Development and fieldwork trial of autonomous surface vehicles for bathymetry mapping

The use of autonomous vehicles is growing in all industries. However, there are no open-source autonomous surface vehicles available in the marine industry. This paper details the design decisions made, construction methods used, and testing performed on a low-cost, open-source vessel. The vessel was designed to cross the Atlantic Ocean as a means of proving its ability to survive the harsh marine environment. A trimaran hull form and free rotating wing sail were used because the combination provided good righting characteristics, durability and low power consumption. The vessel has been shown to navigate autonomously. Total costs were less than $4000 dollars, excluding labor. Vessels of this type could be used for long duration missions recording data in the open ocean at extremely low cost.

Download Full-text

Collision avoidance, guidance and control system for autonomous surface vehicles in complex navigation conditions

Progress in Maritime Technology and Engineering ◽

10.1201/9780429505294-15 ◽

2018 ◽

pp. 121-131 ◽

Cited By ~ 1

Author(s):

M.A. Hinostroza

Keyword(s):

Control System ◽

Collision Avoidance ◽

Guidance And Control ◽

Autonomous Surface Vehicles ◽

And Control

Download Full-text

A Triboelectric-Based Artificial Whisker for Reactive Obstacle Avoidance and Local Mapping

Research ◽

10.34133/2021/9864967 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

Peng Xu ◽

Xingyu Wang ◽

Siyuan Wang ◽

Tianyu Chen ◽

Jianhua Liu ◽

...

Keyword(s):

Obstacle Avoidance ◽

Autonomous Robots ◽

Tactile Sensor ◽

Triboelectric Nanogenerator ◽

Tactile Sensors ◽

Biologically Inspired ◽

External Stimulation ◽

Autonomous Surface Vehicles ◽

Electrostatic Induction ◽

Contact Position

Since designing efficient tactile sensors for autonomous robots is still a challenge, this paper proposes a perceptual system based on a bioinspired triboelectric whisker sensor (TWS) that is aimed at reactive obstacle avoidance and local mapping in unknown environments. The proposed TWS is based on a triboelectric nanogenerator (TENG) and mimics the structure of rat whisker follicles. It operates to generate an output voltage via triboelectrification and electrostatic induction between the PTFE pellet and copper films (0.3 mm thickness), where a forced whisker shaft displaces a PTFE pellet (10 mm diameter). With the help of a biologically inspired structural design, the artificial whisker sensor can sense the contact position and approximate the external stimulation area, particularly in a dark environment. To highlight this sensor’s applicability and scalability, we demonstrate different functions, such as controlling LED lights, reactive obstacle avoidance, and local mapping of autonomous surface vehicles. The results show that the proposed TWS can be used as a tactile sensor for reactive obstacle avoidance and local mapping in robotics.

Download Full-text

A 3-D Lightweight Convolutional Neural Network for Detecting Docking Structures in Cluttered Environments

Marine Technology Society Journal ◽

10.4031/mtsj.55.4.9 ◽

2021 ◽

Vol 55 (4) ◽

pp. 88-98

Author(s):

Maria Inês Pereira ◽

Pedro Nuno Leite ◽

Andry Maykol Pinto

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Research Work ◽

Point Clouds ◽

Measurement Unit ◽

Maritime Industry ◽

Worst Case ◽

Cluttered Environments ◽

Autonomous Surface Vehicles ◽

Average Accuracy

Abstract The maritime industry has been following the paradigm shift toward the automation of typically intelligent procedures, with research regarding autonomous surface vehicles (ASVs) having seen an upward trend in recent years. However, this type of vehicle cannot be employed on a full scale until a few challenges are solved. For example, the docking process of an ASV is still a demanding task that currently requires human intervention. This research work proposes a volumetric convolutional neural network (vCNN) for the detection of docking structures from 3-D data, developed according to a balance between precision and speed. Another contribution of this article is a set of synthetically generated data regarding the context of docking structures. The dataset is composed of LiDAR point clouds, stereo images, GPS, and Inertial Measurement Unit (IMU) information. Several robustness tests carried out with different levels of Gaussian noise demonstrated an average accuracy of 93.34% and a deviation of 5.46% for the worst case. Furthermore, the system was fine-tuned and evaluated in a real commercial harbor, achieving an accuracy of over 96%. The developed classifier is able to detect different types of structures and works faster than other state-of-the-art methods that establish their performance in real environments.

Download Full-text