Teaching Robots Like Dogs: Learning Agile Navigation from Luring, Gesture, and Speech

TL;DR

This paper presents a data-efficient, multimodal human-in-the-loop framework enabling legged robots to learn agile navigation from minimal demonstrations, guided by natural human gestures and speech.

Contribution

It introduces a novel framework combining simulation, data aggregation, and adaptive goal cueing for efficient robot navigation learning from limited human demonstrations.

Findings

Achieved 97.15% success rate in real-world navigation tasks.

Learned from less than 1 hour of demonstration data.

Successfully handled complex scenarios like obstacle jumping.

Abstract

In this work, we aim to enable legged robots to learn how to interpret human social cues and produce appropriate behaviors through physical human guidance. However, learning through physical engagement can place a heavy burden on users when the process requires large amounts of human-provided data. To address this, we propose a human-in-the-loop framework that enables robots to acquire navigational behaviors in a data-efficient manner and to be controlled via multimodal natural human inputs, specifically gestural and verbal commands. We reconstruct interaction scenes using a physics-based simulation and aggregate data to mitigate distributional shifts arising from limited demonstration data. Our progressive goal cueing strategy adaptively feeds appropriate commands and navigation goals during training, leading to more accurate navigation and stronger alignment between human input and robot behavior. We evaluate our framework across six real-world agile navigation scenarios, including jumping over or avoiding obstacles. Our experimental results show that our proposed method succeeds in almost all trials across these scenarios, achieving a 97.15% task success rate with less than 1 hour of demonstration data in total.