US Navy’s Autonomous surface vehicle, ACTUV developed to track quiet diesel-electric submarines, successfully navigated autonomously

Rajesh Uppal June 24, 2020 Navy, Unmanned Comments Off on US Navy’s Autonomous surface vehicle, ACTUV developed to track quiet diesel-electric submarines, successfully navigated autonomously 1,425 Views

China, Russia and North Korea are looking to develop their submarine fleets . Russia is seeking to further bolster its sub-surface capabilities, with new generations of conventional and nuclear propulsion submarines, which promise to be significantly more difficult to detect and track for western naval forces. This includes the Yasen, Lada, Borei and Kalina classes of submarines. According to some estimates, Beijing’s diesel-electric submarine fleet could grow from roughly fifty in 2016 to seventy-five in 2030.

Improving America’s ASW capability is a pressing need, given the proliferation in the number and sophistication of enemy submarines. DARPA launched Anti-Submarine Warfare (ASW) Continuous Trail Unmanned Vessel (ACTUV) program — pronounced “active” — originally conceived as a project to create an unmanned underwater drone that could track enemy submarines. The aim of DARPA’s ACTUV project was to develop an unmanned surface vessel that will be able to locate and track submarines deep under the water, at levels of precision, persistence and flexibility beyond those capabilities available by manned surface ships operating anti-submarine warfare.

DARPA believes using large numbers of inexpensive unmanned ACTUVs are a way to counter submarines as an undersea component of anti-access warfare. “ACTUV represents a new vision of naval surface warfare that trades small numbers of very capable, high-value assets for large numbers of commoditized, simpler platforms that are more capable in the aggregate,” said Fred Kennedy, director of DARPA’s Tactical Technology Office (TTO).

While other unmanned water vessels have been limited by their need to be deployed from a larger ship and remotely-controlled, the 120-foot Sea Hunter is autonomous and designed to be able to launch from a pier and function on its own for up to months at a time and travel for thousands of miles. The ship, which was built by defense contractor Leidos, is currently undergoing trials as part of a joint project with the U.S. Office of Naval Research.

The Class III unmanned surface vessel (USV) has the potential to traverse thousands of kilometres of open ocean for months without a single crew member aboard and at a fraction of current costs – estimates range from $15,000-$20,000 a day compared with $700,000 a day to operate a destroyer. And should an enemy submarine be detected , it would guide U.S. Navy warships or aircraft to the sub’s location to destroy it (the Sea Hunter does not carry any weapons systems). According to DARPA, Sea Hunter could ultimately lead to a whole new class of ocean-going vessel and eradicate the need for larger manned warships, transforming conventional submarine warfare.

In addition to hunting enemy subs, ACTUV will be capable of a wide range of missions, such as reconnaissance and counter-mine deployments. It could also be useful to resupply troops. A suite of sensors “capable of tracking quiet, modern diesel electric submarines” will be implemented, including very high frequency sonar that will produce an “acoustic image” of the target to identify and classify the specific submarine. ACTUV will be smart, it will not just identify other vessels, but also predict how they will behave.

DARPA program manager Ellison Urban, quoted by Defense One, explains the rationale behind the U.S. Navy’s push for robot ships: Instead of chasing down these submarines and trying to keep track of them with expensive nuclear powered-submarines, which is the way we do it now, we want to try and build this at significantly reduced cost. It will be able to transit by itself across thousands of kilometers of ocean and it can deploy for months at a time. It can go out, find a diesel-electric submarine, and just ping on it.

The prototype submarine tracking vessel was ordered in 2012 by the Defense Advanced Research Projects Agency (DARPA), launched in January 2016 and christened Sea Hunter two months later. In October 2016, DARPA and ONR began at-sea testing of Sea Hunter’s sensing and autonomy suites. Between February and September 2017, the vessel passed three progressively challenging tests to integrate the suites and use them to comply with International Regulations for Preventing Collisions at Sea (COLREGS) in operationally realistic scenarios.

DARPA successfully completed its Anti-Submarine Warfare (ASW) Continuous Trail Unmanned Vessel (ACTUV) program in 2018 and has officially transferred the technology demonstration vessel, christened Sea Hunter, to the Office of Naval Research (ONR). ONR will continue developing the revolutionary prototype vehicle as the Medium Displacement Unmanned Surface Vehicle (MDUSV).

The ONR is planning to assess the vessel’s suitability for roles other than submarine hunting, such as logistics support, hydrographic survey and surveillance. Sea Hunter has already demonstrated the Towed Airborne Lift of Naval Systems (TALONS), employing a parakite to elevate various sensors, increasing their range and enhancing the vessel’s situational awareness.

