News & Events


Rapid Adaptation of Deep Learning Teaches Drones to Survive Any Weather


To be truly useful, drones—that is, autonomous flying vehicles—will need to learn to navigate real-world weather and wind conditions. A team of engineers from Caltech has developed Neural-Fly, a deep-learning method that can help drones cope with new and unknown wind conditions in real time just by updating a few key parameters. [Caltech story]

Tags: research highlights GALCIT CMS Yisong Yue Soon-Jo Chung Animashree Anandkumar Xichen Shi Guanya Shi Michael O'Connell Kamyar Azizzadenesheli

What Is the Future of Wind Energy?


Humans have used windmills to capture the force of the wind as mechanical energy for more than 1,300 years. Unlike early windmills, however, modern wind turbines use generators and other components to convert energy from the spinning blades into a smooth flow of AC electricity. In this video, John Dabiri, Centennial Professor of Aeronautics and Mechanical Engineering discusses the future of wind energy technology. [Caltech story]

Tags: research highlights GALCIT MCE John Dabiri

Gunnarson and Dabiri Teach AI to Navigate Ocean with Minimal Energy


Engineers at Caltech, ETH Zurich, and Harvard are developing an artificial intelligence (AI) that will allow autonomous drones to use ocean currents to aid their navigation, rather than fighting their way through them. "When we want robots to explore the deep ocean, especially in swarms, it's almost impossible to control them with a joystick from 20,000 feet away at the surface. We also can't feed them data about the local ocean currents they need to navigate because we can't detect them from the surface. Instead, at a certain point we need ocean-borne drones to be able to make decisions about how to move for themselves," says John Dabiri, Centennial Professor of Aeronautics and Mechanical Engineering. [Caltech story]

Tags: research highlights GALCIT MCE John Dabiri Peter Gunnarson

LEONARDO, the Bipedal Robot, Can Ride a Skateboard and Walk a Slackline


Researchers have built a bipedal robot that combines walking with flying to create a new type of locomotion, making it exceptionally nimble and capable of complex movements. "We drew inspiration from nature. Think about the way birds are able to flap and hop to navigate telephone lines," says Soon-Jo Chung, Bren Professor of Aerospace and Control and Dynamical Systems; Jet Propulsion Laboratory Research Scientist. "A complex yet intriguing behavior happens as birds move between walking and flying. We wanted to understand and learn from that." A paper titled "A bipedal walking robot that can fly, slackline, and skateboard" about the LEO robot was published online on October 6 and was featured on the October 2021 cover of Science Robotics. [Caltech story]

Tags: research highlights CMS Soon-Jo Chung Elena-Sorina Lupu Kyunam Kim Patrick Spieler Alireza Ramezani

New Algorithm Helps Autonomous Vehicles Find Themselves, Summer or Winter


Without GPS, autonomous systems get lost easily. Now a new algorithm developed at Caltech allows autonomous systems to recognize where they are simply by looking at the terrain around them—and for the first time, the technology works regardless of seasonal changes to that terrain. The general process, known as visual terrain-relative navigation (VTRN), was first developed in the 1960s. By comparing nearby terrain to high-resolution satellite images, autonomous systems can locate themselves. The problem is that, in order for it to work, the current generation of VTRN requires that the terrain it is looking at closely matches the images in its database. To overcome this challenge, Anthony Fragoso, Lecturer in Aerospace; Staff Scientist, Connor Lee, Graduate student in Aerospace, Austin McCoy, Undergraduate, and Soon-Jo Chung, Bren Professor of Aerospace and Control and Dynamical Systems and research scientist at JPL, turned to deep learning and artificial intelligence (AI) to remove seasonal content that hinders current VTRN systems. [Caltech story]

Tags: research highlights GALCIT MCE CMS Soon-Jo Chung Anthony Fragoso Connor Lee Austin McCoy

EAS New Horizons Diversity, Equity & Inclusion Award


The Division of Engineering and Applied Sciences seeks nominations to recognize and honor individuals within the EAS community who have actively contributed to EAS’s goal to be a diverse, equitable, and inclusive engineering community. The award is available to members of the EAS community, including current students, postdoctoral scholars, staff, and faculty. Nominations are due Wednesday, May 19, 2021 and are accepted from anyone in the EAS community, EAS alumni and members of the Caltech community. Click here for full description of how to make a nomination.


How Do You Test a Helicopter Bound for Mars?


Caltech grad students helped JPL build a custom wind tunnel in a vacuum chamber for the Mars Ingenuity helicopter. The Ingenuity helicopter may be the first vehicle ever to fly on Mars, but Mars was not the first place it has ever flown. Before packaging it up and blasting it to the Red Planet, engineers at JPL gave the helicopter a trial run in a special wind tunnel. The fan array was designed and built by JPL engineers with input from Chris Dougherty and Marcel Veismann, who are currently working with Morteza Gharib, Hans W. Liepmann Professor of Aeronautics and Bioinspired Engineering and Booth-Kresa Leadership Chair of Caltech's Center for Autonomous Systems and Technologies (CAST). Jason Rabinovitch, who was a mechanical engineer at JPL working on testing the helicopter, reached out to the CAST team in 2017. "I'd earned my PhD at GALCIT, so I was aware of CAST and its facilities," says Rabinovitch. [Caltech story]

Tags: research highlights GALCIT Morteza Gharib Jason Rabinovitch Marcel Veismann Chris Dougherty

Hungry Fruit Flies are Extreme Ultramarathon Fliers


Michael Dickinson, Esther M. and Abe M. Zarem Professor of Bioengineering and Aeronautics; Executive Officer for Biology and Biological Engineering, has discovered that fruit flies can fly up to 15 kilometers (about 9 miles) in a single journey—6 million times their body length, or the equivalent of over 10,000 kilometers for the average human. "The dispersal capability of these little fruit flies has been vastly underestimated. They can travel as far or farther than most migratory birds in a single flight. These flies are the standard laboratory model organism, but they are almost never studied outside of the laboratory and so we had little idea what their flight capabilities were," Dickinson says. [Caltech story]

Tags: research highlights GALCIT Michael Dickinson CNS

Student-Led Moon Dust Shield Team Named Finalist in NASA Competition


As astronauts walk across the moon, land spacecraft on its surface, drive lunar rovers around, or complete other astronaut tasks, they kick up the dust, and that is a problem because it can cause premature wear on mechanical parts, damage to seals, and may pose a health risk for the people breathing it in. "The sun is shining directly on these particles and giving them an electric charge," says third-year Caltech undergraduate student Luis Pabon. "This causes it to stick to the astronaut's suit or to any sensors or cameras that you put out on the moon." The Caltech team's invention, named Habitat Orientable & Modular Electrodynamic Shield (HOMES), tackles the problem of moon dust entering a potential lunar habitat and wreaking havoc within. [Caltech story]

Tags: research highlights GALCIT MCE Luis Pabon

FUTURE Ignited


Nearly 200 undergraduates from more than 120 colleges and universities across the country joined Caltech for FUTURE Ignited, a virtual event that aimed to encourage students of color to pursue graduate studies in science and engineering. The goal of FUTURE Ignited is to diversify STEM with students of color who will go on to become incredible graduate students and scientific leaders in their respective fields. [Caltech story]