A Hybrid Technique for Active SLAM Based on RPPO Model With Transfer Learning

ABSTRACT

The problem of exploration in unknown environments is still a great challenge for autonomous mobile robots due to the lack of a priori knowledge. Active Simultaneous Localization and Mapping (SLAM) is an effective method to realize obstacle avoidance and autonomous navigation. Traditional Active SLAM is usually complex to model and difficult to adapt automatically to new operating areas. This paper presents a novel hybrid technique for Active SLAM algorithm based on Deep Reinforcement Learning (DRL). The Relational Proximal Policy Optimization (RPPO) model with deep separable convolution and data batch processing is used to predict the action strategy and generate the action plan through the acquired environment RGB images, so as to realize the autonomous collision free exploration of the environment. Meanwhile, Gmapping is applied to locate and map the environment. The data show that the new RPPO model has higher training efficiency due to the 30 percent reduction of training time per round, and the exploration efficiency is significantly improved under the premise of effective obstacle avoidance. Then, on the basis of the Transfer Learning, the Active SLAM algorithm is further trained in a more complex environment to optimize the model parameters to adapt to the new complex environment. Finally, we conduct several experiments to demonstrate the feasibility of the Active scanning algorithm in a gradually complex environment for the task of effective exploration and mapping that needs to be completed.