ONR plans additional at-sea tests to further develop ACTUV/MDUSV technologies, including automating payload and sensor data processing, rapidly developing new mission-specific autonomous behaviors, and exploring autonomous coordination among multiple USVs.

The U.S. Navy plans to establish a Surface Development Squadron (SURFDEVRON) to help with the integration of future autonomous platforms like the sub-hunting robot ship Sea Hunter, in an ongoing effort to make U.S. naval surface forces more distributed and reliant on unmanned ships and aircraft, according to local media report.

The new SURFDEVRON will help integrate the new platform and subsequent USVs into the surface fleet. “We’ve got to figure out command and control,” Brown told Defense News. “We’ve got to figure out the man, train and equip aspects — there’s got to be an administrative commander in charge of them, got to be a guy who equips those things, got to be a guy who oversees the training of the people who interact with and use the USVs.”

Rise of the robots: unmanned fleets of the future

DARPA had developed ACTUV, an unmanned surface vehicle (USV) designed to operate and patrol autonomously for 60-90 days straight, tracking quiet diesel-electric submarines and avoid surface ships by itself. The ACTUV is designed to out-endure any diesel-electric submarine, even those equipped with Air Independent Propulsion (AIP) at a fraction of their size and cost. Once the enemy sub is spotted it could guide other U.S. naval assets to the vessel’s location to destroy it.The ACTUV enemy submarine hunter is about 130 feet long and capable of 27 knots. Its extremely slender hull form has a composite fiberglass shell and a foam core to provide structural resilience in conditions up to Sea State 7.

In an interview with Reuters in 2016, former US Deputy Defense Secretary Robert Work said he believed USVs in general, and Sea Hunter in particular, could revolutionise maritime operations. “This is an inflection point,” he said. “This is the first time we’ve ever had a totally robotic, trans-oceanic-capable ship.”

Able to endure up to 90 days at sea without a crew and with an estimated range of 10,000 nautical miles, fleets of unmanned ships could also provide 24/7 protection for inlets, harbours and other sensitive maritime locations, and deliver missiles, torpedoes and other supplies to vessels at sea. “I would like to see unmanned flotillas operating in the western Pacific and the Persian Gulf within five years,” he added, going on to emphasise that such fleets would always be under human control. “There’s no reason to be afraid of a ship like this.”

The ACTUV program was initiated in 2010 and in November 2012 DARPA awarded Leidos a $59 million contract to design, build and test the prototype vessel. The vessel was launched in January 2016 and named Sea Hunter two months later.

The ONR’s commanding officer, Rear Admiral David Hahn, said “It’s being handed over to the ONR so that we can now start to embed it with other warfighting capabilities and truly start to explore how you team with unmanned surface vehicles for warfighting”, he said. This work will include developing a concept of operations for Sea Hunter and defining its performance envelope.

Asked if the ACTUV would receive a self-defense capability, Hahn replied: “It’s certainly something we need to explore as we think about that vehicle [operating] alone, as opposed to operating in concert with a battle group or other surface formation.”

ACTUV program is structured around three primary goals

Explore the performance potential of a surface platform conceived from concept to field demonstration under the premise that a human is never intended to step aboard at any point in its operating cycle. As a result, a new design paradigm emerges with reduced constraints on conventional naval architecture elements such as layout, accessibility, crew support systems, and reserve buoyancy. The objective is to generate a vessel design that exceeds state-of-the art platform performance to provide propulsive overmatch against diesel electric submarines at a fraction of their size and cost.

Advance unmanned maritime system autonomy to enable independently deploying systems capable of missions spanning thousands of kilometers of range and months of endurance under a sparse remote supervisory control model. This includes autonomous compliance with maritime laws and conventions for safe navigation, autonomous system management for operational reliability, and autonomous interactions with an intelligent adversary.

Demonstrate the capability of the ACTUV system to use its unique characteristics to employ non-conventional sensor technologies that achieve robust continuous track of the quietest submarine targets over their entire operating envelope.

High degree of autonomy, AI based

On a competitive basis, the American company Science Applications International Corporation was selected as the lead developer of the device. The ACTUV device must follow the submarines at a distance of up to 3,000 km from its base in remote or autonomous mode. The range of navigation apparatus will be more than 6,000 km, and autonomy – 80 days.

The device will float at the periscope depth and search for enemy submarines using an active hydroacoustic station. If a submarine is detected, the device will continuously monitor it and transfer information about the coordinates to the control center and its anti-submarine forces. According to the requirements of DARPA, the device must carry out three patrols per year (each with a cycle of 80 days at sea and 40 days of service at the base), have a lifetime of 15 years and cost no more than $ 20 million. The control system of the apparatus must be highly autonomous, allow independent actions in case of significant interruptions in communication with the control center and enable them to make decisions independently in various tactical situations. The device will have a warning system for collisions at sea.

