from other stair models to deployment on U-shaped terrain.
Open AccessLearning Transferability: A Two-Stage Reinforcement Learning Approach for Enhancing Quadruped Robots' Performance in U-Shaped Stair Climbing
Quadruped robots are employed in various scenarios in building construction. However, autonomous stair climbing across different indoor staircases remains a major challenge for robot dogs to complete building construction tasks. In this project, we employed a two-stage end-to-end deep reinforcement learning (RL) approach to optimize a robot's performance on U-shaped stairs. The training robot-dog modality, Unitree Go2, was first trained to climb stairs on Isaac Lab's pyramid-stair terrain, and then to climb a U-shaped indoor staircase using the learned policies. This project explores end-to-end RL methods that enable robot dogs to autonomously climb stairs. The results showed (1) the successful goal reached for robot dogs climbing U-shaped stairs with a stall penalty, and (2) the transferability from the policy trained on U-shaped stairs to deployment on straight, L-shaped, and spiral stair terrains, and transferability from other stair models to deployment on U-shaped terrain.
- Open Access
Training and Simulation of Quadrupedal Robot in Adaptive Stair Climbing for Indoor Firefighting: An End-to-End Reinforcement Learning Approach
Quadruped robots are used for primary searches during the early stages of indoor fires. A typical primary search involves quickly and thoroughly looking for victims under hazardous conditions and monitoring flammable materials. However, situational awareness in complex indoor environments and rapid stair climbing across different staircases remain the main challenges for robot-assisted primary searches. In this project, we designed a two-stage end-to-end deep reinforcement learning (RL) approach to optimize both navigation and locomotion. In the first stage, the quadrupeds, Unitree Go2, were trained to climb stairs in Isaac Lab's pyramid-stair terrain. In the second stage, the quadrupeds were trained to climb various realistic indoor staircases in the Isaac Lab engine, with the learned policy transferred from the previous stage. These indoor staircases are straight, L-shaped, and spiral, to support climbing tasks in complex environments. This project explores how to balance navigation and locomotion and how end-to-end RL methods can enable quadrupeds to adapt to different stair shapes. Our main contributions are: (1) A two-stage end-to-end RL framework that transfers stair-climbing skills from abstract pyramid terrain to realistic indoor stair topologies. (2) A centerline-based navigation formulation that enables unified learning of navigation and locomotion without hierarchical planning. (3) Demonstration of policy generalization across diverse staircases using only local height-map perception. (4) An empirical analysis of success, efficiency, and failure modes under increasing stair difficulty.
Open AccessTraining and Simulation of Quadrupedal Robot in Adaptive Stair Climbing for Indoor Firefighting: An End-to-End Reinforcement Learning Approach
Quadruped robots are used for primary searches during the early stages of indoor fires. A typical primary search involves quickly and thoroughly looking for victims under hazardous conditions and monitoring flammable materials. However, situational awareness in complex indoor environments and rapid stair climbing across different staircases remain the main challenges for robot-assisted primary searches. In this project, we designed a two-stage end-to-end deep reinforcement learning (RL) approach to optimize both navigation and locomotion. In the first stage, the quadrupeds, Unitree Go2, were trained to climb stairs in Isaac Lab's pyramid-stair terrain. In the second stage, the quadrupeds were trained to climb various realistic indoor staircases in the Isaac Lab engine, with the learned policy transferred from the previous stage. These indoor staircases are straight, L-shaped, and spiral, to support climbing tasks in complex environments. This project explores how to balance navigation and locomotion and how end-to-end RL methods can enable quadrupeds to adapt to different stair shapes. Our main contributions are: (1) A two-stage end-to-end RL framework that transfers stair-climbing skills from abstract pyramid terrain to realistic indoor stair topologies. (2) A centerline-based navigation formulation that enables unified learning of navigation and locomotion without hierarchical planning. (3) Demonstration of policy generalization across diverse staircases using only local height-map perception. (4) An empirical analysis of success, efficiency, and failure modes under increasing stair difficulty.
