Skip to main content
  1. Home
  2. Emerging Tech
  3. News

Humanoid robot can dive to great depths while human operator stays safe and dry

Add as a preferred source on Google

Exploring the depths of Earth’s oceans is among the more challenging tasks facing the human race. Divers tend to have a hard time descending more than a few hundred feet below water due in part to the dramatic effects of water pressure — along with our general lack of gills. Enter Stanford University’s OceanOne, a humanoid robot initially conceived by the Palo Alto-based school to assist in the study the coral reef located in the depths of the Red Sea. But don’t fret about the prospect of this machine stealing any jobs; Stanford designed the AI-powered OceanOne to work in tandem with a human operator.

While working on the design of OceanOne, the team at Stanford always knew they wanted to develop a system that allowed the robot to function collaboratively with a human driver. The idea was that no robot, no matter how smart, could possess the same kind of care and skill as a human diver — that is, unless a human is the one carefully guiding the robot. About five feet long from end to end, OceanOne boasts stereoscopic vision built into its “head” that’s capable of transmitting exactly what it sees back to its operator. Additionally, the operator has fluid control over two articulated arms.

Recommended Videos

Though the entire robot is an impressive piece of engineering, perhaps the most noteworthy part of OceanOne is its innovative hands. Designed specifically to work with delicate coral reef or the perishable remains of shipwrecks, each hand features force sensors that transmit haptic feedback to the robot’s pilot. Because of this, the driver can feel exactly what OceanOne feels, helping determine if it’s grabbing something dense or delicate. In the future, Stanford says each finger will be fitted with tactile sensors that will also work to inform the robot’s built-in brain.

“You can feel exactly what the robot is doing,” said Stanford professor Oussama Khatib. “It’s almost like you are there; with the sense of touch, you create a new dimension of perception.”

To give the robot an inaugural whirl, Khatib and the team traveled to the Mediterranean Sea to plunder the ancient wreckage of La Lune. OceanOne deftly navigated the shipwreck (located some 330 feet underwater) and eventually grabbed what appeared to be a grapefruit-sized vase. After examining the vase and deciding to bring it to the surface, Khatib piloted the robot over to the team’s recovery basket, softly placed the object inside, and shut the lid. The basket was then brought above water, and Khatib and the rest of the team became the first people in hundreds of years to handle the vase thanks to the innovative OceanOne robot.

Khatib with the ancient vase salvaged from La Lune's wreckage
Khatib with the ancient vase salvaged from La Lune’s wreckage Frederic Osada and Teddy Seguin/DRASSM

“OceanOne will be your avatar,” Khatib said. “The intent here is to have a human diving virtually, to put the human out of harm’s way. Having a machine that has human characteristics that can project the human diver’s embodiment at depth is going to be amazing.”

Amazing indeed, and likely the future of ocean exploration, OceanOne represents the perfect harmony of AI and human interaction. Though Khatib helped in navigating the robot through La Lune’s wreckage, the bot itself can also search completely on its own. All the sensors loaded into OceanOne enable it to consistently monitor surrounding current and turbulence and allowing it to turn on its thrusters accordingly to stay in one spot. Built-in quick-firing motors even allow the robot’s arms to stay steady while working, making it even better at handling sensitive materials.

“We connect the human to the robot in [a] very intuitive and meaningful way. The human can provide intuition and expertise and cognitive abilities to the robot,” Khatib said. “The two bring together an amazing synergy. The human and robot can do things in areas too dangerous for a human, while the human is still there.”

With successful testing complete, the team plans on bringing OceanOne back to Stanford University for further work on the platform. As of now, OceanOne is — as its name implies — the only such humanoid diving robot. However, Khatib hopes to manufacture more in the future in order to create an entire fleet that could work together during future dives. Aside from Stanford’s participation, the OceanOne was developed in partnership with Meka Robotics and Saudi Arabia’s King Abdullah University of Science and Technology.

Rick Stella
Former Associate Editor, Outdoor
Rick became enamored with technology the moment his parents got him an original NES for Christmas in 1991. And as they say…
Anthropic’s sensitive internal data was exposed, and AI helped make it happen
Even the company behind Claude isn't immune to AI-powered security threats, as researchers discovered some worrying vulnerabilities.
Claude Anthropic Featured

AI companies spend enormous amounts of time convincing us their technology is safe and secure. But what happens when those same companies become targets of increasingly sophisticated AI-powered attacks? Anthropic, the company behind Claude, is now facing that question. According to a Washington Post report, cybersecurity startup Cathedral discovered vulnerabilities that let its researchers access sensitive information in Anthropic's internal systems.

The researchers used AI agents to identify potential entry points in less than 12 hours. Interestingly, they didn't need to crack Claude itself. Instead, they exploited weaknesses in third-party business applications that Anthropic uses for everyday operations. Anthropic's security testing program disclosed the findings, which allows outside researchers to identify and report vulnerabilities.

Read more
A new startup wants to fix the military’s working-dog shortage with cloning and gene editing
Promising pitch, plenty of unanswered questions about the dogs.
a new startup wants to fix the militarys working dog shortage with cloning and gene editing warhound featured image

Military working dogs charge into places the rest of us would flee. So, I understand why anyone would want to breed tougher, healthier dogs for the job.

Warhound, a new startup from Colossal Biosciences co-founder Ben Lamm and Anduril co-founder Palmer Luckey, has stepped out of stealth with $200 million to clone and gene-edit working dogs for American troops, police departments, and emergency services (via TechCrunch).

Read more
AI can describe a picture, but it still struggles to understand blind users
A University of Maryland study finds that Be My AI often buries useful answers in lengthy descriptions, leaving blind users to work harder to get the information they need.
Blind Man using walking stick

AI can describe a picture, identify objects, and answer questions about what a camera sees. But when a blind user needs a quick answer, getting an entire spoken essay about the scene isn't exactly helpful. Researchers at the University of Maryland (UMD) have found that AI-powered visual assistance can leave blind users doing too much work to get the information they actually need.

The study, titled Say It My Way: Exploring Control in Conversational Visual Question Answering with Blind Users, examined how people interact with Be My AI, an AI-powered feature of the Be My Eyes app. The researchers found that users often received lengthy descriptions that didn't adequately address their immediate goals, forcing them to ask follow-up questions or find ways to steer the AI towards a more useful answer.

Read more