ACTUV is focused on providing a high degree of autonomy,” said program manager Scott Littlefield. “It’s not just a remote controlled boat.” Computers will drive and control the ship, Littlefield said, but a human will always be observing, able to take charge if necessary. The concept, called Sparse Supervisory Control, means “the human being is in control, but not joy sticking the vessel around,” Littlefield said.

AI currently exists in two waves. The first wave of systems have imparted handcrafted knowledge which enables reasoning over narrowly defined problems, but have no learning capability and poor handling of uncertainty. The second wave of the technology is capable of statistical learning and has the ability to visually perceive – such as in the case of facial or voice recognition, but poor abstracting and reasoning capability.

‘To characterise this current very powerful second wave of technologies, we would say they have nuanced ability to classify data and even to predict the consequences of data, but they don’t really have any ability to understand the context in which they are taking place and minimal capability to reason,’ John Launchbury, the director of DARPA’s Information Innovation Office (I2O), said.

These first and second wave technologies are currently being combined to create very powerful platforms that have the potential to reshape defence missions. A great example here is DARPA’s Anti-Submarine Warfare Continuous Trail Unmanned Vessel (ACTUV) technology demonstration vessel, recently launched to spend months alone at sea with no human operator giving it directions, including understanding what other vessels are doing, navigate sea lanes and carry out its tasks.

The third wave of artificial intelligence will be built around contextual models where the system over time will learn about how that model will be structured; it will perceive the world in terms of that model, it will be able to use that model to reason and make decisions and even to abstract, to take data further.

Launchbury uses an example of a system that is intended to classify images. Give such a system and image of a cat and it will say, ‘That’s a cat’. When asked why it is a cat, the system will say, ‘I did my calculations and cat came out as highest’. ‘That’s not satisfactory. We’d much prefer the system to be able to respond to us and say, ‘Well, it has ears, and paws, and fur, and these other features,’ Launchbury said. ‘This kind of building the ability in these systems to understand or have clarity as to why they are making these decision is going to be very important.’

Highly Autonomous

The ACTUV autonomy suite contains decision algorithms embedded as software modules using an object-oriented framework in which key interface definitions isolate algorithm implementations. It supports multiple, simultaneously executing decision engines and the arbitration logic to choose the best decisions for future actions. It implements a true open systems architecture (OSA) approach that allows for the autonomy capability to be modularly connected to other subsystems—within the same platform and external to the platform. This “plug-and-play” modularity minimizes life-cycle costs, enables reuse, and promotes healthy competition among capability vendors. It also reduces overall risk to the program. In addition, the autonomy capability implements the Service Availability Forum industry standards to achieve a high-availability solution that results in near-continuous uptime when the system is fully integrated.

The OSA uses the Society of Automotive Engineers (SAE) AS4 Joint Architecture for Unmanned Systems (JAUS) messaging between major segments and the OMG Data Distribution Service (DDS) message protocol layer to achieve advanced quality of service. The autonomy engine is a set of algorithm-level specifications for the behaviors and capabilities of the autonomy platform. It lists all the important, high-level, mission-oriented tasks either planned or implemented in the context of the vehicle scenario. It employs a modular approach that supports a Distributed Hierarchical Autonomy (DHA) model and uses replaceable, modular and standard interfaces.

After satisfactory completion of SIL testing, the autonomy suite was installed on a 42-foot test vessel, where frequency-modulated continuous-wave and “X”-band radars provided the sensor input to the autonomy suite, and commands from the autonomy suite were forwarded to the vessel’s autopilot for control of the rudder and engines. The test vessel acted as an ACTUV surrogate and allowed for testing of all the autonomy software and ACTUV sensor systems in parallel with the ACTUV ship construction. These tests successfully demonstrated a fully autonomous capability in a manner fully compliant with international collision regulations.

Sensor and Payloads

In its ASW role, it receives off-board cueing and hand off, then conducts an overt trail with active sonar. It can act as an ASW scout in coordination with area ASW assets like the P-8, conducting large acoustic surveillance using passive and/or active bistatic Surveillance Towed Array Sensor System (SURTASS). It can deploy three Mk-54 or six CRAW torpedoes. In its ISR role, it can work with a surface adaptive force package as an advanced scout employing passive RF, IO/IR and UAV sensors, and in an offensive role, can carry eight RBS-15 surface-to-surface missiles.