- 28 January 2026
- Published by American Society of Civil Engineers (ASCE)
- p. 1000-1009
Analysis of Drone-Assisted Building Inspection Training in VR vs. 2D Monitor Display: An EEG Study
- 28 January 2026
- Published by American Society of Civil Engineers (ASCE)
- p. 1000-1009
Analysis of Drone-Assisted Building Inspection Training in VR vs. 2D Monitor Display: An EEG Study
- 1 September 2025
- Published by SAGE Publications in Proceedings of the Human Factors and Ergonomics Society Annual Meeting
- Vol. 69 (1) , 58-65
Comparing Neural Correlates of Drone Operations in Virtual Reality and 2D Monitor
The aim of this study is to investigate the neural correlates during drone control in both VR and 2D monitor conditions. A total of eight participants were instructed to control a drone and perform a heat loss detection task using either VR or a 2D monitor. Electroencephalogram (EEG) signals were recorded and subsequently analyzed using the dynamic causal modeling (DCM) method. By comparing the laterality and the direction of causal connections derived from DCM analysis, the key role of right hemisphere dorsolateral prefrontal cortex (dlPFC) was identified during presence sensing under the VR condition. The results from this preliminary study may be utilized in applications of the augmented cognition program as they provide the basis for monitoring and evaluating the engagement of users.
- 1 September 2025
- Published by SAGE Publications in Proceedings of the Human Factors and Ergonomics Society Annual Meeting
- Vol. 69 (1) , 58-65
Comparing Neural Correlates of Drone Operations in Virtual Reality and 2D Monitor
The aim of this study is to investigate the neural correlates during drone control in both VR and 2D monitor conditions. A total of eight participants were instructed to control a drone and perform a heat loss detection task using either VR or a 2D monitor. Electroencephalogram (EEG) signals were recorded and subsequently analyzed using the dynamic causal modeling (DCM) method. By comparing the laterality and the direction of causal connections derived from DCM analysis, the key role of right hemisphere dorsolateral prefrontal cortex (dlPFC) was identified during presence sensing under the VR condition. The results from this preliminary study may be utilized in applications of the augmented cognition program as they provide the basis for monitoring and evaluating the engagement of users.
- Open Access
Analysis of Drone-Assisted Building Inspection Training in VR vs 2D Monitor Display: an EEG Study
Researchers have been using simulation-based methods for drone-assisted inspection training. Multiple brain regions are associated with information processes and decision-making, and the connectivity of these regions may further influence inspectors' performance. However, researchers do not understand the pathways of the information flows when drone pilots process the maintenance and manipulation of information, which may affect the efficiency of tacit knowledge transfer. This study aims to reveal the causal connection between participants' brain regions using an electroencephalogram and dynamic causal modeling when processing drone-assisted building energy audit tasks using different display modalities. The results showed similar single-direction connectivity patterns for the different simulation groups. The results also showed similar patterns between brain regions related to visual inspection performance before and after training. These findings highlight the nature of brain asymmetries and may be utilized in measuring cognitive states and designing adaptive automation in the knowledge transfer of drone-based inspection.
Open AccessAnalysis of Drone-Assisted Building Inspection Training in VR vs 2D Monitor Display: an EEG Study
Researchers have been using simulation-based methods for drone-assisted inspection training. Multiple brain regions are associated with information processes and decision-making, and the connectivity of these regions may further influence inspectors' performance. However, researchers do not understand the pathways of the information flows when drone pilots process the maintenance and manipulation of information, which may affect the efficiency of tacit knowledge transfer. This study aims to reveal the causal connection between participants' brain regions using an electroencephalogram and dynamic causal modeling when processing drone-assisted building energy audit tasks using different display modalities. The results showed similar single-direction connectivity patterns for the different simulation groups. The results also showed similar patterns between brain regions related to visual inspection performance before and after training. These findings highlight the nature of brain asymmetries and may be utilized in measuring cognitive states and designing adaptive automation in the knowledge transfer of drone-based inspection.
