Maggie Wang |
|
Robotics Software Engineer
Skydio |
|
Career Panelist
Tech Vision Talk: Skydio Autonomy: Data-Driven Approaches Towards Real-Time 3D Reconstruction in Drones
Abstract: Skydio is the leading US drone company and the world leader in autonomous flight. Our drones are used for everything from capturing amazing video, to inspecting bridges, to tracking progress on construction sites. At the core of our products is a vision-based autonomy system with eight years of development at Skydio, drawing on decades of academic research. This system pushes the state of the art in deep learning, geometric computer vision, motion planning, and control with a particular focus on real-world robustness.
|
|
Using six 4K navigational cameras, our drones create a 3D model of its surroundings that updates at a rate of over one million data points per second, and runs up to nine deep neural networks to predict into the future. In this talk, we will discuss how data-driven processes are used in Skydio 3D Scan, a revolutionary adaptive scanning software that enables Skydio drones to autonomously generate 3D models with comprehensive coverage and ultra-high resolution.
|
|
Biography:
|
|
Maggie is a robotics software engineer at Skydio, an autonomous drone startup in Silicon Valley. With interests in motion planning, control theory, computer vision, and deep learning, her goal is to build robots to expand human consciousness, creativity, and connection. She received her A.B. in Physics and S.M. in Computer Science from Harvard in May 2021. While in college, Maggie led a team to build fixed-wing planes in the Harvard Unmanned Aerial Systems team (now HUAERO) and helped start the Harvard Satellite Team. She also worked on embedded systems and computer vision at Google Nest, researched robust pose estimation in the MIT Robot Locomotion Group, and helped build autonomous underwater robots in the Harvard Self-Organizing Systems Research Group.
|