Huoyuan Tan

Gothenburg, Sweden

tanhuoyuan@gmail.com

I am Huoyuan Tan, a PhD student in the Division of Systems and Control at the Department of Electrical Engineering, Chalmers University of Technology, and a member of the CRAFT lab.

My research interests include structured, interpretable, and experience-driven robot learning, with the aim of enabling resilient and adaptive behavior in collaborative robots. I am interested in connecting high-level reasoning with executable skills so that robots can learn from experience, adapt to changing environments, and collaborate effectively with humans.

I hold an M.Sc. in Computer Science and Engineering from the University of Gothenburg. My master’s research focused on assessment and failure recovery in remote vision-language-action (VLA) deployment, combining real-world robot experiments with simulation-based evaluation.

Before my master’s studies, I worked as a robotics engineer, gaining over five years of industry experience developing and deploying mobile robotic systems for logistics, factory, and port automation. My work covered multi-sensor fusion, SLAM, perception, planning, control, and ROS-based system development.

My background connects practical robot development and deployment with research on robot learning and reliable autonomous behavior.

news

Oct 01, 2026	Joined the CRAFT Lab as a PhD student in the Division of Systems and Control, Department of Electrical Engineering, Chalmers University of Technology.
Jun 12, 2026	Successfully defended my master’s thesis, Assessment and Failure Recovery in Remote Vision-Language-Action Deployment.
Jun 2017	Received the Outstanding Graduate Award (B.Eng. in Medical Information Engineering).

selected publications

Abnormal Activity Detection Using Pyroelectric Infrared Sensors

Xiaomu Luo, Huoyuan Tan, Qiuju Guan, and 3 more authors

Sensors, 2016

Abs DOI

Healthy aging is one of the most important social issues. In this paper, we propose a method for abnormal activity detection without any manual labeling of the training samples. By leveraging the Field of View (FOV) modulation, the spatio-temporal characteristic of human activity is encoded into low-dimension data stream generated by the ceiling-mounted Pyroelectric Infrared (PIR) sensors. The similarity between normal training samples are measured based on Kullback-Leibler (KL) divergence of each pair of them. The natural clustering of normal activities is discovered through a self-tuning spectral clustering algorithm with unsupervised model selection on the eigenvectors of a modified similarity matrix. Hidden Markov Models (HMMs) are employed to model each cluster of normal activities and form feature vectors. One-Class Support Vector Machines (OSVMs) are used to profile the normal activities and detect abnormal activities. To validate the efficacy of our method, we conducted experiments in real indoor environments. The encouraging results show that our method is able to detect abnormal activities given only the normal training samples, which aims to avoid the laborious and inconsistent data labeling process.
Simultaneous Indoor Tracking and Activity Recognition Using Pyroelectric Infrared Sensors

Xiaomu Luo, Qiuju Guan, Huoyuan Tan, and 3 more authors

Sensors, 2017

Abs DOI

Indoor human tracking and activity recognition are fundamental yet coherent problems for ambient assistive living. In this paper, we propose a method to address these two critical issues simultaneously. We construct a wireless sensor network (WSN), and the sensor nodes within WSN consist of pyroelectric infrared (PIR) sensor arrays. To capture the tempo-spatial information of the human target, the field of view (FOV) of each PIR sensor is modulated by masks. A modified partial filter algorithm is utilized to decode the location of the human target. To exploit the synergy between the location and activity, we design a two-layer random forest (RF) classifier. The initial activity recognition result of the first layer is refined by the second layer RF by incorporating various effective features. We conducted experiments in a mock apartment. The mean localization error of our system is about 0.85 m. For five kinds of daily activities, the mean accuracy for 10-fold cross-validation is above 92%. The encouraging results indicate the effectiveness of our system.