James Alan Preiss

I am a Ph.D. student at the USC Robotic Embedded Systems Lab in Los Angeles, CA, advised by Prof. Gaurav Sukhatme. In summer of 2019, I will join Google NYC as a research intern.

I am interested in understanding the structure of optimization problems encountered in robotics and machine learning. My past projects include algorithms and hardness results in trajectory optimization for state observability, and multi-robot motion planning using a discrete/continuous decomposition. I currently focus on reinforcement learning in continuous spaces, particularly on how the system dynamics affect the difficulty of learning.

I also helped design and build USC's Crazyswarm 49-quadcopter research facility. Before joining RESL, I worked as a professional software developer on industrial 3d scanning tools at Geomagic and the JMP visual statistics package at SAS. I completed a B.S. in Mathematics and B.A. in Photography at The Evergreen State College in Olympia, WA.

This page last updated March 2019.

• Trajectory Planning for Quadrotor Swarms
• Downwash-Aware Trajectory Planning for Large Quadcopter Teams
• Crazyswarm: A Large Nano-Quadcopter Swarm
• Observability-Aware Trajectory Optimization for Self-Calibration with Application to UAVs

• Estimating Metric Scale Visual Odometry from Videos using 3D Convolutional Networks.
  Alexander S. Koumis, James A. Preiss, and Gaurav S. Sukhatme.
  IEEE International Conference on Intelligent Robots and Systems (IROS), 2019 (accepted).
• Resilience by Reconfiguration: Exploiting Heterogeneity in Robot Teams.
  Ragesh K. Ramachandran, James A. Preiss, and Gaurav S. Sukhatme.
  IEEE International Conference on Intelligent Robots and Systems (IROS), 2019 (accepted). [preprint]
• Sim-to-(Multi)-Real: Transfer of Low-Level Robust Control Policies to Multiple Quadrotors.
  Artem Molchanov, Tao Chen, Wolfgang Hönig, James A. Preiss, Nora Ayanian, and Gaurav S. Sukhatme.
  IEEE International Conference on Intelligent Robots and Systems (IROS), 2019 (accepted).
• Understanding the Variance of Policy Gradient Estimators in Reinforcement Learning.
  Sébastien M. R. Arnold, James A. Preiss, Chen-Yu Wei and Marius Kloft.
  Southern California Machine Learning Symposium (2019). [preprint: coming soon!] Awarded best poster
• Learning a System-ID Embedding Space for Domain Specialization with Deep Reinforcement Learning.
  James A. Preiss, Karol Hausman, Gaurav S. Sukhatme.
  NeurIPS 2018 Workshop on Reinforcement Learning under Partial Observability. [pdf]
• Simultaneous Self-Calibration and Navigation using Trajectory Optimization.
  James A. Preiss, Karol Hausman, Gaurav S. Sukhatme, and Stephan Weiss.
  International Journal of Robotics Research (IJRR), Invitation-only RSS 2017 special issue. [official page] [preprint]
• Trajectory Planning for Quadrotor Swarms.
  Wolfgang Hönig, James A. Preiss, T.K. Satish Kumar, Gaurav S. Sukhatme, and Nora Ayanian.
  IEEE Transactions on Robotics (T-RO), special issue on aerial swarm robotics. [preprint] [video]
• Trajectory Optimization for Self-Calibration and Navigation.
  James A. Preiss, Karol Hausman, Gaurav S. Sukhatme, and Stephan Weiss.
  Robotics: Science and Systems (RSS), 2017. [pdf]
• Downwash-Aware Trajectory Planning for Large Quadcopter Teams.
  James A. Preiss, Wolfgang Hönig, Nora Ayanian, and Gaurav S. Sukhatme
  IEEE International Conference on Intelligent Robots and Systems (IROS), 2017. [arXiv version] [video]
• Crazyswarm: A Large Nano-Quadcopter Swarm.
  James A. Preiss, Wolfgang Hönig, Gaurav S. Sukhatme, and Nora Ayanian.
  IEEE International Conference on Robotics and Automation (ICRA), 2017. [pdf] [video]
• Observability-Aware Trajectory Optimization for Self-Calibration with Application to UAVs.
  Karol Hausman, James A. Preiss, Gaurav S. Sukhatme, and Stephan Weiss.
  IEEE Robotics and Automation Letters (RA-L), 2017. [arXiv version] [video]

• crazyswarm - our full stack for flying 49+ Crazyflie quadcopters in a motion capture space. Includes object tracking, improved radio protocols, onboard sensor fusion, nonlinear controller, onboard trajectory planning, ROS node, and Python scripting.
• smoothener - convert multi-robot waypoint sequences into smooth piecewise polynomial trajectories. Implementation of the continuous portion of our IROS 2017 paper.
• cmath3d - a 3d math library for embedded C
• pputils - utilities for working with piecewise polynomials in Matlab's ppform.
• quatcompress - compress a quaternion into 32 bits
• 3DC-VO - Alexander Koumis's implementation of metric scale visual odometry using 3D convolutional networks

(first initial) (middle initial) (last name) @ usc.edu