- 5 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
ImmersiveBuild: The Applications of Virtual Reality and Treadmills for the Renovation of Educational Buildings
With school renovations, upgrades to classroom layouts can help students learn more efficiently. However, the traditional requests for information from building occupants, such as students, staff, and faculty members, are based on 2D drawings or 3D models. Occupants may not understand blueprints or express their true feelings. They need to experience the environment and provide feedback about the renovation plans. This research combined Virtual Reality (VR) software and all-directional treadmill hardware to build an ImmersiveBuild platform for participants to sense the environment and evaluate the renovation plans. Our experiments show that the walk-through virtual environment influenced participants' decisions, and participants' physiological data records, such as the heartbeat rate, indicated their involvement and immersion. The ImmersiveBuild has a potential application for future architecture and construction industries in communicating with building occupants to collect feedback on renovation designs.
- 5 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
ImmersiveBuild: The Applications of Virtual Reality and Treadmills for the Renovation of Educational Buildings
With school renovations, upgrades to classroom layouts can help students learn more efficiently. However, the traditional requests for information from building occupants, such as students, staff, and faculty members, are based on 2D drawings or 3D models. Occupants may not understand blueprints or express their true feelings. They need to experience the environment and provide feedback about the renovation plans. This research combined Virtual Reality (VR) software and all-directional treadmill hardware to build an ImmersiveBuild platform for participants to sense the environment and evaluate the renovation plans. Our experiments show that the walk-through virtual environment influenced participants' decisions, and participants' physiological data records, such as the heartbeat rate, indicated their involvement and immersion. The ImmersiveBuild has a potential application for future architecture and construction industries in communicating with building occupants to collect feedback on renovation designs.
- 5 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-2
Gaussian Splatting-Based Thermographic Modeling for Building Envelope Energy Audits
Thermographic modeling is essential for facility managers to conduct energy audits for building envelopes and make retrofitting decisions. However, current thermal images have a lower resolution, resulting in low-quality modeling results. Therefore, we proposed this Gaussian Splatting-based thermographic modeling approach to assist facility managers in visualizing heat loss from building envelopes, conducting building inspection workforce training, and making building renovation decisions. Our framework adapted the Gaussian Splatting pipeline by adding thermal channels to the original Gaussian's 3D position, scale, rotation, transparency, and spherical harmonics. We used a campus building façade as a case study and implemented our approach. It shows that the innovative approach has a clearer vision of the thermographic models than existing approaches.
- 5 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-2
Gaussian Splatting-Based Thermographic Modeling for Building Envelope Energy Audits
Thermographic modeling is essential for facility managers to conduct energy audits for building envelopes and make retrofitting decisions. However, current thermal images have a lower resolution, resulting in low-quality modeling results. Therefore, we proposed this Gaussian Splatting-based thermographic modeling approach to assist facility managers in visualizing heat loss from building envelopes, conducting building inspection workforce training, and making building renovation decisions. Our framework adapted the Gaussian Splatting pipeline by adding thermal channels to the original Gaussian's 3D position, scale, rotation, transparency, and spherical harmonics. We used a campus building façade as a case study and implemented our approach. It shows that the innovative approach has a clearer vision of the thermographic models than existing approaches.
- Open Access
- 14 November 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (22) , 4240
An Aerial Photogrammetry Benchmark Dataset for Point Cloud Segmentation and Style Translation
The recent surge in diverse 3D datasets spanning various scales and applications marks a significant advancement in the field. However, the comprehensive process of data acquisition, refinement, and annotation at a large scale poses a formidable challenge, particularly for individual researchers and small teams. To this end, we present a novel synthetic 3D point cloud generation framework that can produce detailed outdoor aerial photogrammetric 3D datasets with accurate ground truth annotations without the labor-intensive and time-consuming data collection/annotation processes. Our pipeline procedurally generates synthetic environments, mirroring real-world data collection and 3D reconstruction processes. A key feature of our framework is its ability to replicate consistent quality, noise patterns, and diversity similar to real-world datasets. This is achieved by adopting UAV flight patterns that resemble those used in real-world data collection processes (e.g., the cross-hatch flight pattern) across various synthetic terrains that are procedurally generated, thereby ensuring data consistency akin to real-world scenarios. Moreover, the generated datasets are enriched with precise semantic and instance annotations, eliminating the need for manual labeling. Our approach has led to the development and release of the Semantic Terrain Points Labeling—Synthetic 3D (STPLS3D) benchmark, an extensive outdoor 3D dataset encompassing over 16 , featuring up to 19 semantic labels. We also collected, reconstructed, and annotated four real-world datasets for validation purposes. Extensive experiments on these datasets demonstrate our synthetic datasets’ effectiveness, superior quality, and their value as a benchmark dataset for further point cloud research.- 14 November 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (22) , 4240
