Hierarchical Semantic Mapping Using Convolutional Neural Networks for Intelligent Service Robotics

The introduction of service robots in the public domain has introduced a paradigm shift in how robots are interacting with people, where robots must learn to autonomously interact with the untrained public instead of being directed by trained personnel. As an example, a hospital service robot is told to deliver medicine to Patient Two in Ward Three. Without awareness of what “Patient Two” or “Ward Three” is, a service robot must systematically explore the environment to perform this task, which requires a long time. The implementation of a Semantic Map allows for robots to perceive the environment similar to people by associating semantic information with spatial information found in geometric maps. Currently, many semantic mapping works provide insufficient or incorrect semantic-metric information to allow a service robot to function dynamically in human-centric environments. This paper proposes a semantic map with a hierarchical semantic organization structure based on a hybrid metric-topological map leveraging convolutional neural networks and spatial room segmentation methods. Our results are validated using multiple simulated and real environments on our lab's custom developed mobile service robot and demonstrate an application of semantic maps by providing only vocal commands. We show that this proposed method provides better capabilities in terms of semantic map labeling and retain multiple levels of semantic information.