LV-DOT: LiDAR-visual dynamic obstacle detection and tracking for autonomous robot navigation

TL;DR

This paper presents a lightweight, multi-sensor perception framework combining LiDAR and camera data for dynamic obstacle detection and tracking in indoor robot navigation, improving accuracy and real-time performance.

Contribution

It introduces a robust fusion strategy for LiDAR and visual data, enhancing detection accuracy over previous ensemble methods in indoor robotics.

Findings

Outperforms benchmark perception methods in dataset evaluations.

Enables real-time obstacle detection and tracking on onboard hardware.

Validated through physical experiments on a quadcopter robot.

Abstract

Accurate perception of dynamic obstacles is essential for autonomous robot navigation in indoor environments. Although sophisticated 3D object detection and tracking methods have been investigated and developed thoroughly in the fields of computer vision and autonomous driving, their demands on expensive and high-accuracy sensor setups and substantial computational resources from large neural networks make them unsuitable for indoor robotics. Recently, more lightweight perception algorithms leveraging onboard cameras or LiDAR sensors have emerged as promising alternatives. However, relying on a single sensor poses significant limitations: cameras have limited fields of view and can suffer from high noise, whereas LiDAR sensors operate at lower frequencies and lack the richness of visual features. To address this limitation, we propose a dynamic obstacle detection and tracking framework that uses both onboard camera and LiDAR data to enable lightweight and accurate perception. Our proposed method expands on our previous ensemble detection approach, which integrates outputs from multiple low-accuracy but computationally efficient detectors to ensure real-time performance on the onboard computer. In this work, we propose a more robust fusion strategy that integrates both LiDAR and visual data to enhance detection accuracy further. We then utilize a tracking module that adopts feature-based object association and the Kalman filter to track and estimate detected obstacles' states. Besides, a dynamic obstacle classification algorithm is designed to robustly identify moving objects. The dataset evaluation demonstrates a better perception performance compared to benchmark methods. The physical experiments on a quadcopter robot confirms the feasibility for real-world navigation.