The combination of simultaneous localization and mapping (SLAM) and frontier exploration enables a robot to traverse and map an unknown area autonomously. Most prior autonomous SLAM solutions utilize information only from depth sensing devices. However, in situations where the main goal is to collect data from auxiliary sensors such as thermal camera, existing approaches require two passes: one pass to create a map of the environment and another to collect the auxiliary data, which is time consuming and energy inefficient. We propose a sensor-aware frontier exploration algorithm that enables the robot to perform map construction and auxiliary data collection in one pass. Specifically, our method uses a real-time ray tracing technique to construct a map that encodes unvisited locations from the perspective of auxiliary sensors rather than depth sensors; this encourages the robot to fully explore those areas to complete the data collection task and map making in one pass. Our proposed exploration framework is deployed on a LoCoBot with the task to collect thermal images from building envelopes. We validate with experiments in both multi-room commercial buildings and cluttered residential buildings. Using a metric that evaluates the coverage of sensor data, our method significantly outperforms the baseline method with a naive SLAM algorithm.
Simultaneous localization and mapping (SLAM) is a computational problem reconstructing the 3D environment map and estimating the camera trajectories simultaneously. This research topic has been studied for several decades in computer vision field. Among many other components in SLAM, we are concentrating on a loop closure detection determining whether a current view is visited by a camera agent before or not. It is an essential procedure for obtaining a consistent 3D environment map. In this paper, we propose a learning based local patch descriptor using a generative adversarial network to solve a problem of the loop closure detection. We trained the generative adversarial network on local patches of a place-oriented dataset and used the network model to extract the local patch descriptor. By using the descriptor on a general bag-of-visual-word method, we achieved better results than the conventional methods in terms of the precision and recall measure.