Deep Reinforcement Learning Based Loop Closure Detection

In this work, we investigate loop closure detection through a deep reinforcement learning approach. The loop closure detection problem correctly identifies a location or area a robot has previously visited. We propose a reward-driven optimization process that strives to learn loop closure detection. We demonstrate the framework in a simulated grid environment that generates observation data for a learning agent. We designed a grid-based environment to simulate indoor environments and train a policy for loop closure detection. A conversion of real-world map and features to the simulated environment is also demonstrated. The learning agent was tested in simulation and indoor lab environments. Our experimental results show that our algorithm can perform loop closure detection effectively.