Spiders can be creepy — especially when they’re a foot wide and have eyes like Wall-E. But Lucky for us the spiders pictured above share the Pixar’s character’s intent — to help us. They’re a creation of Siemens’ Corporate Technology at Princeton, designed to be the automated construction bots of the future.
Related: See here for more 3D printers and accessories
Livio Dalloro, leader of the Product Design, Modeling and Simulation Research team, calls them SiSpis — shorthand for Siemens Spiders. “SiSpis are part of a larger picture that we define as Siemens Agile Manufacturing Systems (SiAMS) and they represent the core of our autonomous systems research here in Princeton,” Dalloro said.
Instead of spinning silk, these robot spiders spin plastic — or rather, a cornstarch-sugarcane mix called poly lactic acid. They’re essentially 3D printers with legs. Dalloro said, “We are looking at using multiple autonomous robots for collaborative additive manufacturing of structures, such as car bodies, the hulls of ships and airplane fuselages.”
Hasan Sinan Bank, who holds several associated patents and played a leading role in the project said, “Each spider is capable of manufacturing only a small portion of a work piece.” Something as large as the hull of a ship, would need a virtual army of these spiders working together. A good portion of the research involved creating algorithms that let the robots coordinate as they work.
“With the exception of the spiders’ mini motors and cables, which were off-the-shelf products, we developed everything ourselves from the mechanics to the software,” Dalloro said. Physical parts were 3D printed, and the team developed a unique software that combines Siemens’ own NX and a Robot Operating System.
By dividing the area into a grid, the robots use the given length of their arms to figure out the space they need to cover. Input from a laser scanner and camera allow the robots to interpret their environment.
Not only will these robots build on their own, they’ll charge themselves. When a robot’s battery gets low, it will send information about its job to a fully-charged robot, essentially tagging in another worker before it stops working to automatically seek out a charging station. The new worker can take up exactly where the first left off.
Dalloro explained of the project, “Its goal was to create a prototype platform for autonomous manufacturing machines that can understand a task, split it up among available robots, and enter into a manufacturing process in a collaborative and coordinated way without explicit programming.”
Bank said, once these robotic spiders “mature” the technology has broad applications. SiSpis have been in development since 2014, and the team is still at work with no release date announced, so no need to worry about the robot uprising just yet.
San Francisco startup Dimensional advertised for people to walk robot dogs through city streets. The New York Times reported that the job could include carrying a roughly 33-pound robot back to the office if it overheated. A lift home is an awkward requirement for a labor-saving machine.
Keeping the hardware running is only one challenge. Anthropic's robotics tests found that language models mostly failed when controlling joints directly, but did better when directing trained controllers. Giving an AI agent a body doesn't teach it to handle ordinary household objects.
Soon, a mattress protector may be more than a bed cover. Australian medtech company Sleeptite and researchers at RMIT University have received a US patent for FlexiSense, a smart bedding technology that tracks body position and posture to help caregivers identify when older residents may be at risk of falling.
The technology is being developed for Sleeptite’s in-bed monitoring system, REMi, and was recently on display at The MedTech Conference in Boston. A peer-reviewed study in Flexible and Printed Electronics says the sensors can also be made at scale without sacrificing performance or durability.
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.