Design and Application of an Autonomous Surface Vehicle with an AI-Based Sensing Capability

Unmanned autonomous vehicles have been used for military, shipping, transportation, and scientific research applications for decades. Following the advancement of artificial intelligence (AI) technology, autonomous vehicles now possess increased potential for sensing applications. AI-based sensing technologies not only reduce the complication of the data process, but also provide real time sensing results. This study demonstrates the design and applications of an ASV with an AI-based sensor. The functions of the proposed ASV include autonomous sailing, remote communications, smart 3D mapping, and real-time image detection and identification. In addition, the ASV also can sail in dangerous or shallow waters. The experimental results presented herein verify the performances of the proposed functions. The open module design of the ASV can lead to further developments of AI-based sensing applications.

[1]  Csaba Benedek,et al.  Instant Object Detection in Lidar Point Clouds , 2017, IEEE Geoscience and Remote Sensing Letters.

[2]  Fouad Bousetouane,et al.  Fast CNN surveillance pipeline for fine-grained vessel classification and detection in maritime scenarios , 2016, 2016 13th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[3]  Alberto Quattrini Li,et al.  An Autonomous Surface Vehicle for Long Term Operations , 2018, OCEANS 2018 MTS/IEEE Charleston.

[4]  Hanumant Singh,et al.  The WHOI Jetyak: An autonomous surface vehicle for oceanographic research in shallow or dangerous waters , 2014, 2014 IEEE/OES Autonomous Underwater Vehicles (AUV).

[5]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[6]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[7]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[8]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[10]  Chao Wu,et al.  Research of obstacle recognition method for USV based on laser radar , 2017, 2017 4th International Conference on Transportation Information and Safety (ICTIS).