Design and Implementation of a Companion Robot with LLM-Based Hierarchical Emotion Motion Generation
Open Access
- 2 December 2025
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 15 (23) , 12759
Abstract
Recently, human–robot interaction (HRI) with social robots has attracted significant attention. Among them, companion robots, which exhibit pet-like behaviors and interact with people primarily through non-verbal means, particularly require the generation of appropriate gestures. This paper presents the design and implementation of a companion cat robot, named PEPE, with a large language model (LLM)-based hierarchical emotional motion generation method. To design the cat-like companion robot, an analysis of feline emotional behaviors was conducted to identify the body parts and motions essential for effective emotional expression. Based on this analysis, the required degrees of freedom (DoFs) and structural configuration for PEPE were derived. To generate expressive gestures efficiently and reliably, a hierarchical LLM-based emotional motion generation method was proposed. The process defines the robot’s structural features, establishes a gesture generation code format, and incorporates emotion-based guidelines grounded in feline behavioral analysis to mitigate LLM hallucination and ensure physical feasibility. The proposed method was implemented on the physical robot, and eight emotional gestures were generated—Happy, Angry, Sad, Fearful, Joyful, Excited, Positive Feedback, and Negative Feedback. A user study with 15 participants was conducted to validate the system. The high-arousal gestures—Angry, Joyful, and Excited—were rated significantly above the neutral clarity threshold (p < 0.05), demonstrating clear user recognition. Meanwhile, low-arousal gestures exhibited neutral-level perceptions consistent with their subtle motion profiles. These results confirm that the proposed LLM-based framework effectively generates expressive, physically executable gestures for a companion robot.Keywords
Funding Information
- Ministry of Trade, Industry and Energy (20018513)
This publication has 31 references indexed in Scilit:
- EMOTION: Expressive Motion Sequence Generation for Humanoid Robots With In-Context LearningIEEE Robotics and Automation Letters, 2025
- The Role of Coherent Robot Behavior and Embodiment in Emotion Perception and Recognition During Human-Robot Interaction: Experimental StudyJMIR Human Factors, 2024
- Feline faces: Unraveling the social function of domestic cat facial signalsBehavioural Processes, 2023
- Nonverbal Cues in Human–Robot Interaction: A Communication Studies PerspectiveACM Transactions on Human-Robot Interaction, 2023
- Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language ProcessingACM Computing Surveys, 2023
- Robot companion cats for people at home with dementia: A qualitative case study on companoticsDementia, 2020
- A Model for Basic Emotions Using Observations of Behavior in DrosophilaFrontiers in Psychology, 2019
- Development and application of CatFACS: Are human cat adopters influenced by cat facial expressions?Applied Animal Behaviour Science, 2017
- Emotionally expressive dynamic physical behaviors in robotsInternational Journal of Human-Computer Studies, 2015
- The Uncanny Valley [From the Field]IEEE Robotics & Automation Magazine, 2012