Topo-Field: Topometric mapping with Brain-inspired Hierarchical Layout-Object-Position Fields

2024-06-10

AI Summary

Existing mapping approaches for mobile robot navigation struggle to simultaneously achieve semantic richness, spatial accuracy, and computational efficiency. To address this, we propose Layout-Object-Position (LOP) neural fields—a brain-inspired hierarchical representation inspired by posterior parietal cortex spatial coding mechanisms—enabling the first topology-metric joint mapping framework grounded in neuroscientific principles. LOP jointly encodes scene layout, object instances, and their relative spatial relationships, leveraging weak supervision from large foundation models (LFMs) and implicit neural field queries to generate lightweight topological maps end-to-end. Evaluated in multi-room environments, our method significantly improves positional attribute reasoning, cross-modal query-based localization, and topological planning accuracy. Compared to NeRF-based methods, it achieves a 5.2× speedup in inference and reduces memory consumption by 78%, while maintaining strong semantic expressivity and real-time deployability.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Mobile robots require comprehensive scene understanding to operate effectively in diverse environments, enriched with contextual information such as layouts, objects, and their relationships. Although advances like neural radiation fields (NeRFs) offer high-fidelity 3D reconstructions, they are computationally intensive and often lack efficient representations of traversable spaces essential for planning and navigation. In contrast, topological maps are computationally efficient but lack the semantic richness necessary for a more complete understanding of the environment. Inspired by a population code in the postrhinal cortex (POR) strongly tuned to spatial layouts over scene content rapidly forming a high-level cognitive map, this work introduces Topo-Field, a framework that integrates Layout-Object-Position (LOP) associations into a neural field and constructs a topometric map from this learned representation. LOP associations are modeled by explicitly encoding object and layout information, while a Large Foundation Model (LFM) technique allows for efficient training without extensive annotations. The topometric map is then constructed by querying the learned neural representation, offering both semantic richness and computational efficiency. Empirical evaluations in multi-room environments demonstrate the effectiveness of Topo-Field in tasks such as position attribute inference, query localization, and topometric planning, successfully bridging the gap between high-fidelity scene understanding and efficient robotic navigation.

Problem

• Mobile Robotics
• Object Localization
• Efficient Mapping

Innovation

• Topo-Field
• Neural Radiance Fields (NeRFs)
• Topological Mapping