Jonathan DeCastro
Scholar

Jonathan DeCastro

Google Scholar ID: Pnbjx1AAAAAJ
Toyota Research Institute
formal methodsroboticscyber-physical systemsmachine learning
Citations & Impact
All-time
Citations
1,166
 
H-index
17
 
i10-index
26
 
Publications
20
 
Co-authors
22
list available
Resume (English only)
Academic Achievements
  • Published numerous journal articles and peer-reviewed conference papers covering a wide range of topics including but not limited to multiagent behavior modeling, autonomous driving intent recognition, and vehicle trajectory prediction.
Research Experience
  • Currently a Research Scientist at Toyota Research Institute, focusing on areas like multiagent behavior modeling and reasoning, vehicle trajectory prediction, and diversity-aware motion prediction.
Education
  • Received Ph.D. in 2017 from Cornell University, working with Prof. Hadas Kress-Gazit as an affiliate of the Verifiable Robotics Research Group.
Background
  • Research interests lie in the intersection of control theory, dynamical systems and formal methods. Specifically, correct-by-construction synthesis of continuous controllers from temporal logic specifications; algorithms for falsification of interesting system properties, such as safety; application of formal synthesis, verification, and falsification to robotics applications of all kinds.