Relevance: supporting · Type: background
Confidence100%
Ships currently find breaks in underwater power cables by pulling up the entire cable or deploying remotely operated vehicles to traverse the line.
Relevance: primary · Type: background
Confidence100%
An MIT Lincoln Laboratory project focuses on underwater human-robot teaming.
Relevance: supporting · Type: background
Confidence100%
The project is funded through an internally administered R&D portfolio on autonomous systems.
Relevance: supporting · Type: background
Confidence100%
The project is carried out by the Advanced Undersea Systems and Technology Group.
Relevance: primary · Type: background
Confidence100%
The project aims to optimize maritime missions for the U.S. military, including critical infrastructure inspection and repair, search and rescue, harbor entry, and countermine operations.
Madeline Miller, principal investigator
Relevance: supporting · Type: quote
Confidence100%
"Divers and AUVs generally don't team at all underwater,"
Relevance: supporting · Type: background
Confidence100%
Underwater missions requiring humans typically involve manipulation tasks that robots cannot perform, such as repairing infrastructure or deactivating mines.
Relevance: supporting · Type: background
Confidence100%
Remotely operated vehicles face challenges in skilled underwater manipulation tasks because their manipulators lack sufficient agility.
Relevance: supporting · Type: background
Confidence100%
Humans have superior dexterity and excel at recognizing objects underwater.
Relevance: supporting · Type: background
Confidence100%
Humans working underwater cannot perform complex computations or move very quickly when carrying heavy equipment.
Relevance: supporting · Type: background
Confidence100%
Robots have advantages in processing power, high-speed mobility, and endurance over humans in underwater operations.
Relevance: primary · Type: action
Confidence100%
Miller and her team are developing hardware and algorithms for underwater navigation and perception.
Relevance: supporting · Type: background
Confidence100%
Divers may navigate using only a compass and fin-kick counts.
Relevance: supporting · Type: background
Confidence100%
Underwater conditions such as few landmarks, low light at depth, and biological matter in the water column can cause divers to become disoriented and lost.
Relevance: supporting · Type: background
Confidence100%
Optical sensors cannot generate images in dark or turbid underwater conditions.
Relevance: supporting · Type: background
Confidence100%
Acoustic sensors generate images that lack color and show only shapes and shadows of objects in the scene.
Relevance: supporting · Type: background
Confidence100%
A historical lack of large, labeled sonar image datasets has hindered the training of underwater perception algorithms.
Relevance: supporting · Type: background
Confidence100%
In dynamic ocean environments, objects such as downed aircraft broken into multiple pieces or tires covered with mussels may not resemble their original forms, potentially confusing artificial intelligence.
Madeline Miller, principal investigator
Relevance: primary · Type: quote
Confidence100%
"Ultimately, we want to devise solutions for navigation and perception in expeditionary environments. For the missions we're thinking about, there is limited or no opportunity to map out the area in advance. For the harbor entry mission, maybe you have a satellite map but no underwater map, for example."
Relevance: supporting · Type: background
Confidence100%
Miller's team built upon work by the MIT Marine Robotics Group, led by John Leonard, to develop diver-AUV teaming algorithms.
Relevance: supporting · Type: event
Confidence100%
Leonard's group ran simulations under optimal conditions and performed field testing in calm waters using human-paddled kayaks as proxies for both divers and AUVs.
Relevance: supporting · Type: event
Confidence100%
Miller's team integrated the diver-AUV teaming algorithms into a mission-relevant AUV and tested them under realistic ocean conditions, first with a support boat acting as a diver surrogate and then with actual divers.
Madeline Miller, principal investigator
Relevance: primary · Type: quote
Confidence100%
"We quickly learned that you need more sensing capabilities on the diver when you factor in ocean currents. With the algorithms demonstrated by MIT, the vehicle only needed to calculate the distance, or range, to the diver at regular intervals to solve the optimization problem of estimating the positions of both the vehicle and diver over time. But with the real ocean forces pushing everything around, this optimization problem blows up quickly."
Relevance: primary · Type: action
Confidence100%
Miller's team is developing an AI classifier that processes optical and sonar data mid-mission and solicits human input for uncertain object classifications.
Relevance: primary · Type: background
Confidence100%
The feedback loop requires an underwater acoustic modem for diver-AUV communication.
Relevance: supporting · Type: background
Confidence100%
State-of-the-art underwater acoustic communications data rates require tens of minutes to send an uncompressed image from an AUV to a diver.
Relevance: supporting · Type: action
Confidence100%
The team is investigating methods to compress information for usefulness within the constraints of low bandwidth, high latency underwater communications, and low size, weight, and power of commercial off-the-shelf hardware.
Relevance: supporting · Type: action
Confidence100%
The team procured mostly commercial off-the-shelf sensors and built a sensor payload designed to integrate into AUVs routinely used by the U.S. Navy.
Relevance: supporting · Type: background
Confidence100%
The sensor payload includes an acoustic modem for ranging to the diver and several data processing and compute boards.
Relevance: primary · Type: event
Confidence100%
Miller's team tested the sensor-equipped AUV and algorithms in coastal New England.
Relevance: supporting · Type: event
Confidence100%
These tests included the open ocean near Portsmouth, New Hampshire, using the University of New Hampshire's Gulf Surveyor and Gulf Challenger research vessels as diver surrogates.
Relevance: supporting · Type: event
Confidence100%
The team also tested on the Boston-area Charles River using an MIT Sailing Pavilion skiff as the surrogate.
Relevance: supporting · Type: background
Confidence100%
The Gulf Surveyor and Gulf Challenger research vessels can access realistic ocean conditions.
forum Comments (0)
No comments yet. Be the first to comment.