Ethan Shaotran

San Francisco Bay Area Contact Info
1K followers 500+ connections

Join to view profile

About

Ethan Shaotran is the founder of Energize AI and a student at Harvard and MIT. He's the…

Activity

Join now to see all activity

Publications

  • Gesture Learning For Self-Driving Cars

    2021 IEEE International Conference on Autonomous Systems (ICAS)

    Human-computer interaction (HCI) is crucial for safety as autonomous vehicles (AVs) become commonplace. Yet, little effort has been put toward ensuring that AVs understand human communications on the road. In this paper, we present Gesture Learning for Advanced Driver Assistance Systems (GLADAS), a deep learning-based self-driving car hand gesture recognition system developed and evaluated using virtual simulation. We focus on gestures as they are a natural and common way for pedestrians to…

    Human-computer interaction (HCI) is crucial for safety as autonomous vehicles (AVs) become commonplace. Yet, little effort has been put toward ensuring that AVs understand human communications on the road. In this paper, we present Gesture Learning for Advanced Driver Assistance Systems (GLADAS), a deep learning-based self-driving car hand gesture recognition system developed and evaluated using virtual simulation. We focus on gestures as they are a natural and common way for pedestrians to interact with drivers. We challenge the system to perform in typical, everyday driving interactions with humans. Our results provide a baseline performance of 94.56% accuracy and 85.91% F1 score, promising statistics that surpass human performance and motivate the need for further research into human-AV interaction.

    See publication

  • GLADAS: Gesture Learning for Advanced Driver Assistance Systems

    Pre-Print

    See publication

  • Stories from 2045: Artificial Intelligence and the Future of Work

    Economic Singularity Club

    These stories explore the ways that artificial intelligence and related technologies will affect the job market. At the moment, no-one can predict exactly what will happen, but it seems very likely that people will need to retrain and change jobs more often. Looking further ahead, we may need to work out how to make technological unemployment a very positive outcome, and with that in mind, this book has twice as many positive stories as negative ones.

    Other authors
    See publication

  • Tales from Tech Street: Booms and Busts in an AI Financial Takeover

    The Future Society

    An analysis of the future of Wall Street and the financial markets as hedge funds and other institutions with the development of superhuman intelligence.

    Used in "Stories from 2045" by the Economic Singularity Club.

    Other authors
    See publication

  • Stock Prediction with Deep Learning

    Energize.AI

    Whether you’re an expert in Artificial Intelligence, or a newbie aspiring to be one, this book takes a completely new approach in teaching Deep Learning, as well as the process of creating a stock prediction algorithm. Throughout the book, you’ll create your own deep learning model, learn how to develop it, and make it better in order to beat the stock market.

    This book is NOT for people looking for a textbook-like approach to learning Deep Learning. Instead, the book is designed as a…

    Whether you’re an expert in Artificial Intelligence, or a newbie aspiring to be one, this book takes a completely new approach in teaching Deep Learning, as well as the process of creating a stock prediction algorithm. Throughout the book, you’ll create your own deep learning model, learn how to develop it, and make it better in order to beat the stock market.

    This book is NOT for people looking for a textbook-like approach to learning Deep Learning. Instead, the book is designed as a course for you to take at your own pace, learning through doing, with sufficient guidance to make sure you’re understanding key concepts.

    Other authors
    • Dr. J Mark Munoz
    See publication

Patents

  • Battery Preconditioning Management for Vehicle Fleets

    Filed US20230004901A1

    A method of coordinating a fleet of vehicles includes receiving a first preconditioning characteristic of a first battery from a first vehicle of the fleet of vehicles. The method further includes receiving a second preconditioning characteristic of a second battery from a second vehicle of the fleet of vehicles. The method further includes comparing the first preconditioning characteristic and the second preconditioning characteristic to determine a preconditioning ranking for the first…

    A method of coordinating a fleet of vehicles includes receiving a first preconditioning characteristic of a first battery from a first vehicle of the fleet of vehicles. The method further includes receiving a second preconditioning characteristic of a second battery from a second vehicle of the fleet of vehicles. The method further includes comparing the first preconditioning characteristic and the second preconditioning characteristic to determine a preconditioning ranking for the first vehicle and the second vehicle. The method further includes determining a queue of the first and second vehicles for a charging station using the preconditioning ranking of the first and second vehicles.

