Efficient Greedy Algorithms for Feature Selection in Robot Visual Localization

2025-11-25

AI Summary

To address the high computational cost and poor real-time performance caused by feature redundancy in robot visual localization, this paper proposes two low-complexity greedy feature selection algorithms. Methodologically, we pioneer the integration of feature utility evaluation with observability modeling from visual odometry, enabling a lightweight online feature filtering mechanism that dynamically identifies highly informative feature subsets over a prediction horizon. Both algorithms exhibit linear time and space complexity, substantially reducing memory footprint and processing latency. Experimental evaluation on public benchmarks demonstrates that, compared to baseline approaches, our method reduces feature processing volume by 62%–78%, incurs at most a 0.8% degradation in localization accuracy, and accelerates inference by 2.3×–3.1×. This work achieves an effective trade-off between computational efficiency and localization robustness, establishing a new paradigm for real-time visual localization on resource-constrained platforms.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Dimensionality Reduction/Feature Selection
• Computer Vision: Low Level & Physics-based Vision

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Robot localization is a fundamental component of autonomous navigation in unknown environments. Among various sensing modalities, visual input from cameras plays a central role, enabling robots to estimate their position by tracking point features across image frames. However, image frames often contain a large number of features, many of which are redundant or uninformative for localization. Processing all features can introduce significant computational latency and inefficiency. This motivates the need for intelligent feature selection, identifying a subset of features that are most informative for localization over a prediction horizon. In this work, we propose two fast and memory-efficient feature selection algorithms that enable robots to actively evaluate the utility of visual features in real time. Unlike existing approaches with high computational and memory demands, the proposed methods are explicitly designed to reduce both time and memory complexity while achieving a favorable trade-off between computational efficiency and localization accuracy.

Problem

• Selecting informative visual features for robot localization
• Reducing computational complexity in feature selection algorithms
• Balancing efficiency and accuracy in visual localization systems

Innovation

• Fast greedy algorithms for feature selection
• Memory-efficient real-time visual feature evaluation
• Balancing computational efficiency with localization accuracy