Open AccessAn Aerial Photogrammetry Benchmark Dataset for Point Cloud Segmentation and Style Translation
The recent surge in diverse 3D datasets spanning various scales and applications marks a significant advancement in the field. However, the comprehensive process of data acquisition, refinement, and annotation at a large scale poses a formidable challenge, particularly for individual researchers and small teams. To this end, we present a novel synthetic 3D point cloud generation framework that can produce detailed outdoor aerial photogrammetric 3D datasets with accurate ground truth annotations without the labor-intensive and time-consuming data collection/annotation processes. Our pipeline procedurally generates synthetic environments, mirroring real-world data collection and 3D reconstruction processes. A key feature of our framework is its ability to replicate consistent quality, noise patterns, and diversity similar to real-world datasets. This is achieved by adopting UAV flight patterns that resemble those used in real-world data collection processes (e.g., the cross-hatch flight pattern) across various synthetic terrains that are procedurally generated, thereby ensuring data consistency akin to real-world scenarios. Moreover, the generated datasets are enriched with precise semantic and instance annotations, eliminating the need for manual labeling. Our approach has led to the development and release of the Semantic Terrain Points Labeling—Synthetic 3D (STPLS3D) benchmark, an extensive outdoor 3D dataset encompassing over 16 , featuring up to 19 semantic labels. We also collected, reconstructed, and annotated four real-world datasets for validation purposes. Extensive experiments on these datasets demonstrate our synthetic datasets’ effectiveness, superior quality, and their value as a benchmark dataset for further point cloud research. - 1 April 2024
- Published by American Institute of Aeronautics and Astronautics (AIAA) in Journal of Aerospace Information Systems
- Vol. 21 (4) , 332-347
Digital Twin Technologies for Autonomous Environmental Control and Life Support Systems
Environmental control and life support systems will require enhanced self-awareness and self-sufficiency as human spaceflights are designed to reach further destinations. These requirements have led to the development of autonomous technologies and systems to enable more Earth independence, while at the same time relying more heavily on the knowledge contained in their computational models (as opposed to the knowledge of ground control experts). For environmental control and life support systems, these consist of disparate models often tailored to specific subsystems and use cases, such as temperature control and [ ] removal. Therefore, there is a need for technologies supporting the integration of existing models. We propose to extend existing digital twin frameworks to integrate models and serve as a tool for answering onboard queries during operation. Toward this vision, we identify research directions for three types of technologies: i) streamlining the process of merging information models without redundancies by leveraging model-based systems engineering languages; ii) the calibration of simulation models that requires a better understanding of how to encode domain knowledge into a probabilistic representation of subsystem states and model parameters; and iii) automating the query understanding process and constructing a mapping between information and simulation models.
- 1 April 2024
- Published by American Institute of Aeronautics and Astronautics (AIAA) in Journal of Aerospace Information Systems
- Vol. 21 (4) , 332-347
Digital Twin Technologies for Autonomous Environmental Control and Life Support Systems
Environmental control and life support systems will require enhanced self-awareness and self-sufficiency as human spaceflights are designed to reach further destinations. These requirements have led to the development of autonomous technologies and systems to enable more Earth independence, while at the same time relying more heavily on the knowledge contained in their computational models (as opposed to the knowledge of ground control experts). For environmental control and life support systems, these consist of disparate models often tailored to specific subsystems and use cases, such as temperature control and [ ] removal. Therefore, there is a need for technologies supporting the integration of existing models. We propose to extend existing digital twin frameworks to integrate models and serve as a tool for answering onboard queries during operation. Toward this vision, we identify research directions for three types of technologies: i) streamlining the process of merging information models without redundancies by leveraging model-based systems engineering languages; ii) the calibration of simulation models that requires a better understanding of how to encode domain knowledge into a probabilistic representation of subsystem states and model parameters; and iii) automating the query understanding process and constructing a mapping between information and simulation models.