    See patent

  • Systems and Methods for Automated Electrical Panel Analysis

    Filed US20230005126A1

    A method of determining a capability of an electrical panel includes providing information relative to the electrical panel to a computer vision software, such as through an image captured by a camera. An attribute of the electrical panel may be analyzed, using the computer vision software, panel at least partially based on the information. An overall electrical power capacity of the electrical panel may be calculated based at least in part on the attribute of the electrical panel. An…

    A method of determining a capability of an electrical panel includes providing information relative to the electrical panel to a computer vision software, such as through an image captured by a camera. An attribute of the electrical panel may be analyzed, using the computer vision software, panel at least partially based on the information. An overall electrical power capacity of the electrical panel may be calculated based at least in part on the attribute of the electrical panel. An electrical load on the electrical panel may be calculated based at least in part on the attribute of the electrical panel. A report may be generated that includes an unused electrical power capacity of the electrical panel at least partially based on the electrical load and the overall electrical power capacity of the electrical panel.

    See patent

  • Route Based Battery Preconditioning Systems and Methods

    Filed US20230001824A1

    A method of preconditioning a battery of a vehicle includes determining a baseline preconditioning start time relative to an estimated time of arrival at a charging station. The method further includes analyzing a route of the vehicle to the charging station to determine a route characteristic. The method further includes modifying the baseline preconditioning start time based on the route characteristic to determine a route-based preconditioning start time.

    See patent

  • Battery Preconditioning Management for Vehicles of a Distributed Network

    Filed US20230001818A1

    A method of controlling battery preconditioning in a vehicle includes determining a first preconditioning characteristic of a first battery of a first vehicle relative to a charging station. The method further includes transmitting the first preconditioning characteristic. The method further includes receiving, from a second vehicle, a second preconditioning characteristic of a second battery relative to the charging station. The method further includes comparing the first preconditioning…

    A method of controlling battery preconditioning in a vehicle includes determining a first preconditioning characteristic of a first battery of a first vehicle relative to a charging station. The method further includes transmitting the first preconditioning characteristic. The method further includes receiving, from a second vehicle, a second preconditioning characteristic of a second battery relative to the charging station. The method further includes comparing the first preconditioning characteristic and the second preconditioning characteristic to determine a preconditioning ranking for the first vehicle and the second vehicle. The method further includes determining a queue of the first and second vehicles for the charging station using the preconditioning ranking of the first and second vehicles.

    See patent

Organizations

  • PADI

    Divemaster

    - Present

  • Association for Computing Machinery (ACM)

    Member

    - Present

  • Apple Developer

    Head Developer at Purifi Games

    - Present

    Part of the Apple Developer program, where I developed 6 apps for the iOS App Store, with thousands of downloads each: https://itunes.apple.com/us/developer/ethan-shaotran/id1049171468

  • AI Initiative, Harvard Kennedy School

    Affiliate

    -

    The AI Initiative is an initiative of The Future Society incubated at Harvard Kennedy School and dedicated to the rise of Artificial Intelligence. Created in 2015, it gathers students, researchers, alumni, faculty and experts from Harvard and beyond, interested in understanding the consequences of the rise of Artificial Intelligence. Its mission is to help shape the global AI policy framework.

Recommendations received

2 people have recommended Ethan

Join now to view

More activity by Ethan

View Ethan’s full profile

  • See who you know in common
  • Get introduced
  • Contact Ethan directly
Join to view full profile

People also viewed

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More