LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometry

2025-12-22

AI Summary

Existing end-to-end navigation methods for unstructured environments rely on separate localization modules, require precise sensor calibration, and exhibit poor generalization. To address these limitations, this paper proposes an end-to-end trajectory planning framework that jointly integrates implicit localization with metric-aware visual geometric modeling. Our key contributions are: (1) the first “localization-anchored” end-to-end paradigm; (2) a long-horizon vision–geometry backbone network enabling implicit state estimation at absolute scale; and (3) dense scene geometry reconstruction from historical observations to support robust obstacle avoidance. Leveraging implicit geometric memory modeling, multi-task auxiliary supervision (localization + reconstruction), and joint fine-tuning, our method achieves over 27.3% improvement in navigation accuracy over ideal localization baselines in both simulation and real-world settings, significantly reducing cumulative pose error. It demonstrates strong cross-platform and cross-environment generalization without explicit mapping or external localization.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Planning with Language Models
• Computer Vision: Visual Reasoning & Symbolic Representations

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Trajectory planning in unstructured environments is a fundamental and challenging capability for mobile robots. Traditional modular pipelines suffer from latency and cascading errors across perception, localization, mapping, and planning modules. Recent end-to-end learning methods map raw visual observations directly to control signals or trajectories, promising greater performance and efficiency in open-world settings. However, most prior end-to-end approaches still rely on separate localization modules that depend on accurate sensor extrinsic calibration for self-state estimation, thereby limiting generalization across embodiments and environments. We introduce LoGoPlanner, a localization-grounded, end-to-end navigation framework that addresses these limitations by: (1) finetuning a long-horizon visual-geometry backbone to ground predictions with absolute metric scale, thereby providing implicit state estimation for accurate localization; (2) reconstructing surrounding scene geometry from historical observations to supply dense, fine-grained environmental awareness for reliable obstacle avoidance; and (3) conditioning the policy on implicit geometry bootstrapped by the aforementioned auxiliary tasks, thereby reducing error propagation.We evaluate LoGoPlanner in both simulation and real-world settings, where its fully end-to-end design reduces cumulative error while metric-aware geometry memory enhances planning consistency and obstacle avoidance, leading to more than a 27.3% improvement over oracle-localization baselines and strong generalization across embodiments and environments. The code and models have been made publicly available on the href{https://steinate.github.io/logoplanner.github.io/}{project page}.

Problem

• Traditional modular navigation pipelines suffer from latency and cascading errors across perception, localization, mapping, and planning modules.
• Most end-to-end navigation approaches rely on separate localization modules that require accurate sensor calibration, limiting generalization across embodiments and environments.
• There is a need for an end-to-end navigation framework that provides implicit state estimation and metric-aware geometry for consistent planning and obstacle avoidance.

Innovation

• End-to-end navigation framework with implicit state estimation
• Metric-aware visual geometry for localization and planning
• Reconstructed scene geometry for obstacle avoidance