Employing Laban Shape for Generating Emotionally and Functionally Expressive Trajectories in Robotic Manipulators
by Srikrishna Bangalore Raghu, Clare Lohrmann, Akshay Bakshi, Jennifer Kim, Jose Caraveo Herrera, Bradley Hayes, and Alessandro Roncone.

This work addresses a key challenge in human-robot collaboration: robots often move with precise but monotonous motions that lack the ability to communicate intent or capability. By integrating Laban Movement Analysis (LMA)—a framework from dance notation—the team enables robotic manipulators to perform trajectories that are both emotionally expressive (Happy, Sad, Shy, Angry) and functionally expressive, signaling uncertainty or hesitancy through motion.

Key contributions of the paper include:

• Introducing two new Hesitant motions (Spoke-Like and Arc-Like) that allow robots to express uncertainty.
• Enhancing four existing emotional trajectories by combining Laban Shape with Laban Effort, leading to clearer, more distinct expressions.
• Conducting human-subjects studies demonstrating that people perceive these trajectories as meaningful signals of both emotion and robot capability.

The experiments highlight the promise of expressive robotics in improving team transparency, trust, and efficiency. As shown in the results on page 5, hesitant motions were consistently interpreted as signals of reduced competence, validating their role as functional communication cues.

📄 Full paper PDF: CAIRO Link

This research, supported by the Army Research Laboratory (Grant #W911NF-21-2-02905), pushes forward the frontier of expressive robotics by blending insights from dance, psychology, and human-robot interaction.