This inventor holds 4 USPTO granted patents and 3 published patent applications. Top assignee: Zoox, Inc.. Active years: 2026.
Company Filing History:
3 out of 1,296 
Years Active: 2026
Title: Alec Jacob Farid: Innovator in Machine-Learned Vehicle Control
Introduction
Alec Jacob Farid is an accomplished inventor based in Commack, NY (US). He has made significant contributions to the field of vehicle control through his innovative patent. His work focuses on enhancing the efficiency of machine-learned architectures in estimating operational costs for vehicle control.
Latest Patents
Alec holds a patent titled "Machine-learned cost estimation in tree search trajectory generation for vehicle control." This invention presents a machine-learned architecture designed to estimate the cost of operations from a prediction node within a tree search. The architecture is trained using a loss function that addresses the challenges of training without requiring infinite tree searches or achieving convergence. The first loss term is based on the difference between the estimated cost to go from a starting position and the cost determined by the search thus far. The second loss term is adjusted based on various factors, including convergence-based weights and approximations of the difference between the current cheapest action and the globally optimal action.
Career Highlights
Alec is currently employed at Zoox, Inc., where he applies his expertise in machine learning and vehicle control. His innovative approach has positioned him as a key player in the development of advanced vehicle technologies.
Collaborations
Alec collaborates with Sutej Pramod Kulgod, working together to push the boundaries of vehicle control technologies.
Conclusion
Alec Jacob Farid's contributions to machine learning and vehicle control exemplify the innovative spirit of modern inventors. His patent reflects a significant advancement in the field, showcasing the potential of machine-learned architectures in enhancing vehicle operation efficiency.