A Framework for Low-Latency, LLM-driven Multimodal Interaction on the Pepper Robot
For the HRI community, this provides a practical platform for exploring advanced LLM-driven embodied interaction, addressing latency and multimodal integration issues in existing Pepper implementations.
The paper presents an Android framework for the Pepper robot that integrates end-to-end Speech-to-Speech models and extensive Function Calling to reduce latency and enable multimodal interaction. The framework runs on the robot's tablet and can be adapted to other Android devices.
Despite recent advances in integrating Large Language Models (LLMs) into social robotics, two weaknesses persist. First, existing implementations on platforms like Pepper often rely on cascaded Speech-to-Text (STT)->LLM->Text-to-Speech (TTS) pipelines, resulting in high latency and the loss of paralinguistic information. Second, most implementations fail to fully leverage the LLM's capabilities for multimodal perception and agentic control. We present an open-source Android framework for the Pepper robot that addresses these limitations through two key innovations. First, we integrate end-to-end Speech-to-Speech (S2S) models to achieve low-latency interaction while preserving paralinguistic cues and enabling adaptive intonation. Second, we implement extensive Function Calling capabilities that elevate the LLM to an agentic planner, orchestrating robot actions (navigation, gaze control, tablet interaction) and integrating diverse multimodal feedback (vision, touch, system state). The framework runs on the robot's tablet but can also be built to run on regular Android smartphones or tablets, decoupling development from robot hardware. This work provides the HRI community with a practical, extensible platform for exploring advanced LLM-driven embodied interaction.