What DARPA thinks make the Sea Hunter unique, however, are sophisticated sensors which can locate virtually silent enemy submarines. Retrieving the underwater GPS coordinates of stealthy diesel-electric submarines in busy waterways is akin to “trying to identify the sound of a single car engine in the din of a major city,” Rear Adm. Frank Drennan, a senior anti-submarine warfare official said 10 January 2017.

Onboard the ACTUV there are active-passive sonars operating in the mid and high frequency range. The former are able to detect underwater targets at long distances, and the latter serve to clarify their parameters. Additional information is collected by arrays of magnetometers with digital signal processing. At short distances, an ultra-high-frequency sonar is activated to obtain an accurate “acoustic image” of the target and its automatic classification. DARPA has also been working on developing non-conventional sensor technologies to enable the correct identification of surface ships and other objects while at sea.

The MDUSV is equipped with navigation and piloting sensors, electro-optics, and long and short range radar. The MDUSV’s modular design allows it to not only carry out anti-submarine warfare operations, but to be refitted for intelligence, surveillance, and reconnaissance missions. In addition, the vessel is able to report back on the situation and its condition and has computers programmed to identify other vessels and predict what they will do next.

ACTUV’s system for sensing other vessels is based on radar, which provides a “90 percent solution” for detecting other ships. However, radar is less suitable for classification of the type of other vessels, for example determining whether the vessel is a powered vessel or a sailboat.

DARPA had issued a Request for Information (RFI), to augment ACTUV’s capability for sensing and classifying other vessels. DARPA is specifically interested in sensor systems and image-processing hardware and software that use passive (electro-optical/infrared, or EO/IR) or non-radar active (e.g., light detection and ranging, or LIDAR) approaches. The goal is to develop reliable, robust onboard systems that could detect and track nearby surface vessels and potential navigation hazards, classify those objects’ characteristics and provide input to ACTUV’s autonomy software to facilitate correct COLREGs behaviors.

International Regulations for Preventing Collisions at Sea, known as COLREGS

The technical breakthrough is in the autonomy. Sea Hunter’s autonomous control system allows it to operate while avoiding hazards and in compliance with International Regulations for Preventing Collisions at Sea. Sea Hunter’s autonomous control system leverages components of ONR’s CARACaS (Control Architecture for Robotic Agent Command and Sensing) system that has been developed by ONR used in the “USV Swarm” multi-USV demonstrations in 2014 and 2016.

USV Swarm has demonstrated mission-specific “behaviors” such as escort, attack, patrol, intercept, track and trail. These behaviors are what provide a USV a mission capability. Behaviors such as these will be added to Sea Hunter and will be evaluated in future fleet experimentation. Inclusion of autonomous control is a significant advancement in USV capability. DARPA allowed the national security, health, and engineering company Leidos to go forward with the ACTUV program in February 2014. Leidos has completed at-sea demonstrations to fulfill collision regulations (COLREGS).

DARPA Completes Successful testing of ACTUV with TALONS (low-cost, elevated sensor mast carrying ISR payload )

DARPA’s Anti-Submarine Warfare (ASW) Continuous Trail Unmanned Vessel (ACTUV) program has developed and built a technology demonstration vessel that is currently undergoing open-water testing off the coast of California and recently set sail with its first payload: a prototype of a low-cost, elevated sensor mast developed through the Agency’s Towed Airborne Lift of Naval Systems (TALONS) research effort.

TALONS is a parafoil-based flying system capable of carrying up to 150 pounds of intelligence, surveillance, reconnaissance and communications payloads, while flying between 500 and 1,500 feet, equivalent to the height of a skyscraper.

While aloft, TALONS demonstrated significant improvements to the range of the sensors and radios it carried compared to mounting them directly on a surface vessel. For example, TALONS’ surface-track radar extended its range by 500 percent—six times—compared to its range at sea level. Its electro-optical/infrared scanner doubled its observed discrimination range. The TALONS team plugged in a commercial handheld omnidirectional radio; that radio’s range more than tripled.

“TALONS showed the advantages of using a low-cost add-on elevated sensor to extend the vision and connectivity of a surface asset and ACTUV demonstrated its ability as a flexible and robust payload truck,” said Dan Patt, DARPA program manager for TALONS. “This demonstration was an important milestone in showing how clever use of unmanned systems could cost-effectively provide improved capabilities.”

For this exercise, the TALONS system started off on the back of the ACTUV in a “nest.” Once it launched, it reached 1,000 feet and tested its onboard sensors and communications equipment. After completing its test, the TALONS returned to its nest on the back of the ACTUV vehicle while the vehicle maintained its same speed in the water.