Long-Term Online Multi-Session Graph-Based SPLAM with Memory Management

TL;DR

This paper presents a memory management approach for long-term online multi-session SPLAM that efficiently updates and retrieves environment maps, enabling autonomous robot navigation over extended periods with dynamic surroundings.

Contribution

It introduces a memory management mechanism that distinguishes between working and long-term memories for efficient online SPLAM in long-term deployments.

Findings

Successfully patrolled 10.5 km over 11 sessions in indoor environment.

Effectively managed memory to handle dynamic changes and revisit previous areas.

Operated with limited onboard computation capabilities.

Abstract

For long-term simultaneous planning, localization and mapping (SPLAM), a robot should be able to continuously update its map according to the dynamic changes of the environment and the new areas explored. With limited onboard computation capabilities, a robot should also be able to limit the size of the map used for online localization and mapping. This paper addresses these challenges using a memory management mechanism, which identifies locations that should remain in a Working Memory (WM) for online processing from locations that should be transferred to a Long-Term Memory (LTM). When revisiting previously mapped areas that are in LTM, the mechanism can retrieve these locations and place them back in WM for online SPLAM. The approach is tested on a robot equipped with a short-range laser rangefinder and a RGB-D camera, patrolling autonomously 10.5 km in an indoor environment over 11 sessions while having encountered 139 people.