Huoyuan Tan

Gothenburg, Sweden

tanhuoyuan@gmail.com

I am Huoyuan Tan, a Master’s student in Computer Science and Engineering at the University of Gothenburg, with 5+ years of industry experience as an Algorithm Engineer in autonomous driving. My M.Sc. thesis focuses on Assessment & Failure Recovery in Remote Vision-Language-Action (VLA) Deployment.

Prior to graduate school, I worked at Xingyun Intelligence (Shenzhen) Technology Co., Ltd., where I played a key role in bringing autonomous driving systems — Automated Guided Vehicles (AGV), Autonomous Forklifts, and Intelligent Guided Vehicles (IGV) — from prototype to production deployment in ports and factory environments. My work spanned multi-sensor fusion (LiDAR, camera, GNSS/RTK, IMU), localization & SLAM, perception, motion planning, and control on ROS/C++.

My research interests lie at the intersection of Autonomous Driving, Embodied AI (VLA models, World Models), Large Language Models (LLMs), and Reinforcement Learning. I am passionate about building intelligent systems that are not only robust in the real world, but also interpretable and human-centered — systems that people can understand, trust, and safely collaborate with. I believe technology should augment human capability rather than replace human agency, and I am motivated by the opportunity to make autonomous systems that are safer, more transparent, and genuinely beneficial to society.

I am actively looking for Algorithm Engineer or Research Engineer positions at companies and research labs focused on autonomous driving, robotics, and embodied intelligence.

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.