Autonomous Underwater Vehicles (AUVs) are becoming common tools for scientists and underwater contractors. AUVs were traditionally developed for science and military applications but are increasingly becoming viable for commercial ventures such as seabed surveys, oceanographic data collection, offshore oil and gas operations, and military applications.

Data collected from AUVs provide significant cost savings in terms of reduced personnel hours, 24-hour sampling capabilities, and reduced surface ship support. Given low purchase prices ($147,200 for a Fetch2 AUV from Sias Patterson to $300,000 for Hydroid's Remus) and minimal operational budget requirements, it is not difficult to imagine that AUVs will significantly augment ship-based marine resource surveys in the very near future.

This article is not intended to be a complete review of the many missions AUVs have performed while in the service of military or research operations, but to outline the scientific uses of this robust technology and give a recent example of such use. Of particular interest are the smaller AUVs that are well-suited to littoral and estuarine research and require relatively simple and inexpensive logistical support infrastructure (such as ships, technicians, etc.).

More than 60 vehicle designs are now operational at US and worldwide research institutions. This number does not include one-off vehicles developed by and for the military.

While there are many one-off vehicles in operation, there are currently only three commercial US vendors of small work-class AUVs - Sias Patterson, Hydroid, and Bluefin Robotics. The term work-class denotes the ability for sustained mission duration (more than four hours), mission-specific and reconfigurable control software, and reasonable sensor payload capacity.

The small AUV has significant benefits over the larger AUVs that are currently in service, including simplified tooling and consequently lowered manufacturing costs. The smaller vehicles are less cumbersome and don't require costly deployment and recovery systems. Their batteries are less expensive and they have less risk of collisions and deleterious interactions with other items in the coastal ocean. Survey-class AUVs, such as the C&C Technologies/Kongsberg Simrad Hugin, Subsea 7's HS Autosub, and the Maridan vehicles, tend to be larger, have greater endurance and depth capabilities, and often greater payload capacity. Yet they suffer from significant operational and ownership costs and increased logistical requirements. These vehicles have been extensively reviewed elsewhere and will not be discussed in this article.

Of equal or possibly greater importance is the performance of onboard sensors and processing capabilities of the AUV. Sensors typically found on most small AUVs include sidescan sonar, multibeam swath bathymetry, nutrient video cameras, current-temperature-depth (CTD) sensors, acoustic Doppler current velocimeters (ADCP), and numerous other sensor payloads. This article will highlight one recent development in neural network based, automated species recognition of fish, in addition to other objects, imaged with sidescan sonar.

Sias Patterson's Fetch2
The second-generation Fetch AUV from Sias Patterson is the newest and perhaps most revolutionary of the small work class vehicles currently available. Fetch2 is a small, multipurpose, networkable AUV that uses off-the-shelf components. It can be programmed by operators who are not experts in robotics.

Size and performance specifications include a length of 77 inches, diameter of 11.5 inches, and weight of 160 pounds. Typical survey speed is five knots, with top speed reaching nine knots. Mission duration is more than 22 hours at survey speed and eight hours at maximum speed. Fetch2 has a maximum rated depth of 500 feet (150m). A 1,000-foot (300m) model is currently under construction and will become commercially available later this year.

The vehicle incorporates a low-drag, hydrodynamic hull shape and has folding forward dive planes, aft rudders and communications mast to aid launch and recovery. The non-cruciform control surface configuration also allows for unparalleled maneuverability.

Hydroid's Remus
The Remote Environmental Measuring Unit System, or Remus, is a small shallow-water AUV that was developed at the Woods Hole Oceanographic Institute. It is marketed by Hydroid under commercial license.

Remus is one of the smaller AUVs on the market, with a 7.6-inch diameter and length of 64 inches. It weighs 80 pounds. It is limited to a depth of 330 feet (100m) and has an endurance of 22 hours at low speeds (three knots) and a drastically reduced endurance (0.8 hours) at its top speed of five knots. While slower than the other comparable vehicles, Remus is currently the most prolific AUV on the market, with more than 20 in service or on order. The Remus has logged more than 5,000 missions during the past 10 years.

