# Efficient Learning-Based Robotic Navigation Using Feature-Based RGB-D Pose Estimation and Topological Maps

## TL;DR

This paper introduces a cost-effective robotic navigation system using RGB-D cameras and machine learning, achieving reliable indoor navigation on regular hardware.

## Contribution

The novel pipeline combines feature-based pose estimation with a lightweight MLP policy for efficient, real-time navigation without metric SLAM.

## Key findings

- The agent successfully navigated 190.44 m across multiple environments, stopping within 0.1 m of goals.
- LightGlue features outperformed alternatives in information gain under lighting changes.
- The system replanned in real time and operated efficiently on commodity hardware.

## Abstract

Robust indoor robot navigation typically demands either costly sensors or extensive training data. We propose a cost-effective RGB-D navigation pipeline that couples feature-based relative pose estimation with a lightweight multi-layer-perceptron (MLP) policy. RGB-D keyframes extracted from human-driven traversals form nodes of a topological map; edges are added when visual similarity and geometric–kinematic constraints are jointly satisfied. During autonomy, LightGlue features and SVD give six-DoF relative pose to the active keyframe, and the MLP predicts one of four discrete actions. Low visual similarity or detected obstacles trigger graph editing and Dijkstra replanning in real time. Across eight tasks in four Habitat-Sim environments, the agent covered 190.44 m, replanning when required, and consistently stopped within 0.1 m of the goal while running on commodity hardware. An information-theoretic analysis over the Multi-Illumination dataset shows that LightGlue maximizes per-second information gain under lighting changes, motivating its selection. The modular design attains reliable navigation without metric SLAM or large-scale learning, and seamlessly accommodates future perception or policy upgrades.