3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning

TL;DR

3D-Mem introduces a novel 3D scene memory system for embodied agents that uses multi-view images and frontier-based exploration to improve scene understanding and active exploration in complex environments.

Contribution

The paper presents 3D-Mem, a new framework combining multi-view scene representations with frontier-based exploration and memory management for lifelong embodied AI tasks.

Findings

Significantly improves exploration efficiency in 3D environments.

Enhances reasoning capabilities with richer scene representations.

Demonstrates superior performance on three benchmark datasets.

Abstract

Constructing compact and informative 3D scene representations is essential for effective embodied exploration and reasoning, especially in complex environments over extended periods. Existing representations, such as object-centric 3D scene graphs, oversimplify spatial relationships by modeling scenes as isolated objects with restrictive textual relationships, making it difficult to address queries requiring nuanced spatial understanding. Moreover, these representations lack natural mechanisms for active exploration and memory management, hindering their application to lifelong autonomy. In this work, we propose 3D-Mem, a novel 3D scene memory framework for embodied agents. 3D-Mem employs informative multi-view images, termed Memory Snapshots, to represent the scene and capture rich visual information of explored regions. It further integrates frontier-based exploration by introducing Frontier Snapshots-glimpses of unexplored areas-enabling agents to make informed decisions by considering both known and potential new information. To support lifelong memory in active exploration settings, we present an incremental construction pipeline for 3D-Mem, as well as a memory retrieval technique for memory management. Experimental results on three benchmarks demonstrate that 3D-Mem significantly enhances agents' exploration and reasoning capabilities in 3D environments, highlighting its potential for advancing applications in embodied AI.