Bluefin Robotics' Odyssey III
The Odyssey line of AUVs from Bluefin Robotics, a spin-off from the Ocean Engineering Department of the Massachusetts Institute of Technology, is a study in manufacturing and design elegance. It is the only AUV listed here that uses a wet, or flooded, hull design.

Vehicle and mission components are sealed in pressure vessels and placed within a hydrodynamic, very low drag fairing. This allows the vehicle to obtain depths of 14,760 (4,500m) yet maintain a relatively small size.

The vehicle is eight feet long, has a diameter of 21 inches, and weighs 450 pounds. Normal survey speed is three knots and it has a range of 30 miles (or just over nine hours of endurance). Pricing for the Odyssey is around $300,000 for a basic vehicle. The vehicle is now in its third generation and has performed science missions all over the world, including under the Arctic ice pack.

Neural Network Classifier
AUVs are essentially small, inexpensive research platforms that significantly reduce the spatial and temporal variability that is common to ship-collected data. The future success of AUV deployments will be enhanced by further developments in sensor fusion and the creation of new data collection methodologies. One such development is a neural network classifier of sidescan sonar imagery.

Artificial neural networks (ANNs) are computational models inspired by advances in neuroscience and neurobiology. Essentially, a neural network is composed of many simple processors, called units or nodes, organized into layers that may possess discreet amounts of local memory. Each of these layers and individual units are connected to each other and carry various sorts of numerical data. Each unit processes and passes on, or halts, the data that it receives from other units or layers.

From a biological model, each node or unit is similar to a neuron and the connections between units are similar to synapses. It is important to note that artificial neural networks take their design from biological models but do not attempt to replicate real neural connections. Advances in desktop computing and the availability of numerous robust ANN models have made neural computing a viable solution for pattern recognition and other computational tasks.

The radial basis function (RBF) artificial neural network model has been found to excel at classification of side-scan sonar imagery. RBF networks offer the advantages of high levels of noise immunity and great ability in solving complex, non-linear problems in the fields of speech and pattern recognition, robotics, real-time signal analysis, and other areas dominated by non-linear processes. Once the network has been trained with prototypes or ground-truthed imagery, it can perform recognition tasks on previously unseen data.

Neural network classifiers, using radial basis functions, are a promising tool for analyzing putative fish targets in sidescan sonar images. In a recent study, odontaspids (sand tiger shark) and carangids (crevalle jack) were successfully distinguished from several fish species unknown to the classifier. Classifier success ranged between 90 and 96 percent. These sonar images were gathered in the noise-rich environment of a public aquarium, not under acoustically ideal conditions, thus illustrating the robustness of the RBF classifier.

The classifier has the capability to learn hundreds of species and such networks can make classifications in real time. The constraints on this type of system include the requirement of known, or ground truthed, training data and sufficient variability, either acoustic intensity or shape of the targets, within the imagery.

Combining AUV technology with high-resolution sidescan sonar should provide a useful tool for stock assessment and related fisheries questions, including the delineation of essential fish habitat, especially inhard to sample areas such as reef environments or shallow waters.

What's Next?
The next steps for this technology are the automation and integration of the classifier algorithms into the AUV control software for future adaptive sampling needs. This will enable future, real-time adaptive sampling protocols to be implemented onboard the AUV.

For instance, aggregations of a species in a school could be recognized as the AUV passes by, and the range and bearing computed, which could, in turn, be used to control the speed and path of the AUV. It is anticipated that fisheries research AUVs that can follow individual fishes or schools of fish for extended periods of time will be developed very soon, providing an unprecedented view of habitat utilization and mapping of essential fish habitat. In fact, Iwakami et al., in a recent Marine Technology Society Journal, reported the ability of a large AUV to locate and approach within 50m a humpback whale (Megaptera novaeangliae) using passive sonar tracking algorithms.