MIT researchers have created a new system that enables robots to identify objects using tactile information, reports Darrell Etherington for TechCrunch. “This type of AI also could be used to help robots operate more efficiently and effectively in low-light environments without requiring advanced sensors,” Etherington explains.
Fast Company reporter Michael Grothaus writes that CSAIL researchers have developed a new system that allows robots to determine what objects look like by touching them. “The breakthrough could ultimately help robots become better at manipulating objects,” Grothaus explains.
TechCrunch reporter Darrell Etherington writes that MIT researchers have developed a system that can predict a perso's trajectory. The tool could allow “robots that typically freeze in the face of anything even vaguely resembling a person walking in their path to continue to operate and move around the flow of human foot traffic."
Bloomberg News spotlights how MIT researchers have developed a fleet of autonomous boats that can automatically latch onto one another. Bloomberg notes that the boats will be able to “transport goods and people, collect trash and assemble into floating stages and bridges.”
Boston Globe reporter Martin Finucane writes that MIT researchers have developed an automated latching system that could enable a fleet of autonomous boats to connect to docking stations and other boats. Finucane explains that in turbulent water, “after a missed first attempt, the system can autonomously adapt, repositioning the roboat and latching.”
Popular Mechanics reporter Daisy Hernandez writes that MIT researchers have developed an autonomous aquatic boat that can target and latch onto one another to form new structures. Hernandez writes that the boats were conceived “as a way to explore new modes of transportation and help improve traffic flow.”
Mashable highlights how MIT researchers have developed a new system of computationally simple robots inspired by biological cells that can connect in large groups to move around, transport objects and complete tasks. Mashable explains that robots made up of simplistic components, “could enable more scalable, flexible and robust systems.”
TechCrunch reporter Darrell Etherington writes that MIT researchers have developed a new system that enables autonomous boats to latch onto one another to create new structures. Etherington explains that the researchers envision fleets of autonomous boats forming “on-demand urban infrastructure, including stages for concerts, walking bridges or even entire outdoor markets.”
Motherboard reporter Rob Dozier writes about Glitch, an MIT startup that uses machine learning to design clothing. “These tools are meant to empower human designers,” explains graduate student Emily Salvador. “What I think is really cool about these creative-focused AI tools is that there’s still this really compelling need for a human to intervene with the algorithm.”
A new sensory glove developed by MIT researchers provides insight into how humans grasp and manipulate objects, reports The Economist. The glove will not only “be useful in programming robots to mimic people more closely when they pick objects up,” but also could “provide insights into how the different parts of the hand work together when grasping things.”
A new glove embedded with sensors can enable AI systems to identify the shape and weight of different objects, writes HealthDay reporter Dennis Thompson. Using the glove, “researchers have been able to clearly unravel or quantify how the different regions of the hand come together to perform a grasping task,” explains MIT alumnus Subramanian Sundaram.
New Scientist reporter Chelsea Whyte writes that MIT researchers have developed a smart glove that enables neural networks to identify objects by touch alone. “There’s been a lot of hope that we’ll be able to understand the human grasp someday and this will unlock our potential to create this dexterity in robots,” explains MIT alumnus Subramanian Sundaram.
MIT researchers have developed a low-cost electronic glove equipped with sensors that can use tactical information to identify objects, reports Katherine Wu for NOVA Next. Wu writes that the glove is “easy and economical to manufacture, carrying a wallet-friendly price tag of only $10 per glove, and could someday inform the design of prosthetics, surgical tools, and more.”
Researchers from MIT and a number of other institutions have found that grammar-enriched deep learning models had a better understanding of key linguistic rules, reports Kyle Wiggers for VentureBeat. The researchers found that an AI system provided with knowledge of basic grammar, “consistently performed better than systems trained on little-to-no grammar using a fraction of the data, and that it could comprehend ‘fairly sophisticated’ rules.”
In this video, Mashable highlights how CSAIL researchers have developed a new system that can help lift heavy objects by mirroring human activity. The system uses sensors that monitor muscle activity and detect changes in the user’s arm.