Learning to Prevent Monocular SLAM Failure using Reinforcement Learning

TL;DR

This paper introduces a reinforcement learning approach to generate fail-safe trajectories for monocular SLAM, significantly reducing failure rates and improving SLAM quality in both simulated and real-world robot experiments.

Contribution

It presents a novel RL-based framework that learns to produce trajectories preventing monocular SLAM failure, integrating perception and control.

Findings

SLAM quality improves with RL-generated trajectories

Method scales across different SLAM frameworks

Effective in both simulation and real-world experiments

Abstract

Monocular SLAM refers to using a single camera to estimate robot ego motion while building a map of the environment. While Monocular SLAM is a well studied problem, automating Monocular SLAM by integrating it with trajectory planning frameworks is particularly challenging. This paper presents a novel formulation based on Reinforcement Learning (RL) that generates fail safe trajectories wherein the SLAM generated outputs do not deviate largely from their true values. Quintessentially, the RL framework successfully learns the otherwise complex relation between perceptual inputs and motor actions and uses this knowledge to generate trajectories that do not cause failure of SLAM. We show systematically in simulations how the quality of the SLAM dramatically improves when trajectories are computed using RL. Our method scales effectively across Monocular SLAM frameworks in both simulation and in real world experiments with a mobile robot.