Intelligent Physical Interaction Robotics Laboratory
Research Field
Dr. Chen-Ting Wen is an Assistant Professor in the Department of Mechanical Engineering at the National Taiwan University of Science and Technology (Taiwan Tech). His research focuses on intelligent robotic systems capable of perceiving, interpreting, and physically interacting with their environment. In particular, he is interested in tactile perception, multimodal sensory integration, robot manipulation, soft robotics, and physics-informed machine learning. Through the integration of sensing, modeling, and control, his research aims to enable robots to perform reliable and adaptive physical interaction in uncertain and dynamically changing environments.
The Intelligent Physical Interaction Robotics Laboratory, or i-Phi Lab, investigates how robots can intelligently interact with objects, humans, and their surrounding environment through physical contact. The laboratory integrates tactile, visual, proximity, force, and other sensory modalities with robot control and machine-learning methods. Its central philosophy is that physical contact provides essential information that cannot always be obtained through vision alone. Accordingly, i-Phi Lab develops robotic systems that can perceive contact conditions, understand physical interactions, and adapt their actions in real time. The laboratory also provides students with systematic training in robot kinematics, trajectory generation, sensing, control, experimental implementation, and research methodology.
The primary research topics of i-Phi Lab include tactile perception and tactile servoing, vision-tactile fusion, dual-arm manipulation, soft robotic systems, smart-material-based robotic grippers, and physics-informed robot learning. Current research investigates tactile-image-based manipulation, ball-rolling and in-hand manipulation, contact-rich insertion tasks, and robust robotic operation under visual occlusion or unstable lighting conditions. The laboratory also studies the modeling and control of soft robots using physical information, data-driven dynamic models, neural differential equations, Hamiltonian-based learning, and state-space models. Additional research directions include human-robot physical interaction, deformable-object manipulation, multimodal sensing, adaptive grasping, medical robotics, agricultural robotics, and autonomous robotic systems.
Associate Area Editor, International Journal of Automation and Smart Technology (AUSMT)
Dr. Wen received his bachelor’s degree from National Cheng Kung University in Taiwan and subsequently pursued advanced education and research in robotics in Japan. During his academic training, he developed expertise in robot manipulation, physical human-robot interaction, tactile sensing, and intelligent robotic control. He later conducted research at Tohoku University and Toyohashi University of Technology, where he participated in multidisciplinary projects involving robotic manipulation, soft grippers, tactile feedback, agricultural robots, and human-support robotic systems. His educational and research experience across Taiwan and Japan has shaped his interdisciplinary approach, which combines mechanical engineering, robotics, control theory, sensing technology, and machine learning.
Job Description
The internship is planned as a short-term research activity of approximately one month. The intern will work under the supervision of the host laboratory and participate in research discussions related to robotics, motion analysis, and control engineering. The expected outcome may include a short technical report, summarized experimental observations, and preliminary analysis results on humanoid robot gait behavior.
Preferred Intern Educational Level
Senior undergraduate student or above in mechanical engineering, robotics, control engineering, electrical engineering, or a related field.
Skill sets or Qualities
The applicant is expected to have basic knowledge of mechanics, robotics, kinematics, and control engineering at the senior undergraduate level. Basic programming skills in MATLAB, Python, or a similar language are preferred. Experience with data analysis, robot simulation, motion capture, or experimental measurement is helpful but not strictly required. The applicant should be motivated to learn, able to work carefully with experimental data, and willing to discuss research progress with laboratory members.