Popular Science reporter Jamie Dickman writes that using liquid neural networks, MIT researchers have “trained a drone to identify and navigate toward objects in varying environments.” Dickman notes that: “These robust networks enable the drone to adapt in real-time, even after initial training, allowing it to identify a target object despite changes in their environment.”
Researchers at MIT have developed a new type of autonomous drone that uses advanced neural networks to fly, reports Tony Ho Tran for The Daily Beast. “The new design allows the drone to make better decisions when flying through completely new environments,” writes Tran, “and could have future applications in self-driving cars, search and rescue operations, wildlife monitoring, or even diagnosing medical issues.”
MIT researchers have developed Robust MADER, an updated version of a previous system developed in 2020 to help drones avoid in-air collisions, reports Brian Heater for TechCrunch. “The new version adds in a delay before setting out on a new trajectory,” explains Heater. “That added time will allow it to receive and process information from fellow drones and adjust as needed.”
Venti Technologies, a startup co-founded by MIT professors and alumni that builds autonomous vehicles for industrial and logistics centers, has raised $29 million in Series A funding. The company’s “target customer comes from the wide range of supply chain businesses that operate across warehouses, ports and other shipping and logistics environments where vehicles — currently driven by humans — are central to operations,” writes Ingrid Lunden for TechCrunch.
MIT engineers have developed a new technique that enables bug-sized aerial robots to handle a sizeable amount of damage and still fly, reports Andrew Paul for Popular Science. “The new repair techniques could come in handy when using flying robots for search-and-rescue missions in difficult environments like dense forests or collapsed buildings,” writes Paul.
Postdoc Saverio Cambioni speaks with Andrew Corselli of Tech Briefs about NASA’s DART mission, which was aimed at testing a method to protect Earth in case of an asteroid impact threat. “DART showed that it is technologically possible to intercept and impact a sub-kilometer asteroid, with limited prior knowledge of its shape and surface properties,” Cambioni explains.
Researchers at MIT have predicted that without improvements in hardware efficiency, energy consumption and emissions from autonomous vehicles could be “comparable to that of data centers today,” reports Sarah Wells for Popular Mechanics. “In order to reduce the future carbon footprint of AVs, scientists will need to make the computing systems of AVs, including smart sensors, far more efficient,” writes Wells.
MIT researchers have constructed a mini city to test to safely test algorithms designed for autonomous vehicles, reports Mashable. “The idea of the mini city is that we have lots of cars going at the same time and we can actually test out new algorithms in a safe environment,” says graduate student Noam Buckman.
Researchers at MIT have developed an autonomous vehicle with “mini sensors to allow it to see the world and also with an artificially intelligent computer brain that can allow it to drive,” explains postdoctoral associate Alexander Amini in an interview with Mashable. “Our autonomous vehicles are able to learn directly from humans how to drive a car so they can be deployed and interact in brand new environments that they’ve never seen before,” Amini notes.
An MIT study has found that the wide spread adoption of self-driving cars could lead to increased carbon emissions, reports Rima Sabina Aouf for Dezeen. “The study found that with a mass global take up of autonomous vehicles, the powerful onboard computers needed to run them could generate as many greenhouse gas emissions as all the data centers in operation today,” writes Aouf.
A new study by MIT researchers finds that “the energy required to run computers in a future global fleet of autonomous vehicles could produce as much greenhouse gas emissions as all the data centers in the world,” reports Sharon Udasin for The Hill. The researchers found that “1 billion such cars, each driving for an hour daily, would use enough energy to generate the same amount of emissions that data centers do today.”
Politico reporter Derek Robertson writes that a new study by MIT researchers finds the computing power required to replace the world’s auto fleet with AVs would produce about the same amount of greenhouse gas emissions as all the data centers currently operating. Robertson writes that the researchers view the experiment “as an important step in getting auto- and policymakers to pay closer attention to the unexpected ways in which the carbon footprint for new tech can increase.”
Graduate student Soumya Sudhakar speaks with BBC Digital Planet host Gareth Mitchell about her new study showing that hardware efficiency for self-driving cars will need to advance rapidly to avoid generating as many greenhouse gas emissions as all the data centers in the world.
Using statistical modeling, MIT researchers have found that the energy needed to power a fleet of fully autonomous EVs could generate as much carbon emissions as all the world’s data centers combined, reports Andrew Paul for Popular Science.
Washington Post reporter Pranshu Verma writes that a new study by MIT researchers finds the “future energy required to run just the computers on a global fleet of autonomous vehicles could generate as much greenhouse gas emissions as all the data centers in the world today.”