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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Studerus, Erich, Zhong, Vivienne Jia, Vonschallen, Stephan
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908905573974016
author Studerus, Erich
Zhong, Vivienne Jia
Vonschallen, Stephan
author_facet Studerus, Erich
Zhong, Vivienne Jia
Vonschallen, Stephan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_21013
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Framework for Low-Latency, LLM-driven Multimodal Interaction on the Pepper Robot
Studerus, Erich
Zhong, Vivienne Jia
Vonschallen, Stephan
Artificial Intelligence
Machine Learning
Robotics
I.2.9; H.5.2
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.
title A Framework for Low-Latency, LLM-driven Multimodal Interaction on the Pepper Robot
topic Artificial Intelligence
Machine Learning
Robotics
I.2.9; H.5.2
url https://arxiv.org/abs/2603.21013