Tracking Sharks With Robots

Scientists have been tracking sharks with robots for years, but a new design is able to do this while following the animal. Biologists from Mote Marine Laboratory and engineers at Harvey Mudd College developed the system using off-the-shelf components.

It has a powerful gripping force capable of enduring pull-off forces 340 times its own weight. It also can detect changes in objects and adjust its course in line with the changes.

Autonomous Underwater Vehicles (AUVs)

Autonomous underwater vehicles (AUV) are robots that are programmable and according to the design they can drift or travel through the ocean without any human supervision in real-time. They are equipped with sensors that can record water parameters, map and map features of the ocean's geology and habitats and more.

They are controlled by a surface ship with Wi-Fi or acoustic connections for sending data back to the operator. The AUVS can be used to collect any type of spatial or temporal samples and are able to be deployed in large groups to cover more ground faster than could be done by the use of a single vehicle.

Similar to their land counterparts, AUVs can navigate using GPS and a Global Navigation Satellite System (GNSS) to determine where they are in the world and how far they've traveled from their starting point. This information, in conjunction with sensors for the environment that send information to the computer systems onboard, allows AUVs follow their intended course without losing sight of their destination.

When a research mission is complete, the AUV will be able to float to the surface, and be recovered on the research vessel from which it was launched. A resident AUV may also remain underwater for months and perform regular inspections pre-programmed. In either scenario, an AUV will periodically surface in order to signal its location using an GPS or acoustic signal which is transmitted to the surface vessel.

Certain AUVs can communicate with their operators continuously through a satellite connection on the research vessel. Scientists can continue their experiments on the ship while the AUV collects data under water. Other AUVs communicate with their operators at certain times. For example when they require to refill their sensors or verify their status.

Free Think claims that AUVs are not just used to collect data from oceanography but can also be used to search underwater resources, such as minerals and gas. They can also be utilized to assist in environmental disaster response and assist in rescue and search operations following oil spills or tsunamis. They can also be used to monitor volcanic activity in subsurface areas and to monitor the health of marine life, such as coral reefs and whale populations.

Curious Robots

Unlike traditional undersea robots, that are programmed to search for a single element of the ocean floor The curious robots are built to be able to see and adjust to changing conditions. This is important, because the conditions below the waves is often unpredictable. For example, if the water suddenly gets warmer, it could change the behavior of marine creatures or even lead to an oil spill. Curious robots can spot these changes quickly and efficiently.

Researchers are working on a new robotic platform which uses reinforcement learning to train robots to be curious. The robot, which looks like the image of a child wearing an orange jacket with a green hand, can be taught to recognize patterns, which could signal a fascinating discovery. It is also able to decide what it should do next depending on the results of its previous actions. The results of this research could be applied to create a robot that is capable of learning on its own and adapting to the changing environment.

Scientists are also using robots to study areas that are dangerous for humans to dive. Woods Hole Oceanographic Institution's (WHOI) for instance, has a robot called WARP-AUV that is used to investigate shipwrecks and locate them. The robot can recognize reef creatures and discern jellyfish and semi-transparent fish from their dim backgrounds.

It takes years of training to train an individual to be able to do this. The brain of the WARP-AUV has been trained to recognize familiar species after thousands of images have been fed into it. In addition to its capabilities as a marine sleuth, the WARP-AUV has the ability to send topside supervisors real-time images of underwater scenes and sea creatures.

Other teams are working to create robots that have the same curiosity as humans. A team from the University of Washington’s Paul G. Allen school of Computer Science & Engineering, for instance, is examining how robots can be taught to be curious about their surroundings. This team is a part of a Honda Research Institute USA initiative to develop machines that are curious.

Remote Missions

There are a lot of uncertainties in space missions that can cause mission failure. Scientists don't know how long a mission will last and how well components of the spacecraft will function and if other forces or objects might interfere with spacecraft operation. The Remote Agent software is designed to help reduce the uncertainty. It can perform many of the complex tasks ground control personnel would do if they were on DS1 at the time of the mission.

The Remote Agent software system includes an executive planner/scheduler model-based reasoning algorithm. The planner/scheduler generates a set of time-based and event-based activities called tokens. These are sent to the executive. The executive determines how to expand these tokens into a sequence of commands to be directly sent to the spacecraft.

During the experiment during the test, a DS1 crew member is available to assist in resolving any issues that occur outside of the scope of the test. All regional bureaus must adhere to Department requirements for records management and keep all documentation used in conjunction with establishing the remote mission.

REMUS SharkCam

Researchers aren't aware of the actions of sharks below the surface. However, scientists using an autonomous underwater vehicle called SharkCam from REMUS are beginning to penetrate the blue layer, and the results are both incredible and terrifying.

The SharkCam team is a group of Woods Hole Oceanographic Institution, took the torpedo-shaped SharkCam to Guadalupe Island last year to track and film great white sharks in their natural habitat. The 13 hours of video footage combined with visuals from acoustic tags attached to sharks, provide much about the underwater behavior of these predators.

The REMUS SharkCam, which is developed in Pocasset, MA by Hydroid it is designed to track the location of a animal that is tagged without disrupting its behavior or causing alarm. It employs an multidirectional ultra-short baseline navigation device to determine the range, bearing, and depth of the shark. It then it closes in at a predetermined distance and location (left, right, above or below) to capture it swimming and interacting with its environment. It communicates with scientists at the surface every 20 seconds, and can respond to commands to alter its speed or depth, as well as standoff distance.

State shark scientist Greg Skomal, WHOI engineer Amy Kukulya, Pelagios-Kakunja Shark RV2610WA: Advanced AI Robot Vacuum And Mop researcher Edgar Mauricio Hoyos-Padilla from Mexico's Marine Conservation Society and REMUS SharkCam software creator Roger Stokey first envisioned tracking and filming great white sharks using the self-propelled torpedo, which they named REMUS SharkCam, they worried that it could disturb the sharks' movements and potentially make them flee the area they were studying. Skomal and his colleagues, reported in a recent paper published in the Journal of Fish Biology that the SharkCam was able to stand up to nine bumps and a biting attack from great whites that weighed tens of thousands of pounds over a week of research along the coast of Guadalupe.

Researchers interpreted the interactions of sharks and REMUS SharkCam (which had been tracking four sharks that were tagged) as predatory behavior. Researchers recorded 30 Efficient Shark AI Ultra Robot Vacuum with Mapping And Self-Emptying interactions including simple bumps and nine bites that were aggressive.