Avatar

Carlos Jaramillo

Perception Engineer

Aurora Flight Sciences, a Boeing Company

Biography

Carlos Jaramillo is currently a Perception Engineer at Aurora Flight Sciences, a Boeing Company working on aerospace autonomy. In 2018, he earned his doctorate degree in computer science at the City University of New York under the supervision of Dr. Jizhong Xiao at the CCNY Robotics Lab. His Ph.D thesis dissertation included research in topics of computer vision applied to robotic sensing for navigation, mobile autonomous robots and omnidirectional vision sensors. He enjoys researching science, hacking technology, and programming in any language that gets the job done, but his preferences are Python, C and C++. He has participated in various international events, conferences, and competitions. For instance, in 2009, he joined the CityALIEN team, which won the Design Competition during the Intelligent Ground Vehicle Competition (IGVC), and then he led a new team in 2011. He interned at Mitsubishi Electric Research Laboratories (MERL) for a year (2016-2017) where he was able to collaborate with Dr. Yuichi Taguchi on developing algorithms for SLAM (simultaneous localization and mapping) and 3D reconstruction.

Interests

  • Computer Vision
  • Robotics Autonomous Navigation
  • Omnidirectional Vision
  • Catadioptrics
  • Machine Learning
  • Aerospace

Education

  • PhD in Computer Science, 2018

    CUNY Graduate Center

  • MSc in Computer Science, 2011

    City College of New York

  • BEng in Computer Engineering, 2009

    City College of New York

  • ASc in Computer Science, 2003

    SUNY Westchester Community College

Recent Publications

Quickly discover relevant content by filtering publications.

Visual Odometry with a Single-Camera Stereo Omnidirectional System

We present the advantages of a single-camera stereo omnidirectional system (SOS) in estimating egomotion in real-world environments.

Enhancing 3D Visual Odometry with Single-Camera Stereo Omnidirectional Systems

We explore low-cost solutions for efficiently improving the 3D pose estimation problem of a single omnidirectional camera moving in an …

Direct Multichannel Tracking

We present direct multichannel tracking, an algorithm for tracking the pose of a monocular camera (visual odometry) using …

GUMS: A Generalized Unified Model for Stereo Omnidirectional Vision (Demonstrated Via a Folded Catadioptric System)

GUMS is a complete projection model for omnidirectional stereo vision systems. GUMS is based on the existing generalized unified model …

Design and Analysis of a Single-Camera Omnistereo Sensor for Quadrotor Micro Aerial Vehicles (MAVs)

We describe the design and 3D sensing performance of an omnidirectional stereo (omnistereo) vision system applied to Micro Aerial …

Autonomous Quadrotor Flight Using Onboard RGB-D Visual Odometry

We present an on-board navigation system for Micro Aerial Vehicles (MAV) based on information provided by a visual odometry algorithm …

A Single-Camera Omni-Stereo Vision System for 3D Perception of Micro Aerial Vehicles (MAVs)

We introduce a catadioptric single-camera omnistereo vision system that uses a pair of custom-designed mirrors (in a folded …

Generating near-spherical range panoramas by fusing optical flow and stereo from a single-camera folded catadioptric rig

We design a novel ‘folded’ spherical catadioptric rig (formed by two coaxially-aligned spherical mirrors of distinct radii …

Incremental Registration of RGB-D Images

We present a real-time technique for 6-DoF camera pose estimation through the incremental registration of RGB-D images.

Fusing Optical Flow and Stereo in a Spherical Depth Panorama Using a Single-Camera Folded Catadioptric Rig

We design a novel ‘folded’ spherical catadioptric rig (formed by two coaxially-aligned spherical mirrors of distinct radii …

Projects

*

Visual Odometry with a Single-Camera Stereo Omnidirectional System

A single-camera stereo omnidirectional system (SOS) is applied for estimating egomotion in real-world environments.

Machine Learning Project - Multidimensional Classification using LUTs

Project for Prof. Robert Haralick’s Machine Learning Course at CUNY Graduate Center. The goal was to design a labeled two class …

CATA

In 2011, a new intelligent ground vehicle CATA (City Autonomous Transportation Agent) was rebuilt to employ the ROS framework to …

CityALIEN

In 2010, our intelligent ground vehicle CityALIEN participated and won the IGVC Design Challenge.

Contact

  • Cambridge, MA, 02142, United States