Future of Aerospace Autonomy: How to Combine Machine Learning with Guidance, Navigation, and Control?
One common theme of our research projects at CAST and my research group http://aerospacerobotics.caltech.edu/is to systematically leverage AI and Machine Learning (ML) towards achieving safe and stable autonomy of aerospace systems, such spacecraft swarms and heavylifting drones. Stability and safety are often research problems of control theory and robotics, while conventional black-box AI approaches lack the much-needed robustness, scalability, and interpretability, which are indispensable to designing control and autonomy engines for safe-critical aerospace robotic systems. For example, engineers at CAST are developing the Autonomous Flying Ambulance, which can fly a short distance using distributed electric fans combined with efficient wings to med-vac a patient to a local hospital under any severe weather conditions. Realizing such an autonomous heavylifting drone system with all the necessary autonomous capabilities will revolutionize how we travel, how we save lives, and how we respond to natural disasters and emergencies. I will also briefly introduce the spaceflight project under development with NGIS and JPL to demonstrate the most advanced autonomy GNC algorithms in spacecraft flying in swarms.
Available for public on YouTube: <https://youtu.be/uYTImX0Vy2A>"
Contact: Benedikt Barthel firstname.lastname@example.org