Embodied Human-Robot Interaction via Acoustics: A MARL Approach with AcoustoBots for Spatial Data Physicalization

2026-07-07

AI Summary

Traditional static data physicalization struggles to convey embodied spatial dynamics and elicit effective interaction. This work proposes AcoustoBots, a novel system that integrates ultrasonic phased-array acoustic levitation with multi-robot collaborative navigation to dynamically encode urban scalar data into the levitation height of particles, thereby establishing a perception-display-action loop. The system employs multi-agent deep deterministic policy gradient (MADDPG) for obstacle-aware navigation, leverages the Gerchberg–Saxton algorithm for real-time control of levitation height, and utilizes PhaseSpace for high-precision localization. Experimental results demonstrate task success rates of 90% and 80% in single- and dual-robot scenarios, respectively, achieving stable, position-dependent data visualization during motion. This approach offers a novel, glanceable form of physical cueing for embodied human–robot interaction.

Abstract

Traditional data physicalization is often static and disconnected from real environments, limiting its ability to convey embodied spatial dynamics and engage users. To address this limitation, we present AcoustoBots, a mobile acoustophoretic data-physicalization platform in which TurtleBot3 robots carry upward-facing 8 x 8 ultrasonic phased arrays. Each array levitates a particle whose height (1-10 cm) encodes a local urban scalar value, such as population density, noise, or traffic. A MARL (Multi-Agent Reinforcement Learning) policy based on the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm, with centralized training and decentralized execution, selects collision-aware navigation actions, while a high-rate Gerchberg-Saxton-Phased Array of Transducers (GS-PAT) acoustic controller maintains trap stability and updates array phases to achieve the commanded height during motion. This creates a closed perception-display-action loop. We evaluate single-robot city-to-city traversal and dual-robot cooperative coverage on a 4 m x 3 m scaled UK map using PhaseSpace-based localization for repeatable multi-robot trials. Results show stable in-motion levitation and consistent, location-dependent height rendering, with task success rates of 90% and 80% for the single and dual-robot regimes, respectively, over 10 trials per regime, and low collision counts. These findings support acoustophoretic levitation as a simple, glanceable, robot-mediated communication cue for embodied human-robot interaction in spatial analytics.

Problem

• data physicalization
• embodied interaction
• spatial dynamics
• human-robot interaction
• acoustic levitation

Innovation

• acoustophoresis
• multi-agent reinforcement learning
• data physicalization
• ultrasonic phased array
• embodied interaction