Skip to main content Skip to footer
RESEARCH PROJECTS & TEAM

Digital Twin & HRI

Develops a multimodal digital twin environment combining 3D scene reconstruction and semantic reasoning for autonomous humanoid robot control.

Digital Twin & HRI

Related
Technology
Foundation Reinforcement Learning Models Humanoid Robot Control 3D Scene Reconstruction Semantic Reasoning Task Planning

Research Project

Reinforcement Learning (Rl) Methods For Care-Aimed Assistive Robots

This project develops reinforcement learning (RL) methods for assistive robots in home-care, hospital, and care-center environments. It first focuses on zero-shot RL generalization for robotic manipulation, aiming to enable robot arms to pick, place, and deliver diverse unseen objects such as medications, IV drips, injections, and daily necessities without task-specific retraining. To make this feasible in real-world care settings, the project then studies cross-domain RL, transferring knowledge from data-rich, low-cost source domains such as simulation to data-scarce, high-cost target domains such as hospital or home-care robots. This reduces the burden and risk of collecting large-scale real-world robot data. Finally, the project incorporates human-like RL so that robot action sequences better align with human behavior. By distilling demonstrations into reusable macro actions and optimizing human-like trajectories, the robots can behave more naturally and support seamless human–robot collaboration in sensitive care environments.

Project Details

Principal Investigator

Ping-Chun Hsieh Associate Professor

Research Field: Bandit Learning, Reinforcement Learning, Wireless Networks, and Bayesian Optimization

PI Details

Research Project

Speed Up Robot Motion Planning Computations

This project aims to leverage emerging parallel processing hardware accelerators through hardware-software integration to speed up robot motion planning computations. Motion planning enables robots to smoothly avoid obstacles in real-world environments, requiring them to find optimal movement steps and paths under specific constraints.

Project Details

Principal Investigator

Tsung-Tai Yeh Associate Professor

Research Field: Computer Architecture, GPU, AI Chip System Design

PI Details

Research Project

Multimodal Digital Twin and Human-Robot Interaction Technologies

The goal of this project is to build multimodal AI agents capable of continuously perceiving context, anticipating user needs, and proactively providing assistance in everyday life. Such agents are envisioned to run seamlessly on wearables, smart glasses, and service robots, serving as intelligent collaborators for humans in homes, workplaces, and public spaces. Realizing this vision requires AI agents to move beyond the passive paradigm of waiting for explicit commands, and to develop higher-order capabilities of observation, inference, and proactive intervention.

Project Details

Principal Investigator

An-Zi Yen Assistant Professor

Research Field: Natural Language Processing, Information Retrieval and Extraction, Deep Learning, Artificial Intelligence

PI Details

Research Project

Quality Assessment And Trustworthy Human-Robot Collaboration Technologies For Robot-Perceived VR Digital Twins

This project aims to develop quality assessment and trustworthy human-robot collaboration technologies for robot-perceived VR digital twins. Based on robot first-person views, depth information, semantic maps, robot states, and task-related information, this project will construct a multimodal digital twin interface in VR and investigate how its visual quality, reconstruction errors, information consistency, and latency affect human operators’ situational awareness, trust, cognitive workload, and decision-making performance. The project will further develop a multimodal quality assessment model capable of predicting the perceived quality of the digital twin interface and the reliability of human decision-making, while exploring quality-aware interaction optimization methods.

Project Details

Principal Investigator

Yu-Chih Chen Assistant Professor

Research Field: Multimodal Perception & Learning, Generative AI Media, Computer Vision, Deep Learning, Interactive & Immersive Media

PI Details