CuriousBot: Interactive Mobile Exploration via Actionable 3D Relational Object Graph

TL;DR

CuriousBot introduces a novel 3D relational object graph for mobile robots to actively explore environments through interaction, addressing challenges like large spaces and complex object relations, and demonstrating superior performance over vision-language models.

Contribution

The paper presents a new 3D relational object graph representation enabling active interaction for mobile exploration, improving over existing perception-focused methods.

Findings

Effective exploration across diverse scenes

Generalizes well to different objects and relations

Outperforms vision-language model-based methods

Abstract

Mobile exploration is a longstanding challenge in robotics, yet current methods primarily focus on active perception instead of active interaction, limiting the robot's ability to interact with and fully explore its environment. Existing robotic exploration approaches via active interaction are often restricted to tabletop scenes, neglecting the unique challenges posed by mobile exploration, such as large exploration spaces, complex action spaces, and diverse object relations. In this work, we introduce a 3D relational object graph that encodes diverse object relations and enables exploration through active interaction. We develop a system based on this representation and evaluate it across diverse scenes. Our qualitative and quantitative results demonstrate the system's effectiveness and generalization across object instances, relations, and scenes, outperforming methods solely relying on vision-language models (VLMs).