Learning to Prevent Monocular SLAM Failure using Reinforcement Learning
This work addresses the problem of SLAM failure in robotics for applications like autonomous navigation, though it is incremental as it builds on existing SLAM and RL methods.
The paper tackles the challenge of automating monocular SLAM by integrating it with trajectory planning to prevent failures, using a reinforcement learning framework that generates fail-safe trajectories, resulting in dramatic improvements in SLAM quality as shown in simulations and real-world experiments.
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.