A5007645958- Social Robot Interaction and HRI
- Emotion and Mood Recognition
- Multimodal Machine Learning Applications
- Advanced Image and Video Retrieval Techniques
- Human-Automation Interaction and Safety
- Action Observation and Synchronization
- Evolutionary Game Theory and Cooperation
- Mental Health Research Topics
- Domain Adaptation and Few-Shot Learning
- Autism Spectrum Disorder Research
- Technology Use by Older Adults
- Reinforcement Learning in Robotics
- Topic Modeling
- Digital Mental Health Interventions
- Mental Health via Writing
- Recommender Systems and Techniques
- Robot Manipulation and Learning
- Opinion Dynamics and Social Influence
- Misinformation and Its Impacts
- Identity, Memory, and Therapy
- Infant Health and Development
- Human-Animal Interaction Studies
- Robotics and Automated Systems
National Taiwan University
2017-2022
In this work, we created an end-to-end autonomous robotic platform to give emotional support children in long-term, multi-session interactions. Using a mood estimation algorithm based on visual cues of the user's behaviors through their facial expressions and body posture, multidimensional model predicts qualitative measure subject's affective state. novel Interactive Reinforcement Learning algorithm, robot is able learn over several sessions social profile user, adjusting its behavior match...
This article discusses the implementation of a brain-inspired episodic memory model, which provides assistance and tackles modern public issue impairment embedded as an end-to-end system on robot companion, Pepper. Based fusion adaptive resonance theory, proposed model can observe memorize content daily events in five aspects: 1) people; 2) activities; 3) times; 4) places; 5) objects. The is based human pipeline, containing working two-layer long-term effectively merge, cluster, summarize...
Reminiscence is a lifelong activity that happens throughout our lifespan. While memories can serve as topics in people's everyday conversations, recalling the past also help us build self-esteem and increase level of happiness. In this paper, we aim to develop robot companion helps people recollect their from personal photographs. We focus on how associate concepts relevant content photographs evoke by asking questions are both relatable engaging. To understand picture, applied deep learning...
As robots participate in human's daily activities more and frequently, mobility performance has become one of the main factors determining how will share an environment with humans harmoniously near future. Among several different kinds mobile platforms, using omnidirectional configurations is gradually becoming a trend robotics community; however, few researchers have addressed impact from perspective human-robot interaction (HRI). In this paper, we proposed socializing model for robot...
Human social interactions are laden with behavioral preferences that stem from hidden network representations. In this study, we applied an artificial neural machine theory of mind (ToMnet+) to learn and predict based on implicit information the way agents targets interact behaviorally. Our findings have implications for applications seek infer structures solely third-person observation behaviors. We consider machines such ability would enhanced potential more naturalistic human-machine interactions.