Aerial online mapping on-board system by real-time object detection for UGV path generation in unstructured outdoor environments

An optimal path provides efficient operation of unmanned ground vehicles (UGVs) for many kinds of tasks such as transportation, exploration, surveillance, and search and rescue in unstructured areas that include various unexpected obstacles. Various onboard sensors such as LiDAR, radar, sonar, and cameras are used to detect obstacles around the UGVs. However, their range of view is often limited by movable obstacles or barriers, resulting in inefficient path generation. Here, we present the aerial online mapping system to generate an efficient path for a UGV on a two-dimensional map. The map is updated by projecting obstacles detected in the aerial images taken by an unmanned aerial vehicle through an object detector based on a conventional convolutional neural network. The proposed system is implemented in real-time by a skid steering ground vehicle and a quadcopter with relatively small, low-cost embedded systems. The frameworks and each module of the systems are given in detail to evaluate the performance. The system is also demonstrated in unstructured outdoor environments such as in a football field and a park with unreliable communication links. The results show that the aerial online mapping is effective in path generation for autonomous UGVs in real environments.

Automated summary

In this study, an aerial online mapping system is proposed to generate efficient paths for unmanned ground vehicles (UGVs) on a two-dimensional map. The system utilizes aerial images taken by an unmanned aerial vehicle and an object detector based on a convolutional neural network. Experimental results show that this system is effective in path generation for autonomous UGVs in real environments.