News & Events

Headlines

Machine Learning Helps Robot Swarms Coordinate

07-14-20

Soon-Jo Chung, Bren Professor of Aerospace, Yisong Yue, Professor of Computing and Mathematical Sciences, postdoctoral scholar Wolfgang Hönig, and graduate students Benjamin Rivière and Guanya Shi, have designed a new data-driven method to control the movement of multiple robots through cluttered, unmapped spaces, so they do not run into one another. "Our work shows some promising results to overcome the safety, robustness, and scalability issues of conventional black-box artificial intelligence (AI) approaches for swarm motion planning with GLAS and close-proximity control for multiple drones using Neural-Swarm," says Chung. [Caltech story]

Tags: research highlights GALCIT CMS Yisong Yue Soon-Jo Chung postdocs Benjamin Rivière Guanya Shi Wolfgang Hönig

Daniel Neamati Receives 2020 Henry Ford II Scholar Award

06-08-20

Daniel Neamati is a recipient of the 2020 Henry Ford II Scholar Award. Daniel’s interests sit at the cross-section of mechanical engineering, aerospace engineering, and planetary science. Daniel's research includes modern computational techniques in microfluidic analyses, and he has contributed to JPL projects such as the Europa Lander and Mars 2020. In the near future, Daniel plans to conduct a SURF at Stanford, and a senior thesis with Professor Soon-Jo Chung in the Aerospace Robotics and Control Laboratory. Thereafter, Daniel plans to pursue a Ph.D. in control systems in aerospace engineering. The Henry Ford II Scholar Award is funded under an endowment provided by the Ford Motor Company Fund. The award is made annually to engineering students with the best academic record at the end of the third year of undergraduate study.

Tags: honors GALCIT Henry Ford II Scholar Award Soon-Jo Chung Daniel Neamati

Best Student Paper Award at International Workshop

07-23-19

The paper "Distributed multi-target relative pose estimation for cooperative spacecraft swarm" co-authored by GALCIT students Kai Matsuka, Sorina Lupu, Yashwanth Kumar Nakka, and Rebecca Foust, as well as Professor Soon-Jo Chung and JPL Chief Technologist, Dr. Fred Hadaegh has won one of the two Best Student Paper awards at the 2019 International Workshop on Satellite Constellations and Formation Flying (IWSCFF). The paper presents a multi-agent localization algorithm architecture applied to a large-scale spacecraft swarm. The proposed algorithm is verified by simulation and robotic experiments using the air-bearing spacecraft simulators. The team also acknowledged the work of two Caltech undergraduate students Aaron Feldman and Jennifer Sun for their contribution to the robotic experiments. [Read the paper]

Tags: honors alumni Soon-Jo Chung student Fred Hadaegh Kai Matsuka Yashwanth Kumar Nakka Rebecca Foust Sorina Lupu

"Neural Lander" Uses AI to Land Drones Smoothly

05-23-19

Professors Chung, Anandkumar, and Yue have teamed up to develop a system that uses a deep neural network to help autonomous drones "learn" how to land more safely and quickly, while gobbling up less power. The system they have created, dubbed the "Neural Lander," is a learning-based controller that tracks the position and speed of the drone, and modifies its landing trajectory and rotor speed accordingly to achieve the smoothest possible landing. The new system could prove crucial to projects currently under development at CAST, including an autonomous medical transport that could land in difficult-to-reach locations (such as a gridlocked traffic). "The importance of being able to land swiftly and smoothly when transporting an injured individual cannot be overstated," says Professor Gharib who is the director of CAST; and one of the lead researchers of the air ambulance project. [Caltech story]

Tags: research highlights Morteza Gharib Yisong Yue Soon-Jo Chung Animashree Anandkumar

Engineers Taught a Drone to Herd Birds Away From Airports

08-08-18

Soon-Jo Chung, Associate Professor of Aerospace and Bren Scholar; Jet Propulsion Laboratory Research Scientist, and colleagues have developed a new control algorithm that enables a single drone to herd an entire flock of birds away from the airspace of an airport. The effectiveness of the algorithm is only limited by the number and size of the incoming birds, Professor Chung says, adding that the team plans to explore ways to scale the project up for multiple drones dealing with multiple flocks.[Caltech story]

Tags: research highlights GALCIT Soon-Jo Chung

Professor Chung’s Bat Bot Featured in Museum of Arts and Crafts in Hamburg

10-21-17

The Bat Bot, a self-contained robotic bat with soft, articulated wings, created by Professor Soon-Jo Chung and his colleagues has been selected by the Museum of Arts and Crafts in Hamburg to be placed in a special exhibit entitled Animals: Respect / Harmony / Subjugation. Professor Chung’s robotic bat will be on special display along with the work of virtuosos like Albrecht Dürer till March 4, 2018.

Tags: honors GALCIT CMS Soon-Jo Chung

Robot Drone That Mimics Bat Flight

02-01-17

Soon-Jo Chung, Associate Professor of Aerospace and Bren Scholar; Jet Propulsion Laboratory Research Scientist, and colleagues have recreated the key flight mechanisms of bats with unprecedented fidelity in the Bat Bot—a self-contained robotic bat with soft, articulated wings. [Caltech story]

Tags: research highlights GALCIT CMS Soon-Jo Chung

Taking Flight: Professor Soon-Jo Chung

01-27-17

Soon-Jo Chung, Associate Professor of Aerospace and Bren Scholar; Jet Propulsion Laboratory Research Scientist, has wide research interests ranging from the creation of a robotic bat with flexible wings and realistic flight dynamics to the control of swarms of small satellites to the development of computer-vision-based navigation systems. [Interview with Professor Soon-Jo Chung]

Tags: research highlights GALCIT CMS Soon-Jo Chung