DynamicFilter: an Online Dynamic Objects Removal Framework for Highly Dynamic Environments

TL;DR

This paper presents DynamicFilter, an online framework designed to effectively remove dynamic objects in urban environments, enhancing robotic navigation by integrating visibility-based and map-based methods in real-time.

Contribution

The paper introduces a novel online removal framework combining scan-to-map and map-to-map modules for highly dynamic environments, validated through simulations and real-world data.

Findings

Effective removal of dynamic objects in urban navigation scenarios

Validated framework performance in simulation and real-world datasets

Improved spatial structure stability during robot navigation

Abstract

Emergence of massive dynamic objects will diversify spatial structures when robots navigate in urban environments. Therefore, the online removal of dynamic objects is critical. In this paper, we introduce a novel online removal framework for highly dynamic urban environments. The framework consists of the scan-to-map front-end and the map-to-map back-end modules. Both the front- and back-ends deeply integrate the visibility-based approach and map-based approach. The experiments validate the framework in highly dynamic simulation scenarios and real-world datasets.