A Framework for Low-Latency, LLM-driven Multimodal Interaction on the Pepper Robot

TL;DR

This paper introduces an open-source Android framework for the Pepper robot that enables low-latency, multimodal interaction by integrating end-to-end speech models and advanced function calling for autonomous robot control.

Contribution

It presents a novel framework that combines end-to-end speech processing with LLM-based multimodal perception and control, addressing latency and capability limitations of prior systems.

Findings

Achieved low-latency speech-to-speech interaction preserving paralinguistic cues

Enabled LLM-driven multimodal perception and autonomous robot actions

Framework is adaptable to standard Android devices

Abstract

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.