bsu-slim/emro-misty

Misty-EMRO: Emotion Recognition Model from Robot Behaviors for Misty Robot

This is a RoBERTa-based text classification model fine-tuned specifically to recognize emotions from robot-generated behaviors. It is trained on data collected from the Misty robot and is capable of classifying textual descriptions of robot actions into one of six emotion categories.

Development code: https://github.com/bsu-slim/emro-gred-misty

Model Details

• Base Model: RoBERTa-base
• Tasks: Text Classification (Emotion Classification)
• Number of Classes: 6 emotions
• Emotion Labels:
  • 0: anger_frustration
  • 1: interest_desire
  • 2: confusion_sorrow_boredom
  • 3: joy_hope
  • 4: understanding_gratitude_relief
  • 5: disgust_surprise_alarm_fear

Files in this repo

• pytorch_model.bin – Fine-tuned model weights
• config.json – Model architecture and label mapping
• vocab.json, merges.txt, tokenizer_config.json, special_tokens_map.json – Tokenizer files
• misty_emro.py – Custom model class definition (RobertaClass)

How to Use

You need to use the provided custom model class RobertaClass defined in misty_emro.py to load the model:

import torch
from transformers import RobertaTokenizer, RobertaConfig
from misty_emro import RobertaClass

model_name = "bsu-slim/emro-misty"  # can be replaced with the repo name

# Load configuration and tokenizer
config = RobertaConfig.from_pretrained(model_name)
tokenizer = RobertaTokenizer.from_pretrained(model_name)

# Load model
model = RobertaClass(num_classes=config.num_labels)
model.load_state_dict(torch.load("pytorch_model.bin"))

Citation

@INPROCEEDINGS{11246523,
  author={Baral, Rista and Grenz, Bethany and Kennington, Casey},
  booktitle={2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, 
  title={Recognizing and Generating Novel Emotional Behaviors on Two Robotic Platforms}, 
  year={2025},
  volume={},
  number={},
  pages={21503-21510},
  keywords={Training;Emotion recognition;Behavioral sciences;Robots;Intelligent robots},
  doi={10.1109/IROS60139.2025.11246523}}