Avatar

Eric Heiden

Ph.D. Student

University of Southern California

I am a Ph.D. student at the Robotic Embedded Systems Lab (RESL) advised by Gaurav S. Sukhatme at the University of Southern California (USC). I am supported by a Google PhD Fellowship. My research is focused on representations and algorithms that equip robots with the ability to act autonomously in uncertain environments while building models that allow them to make long-term plans. I am investigating novel robot simulators as semantic models of the world that can be updated from measurements. The resulting representation is parameterized by physically meaningful variables and enables approaches in task and motion planning that react to changes in the environment.

Before pursuing my Ph.D., I received my Master’s degree from USC where I worked as research assistant at RESL and at the Information Sciences Institute (ISI) with Craig Knoblock and Pedro Szekeley. Previously, I obtained my Bachelor’s degree from the University of Rostock (Germany) under the guidance of Sebastian Bader and Thomas Kirste.

Interests

  • Robot learning
  • Physics simulators
  • Autonomous robots
  • Task and Motion Planning

Education

  • PhD Computer Science, 2021 (expected)

    University of Southern California

  • MSc Computer Science (Intelligent Robotics), 2017

    University of Southern California

  • BSc Computer Science, 2015

    University of Rostock, Germany

Projects

Motion Generation

Trajectory generation through path planning, trajectory optimization, and novel robot learning approaches.

Autonomous navigation

Navigate unknown environments while coping with noisy sensor measurements.

Interactive Differentiable Simulation

Overcome sim2real gap using differentiable simulators that are continuously updated from measurements.

Journal Articles

(2020). Experimental Comparison of Global Motion Planning Algorithms for Wheeled Mobile Robots. Under review at IEEE Transactions on Robotics (T-RO).

PDF Code Project

(2019). Scaling simulation-to-real transfer by learning composable robot skills. Invited submission to International Journal of Robotics Research.

Code Project Video

(2019). Confidence-rich Grid Mapping. International Journal of Robotics Research.

PDF Project DOI

Conference Proceedings

(2019). LAMP: Large-Scale Autonomous Mapping and Positioning for Exploration of Perceptually-Degraded Subterranean Environments. International Conference on Robotics and Automation (ICRA) 2020.

PDF Project

(2019). Auto-conditioned Recurrent Mixture Density Networks for Learning Generalizable Robotic Manipulation Skills. Southern California Robotics Symposium (SCR).

PDF Project Poster Slides Video

(2018). Heterogeneous Sensor Fusion via Confidence-rich 3D Grid Mapping: Application to Physical Robots. International Symposium on Experimental Robotics (ISER).

PDF Project

(2018). Scaling simulation-to-real transfer by learning composable robot skills. International Symposium on Experimental Robotics (ISER).

PDF Code Video

(2018). Gradient-Informed Path Smoothing for Wheeled Mobile Robots. In International Conference on Robotics and Automation (ICRA).

PDF Code Project Video

(2017). Confidence-rich Grid Mapping. International Symposium on Robotics Research (ISRR).

PDF Project

(2017). Planning High-speed Safe Trajectories in Confidence-rich Maps. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

PDF Project Project

(2017). Concept and Realization of a Diagnostic System for Smart Environments. International Conference on Agents and Artificial Intelligence (ICAART).

PDF DOI

Workshop articles & Abstracts

(2018). Simulator Predictive Control: Using Learned Task Representations and MPC for Zero-Shot Generalization and Sequencing. NeurIPS Workshop on Deep Reinforcement Learning.

PDF

(2017). Web Text-based Network Industry Classifications: Preliminary Results. SIGMOD Workshop on Data Science for Macro-Modeling with Financial and Economic Datasets (DSMM).

PDF DOI

(2017). Confidence-aware Occupancy Grids. IROS Workshop on Vision-based Agile Autonomous Navigation of UAVs.

(2017). High-speed Safe Trajectory Planning in Confidence-rich Maps. IROS Workshop on Vision-based Agile Autonomous Navigation of UAVs.

Experience

 
 
 
 
 

Deep Learning Intern

NVIDIA

May 2020 – Aug 2020 Seattle, WA
 
 
 
 
 

Research Intern

Google Brain

Jan 2020 – May 2020 Mountain View, CA
 
 
 
 
 

Research Intern

NASA Jet Propulsion Laboratory (JPL)

May 2018 – Aug 2018 Pasadena, CA
Researched representations and algorithms enabling autonomy of novel robot platforms.
 
 
 
 
 

Software Engineering Intern

Two Sigma Investments

May 2016 – Aug 2016 New York, NY
Added support for parallel computing platform Apache Spark to the data science toolbox Beaker Notebook (now BeakerX).
 
 
 
 
 

Research Assistant

Information Sciences Institute (ISI)

Jan 2016 – May 2017 Marina del Rey, CA
Built large-scale information retrieval system for gaining information about >300k firms from company web pages.
 
 
 
 
 

Software Engineering Intern

Microsoft

Sep 2014 – Mar 2015 Dublin, Ireland
Built business intelligence dashboard and language processing tools for software engineering teams.
 
 
 
 
 

Research Assistant

University of Rostock

Oct 2012 – Jun 2014 Rostock, Germany
Designed software tools and assisted with research projects in ubiquitous computing, bioinformatics, and web services.

Contact