Emotion-modulated gait generation enables expressive humanoid walking
EMoG: Emotion-Modulated Gait Generation for Expressive Humanoid Locomotion
Robotics
Summary
Humanoid robots usually focus on walking steadily and completing tasks, but showing emotions through their walk is hard. The authors created EMoG, a system that changes a robot's walking style based on different emotions with adjustable intensity. They collected walking patterns from professional performers showing emotions and trained the robot to copy these while still walking properly. EMoG can also understand natural language commands to change the robot's walking style interactively. This helps robots walk with more human-like expressiveness, which could improve how they interact with people.
What this means in practice
- •For robotics engineers: Generate emotionally expressive walking patterns for humanoid robots to improve their interaction capabilities in real time.
- •For game developers: Create characters whose walking styles reflect emotional states dynamically, enhancing realism and immersion in interactive games.
Authors
Yi Lu, Tianhao Jiang, Honglong Tian, Yumeng Zhang, Qingrui Zhao, Zhengtao Wang, Xiao-Xiao Long, Qiu Shen, Xun Cao
Abstract
Existing humanoid locomotion systems primarily focus on stability and task execution, while integrating expressiveness with explicit locomotion control remains challenging. We propose EMoG, an emotion-modulated gait generation framework for expressive humanoid locomotion. EMoG introduces an emotional-style code with continuously adjustable intensity. Conditioned on this code and physical commands, a lightweight MLP generates expressive, command-consistent periodic gait trajectories in real time, which are tracked by a unified reinforcement learning policy for physical execution. To support training, we collect a large-scale emotion-annotated gait dataset from professional performers and develop an automated pipeline to extract physically consistent periodic gait cycles. EMoG also integrates an LLM-based parser that converts free-form language into emotional style and motion parameters for interactive control. Experiments demonstrate continuous gait-style modulation with perceptible expressive cues while maintaining command tracking. EMoG provides a practical approach to parameterized emotional-style walking for human-robot interaction.