Research

During my PhD, I was a member of the Autonomous Robotics and Perception Laboratory at the University of Colorado, Boulder where I undertook research in perception, planning and control for agile autonomous vehicles under the direction of Dr. Gabe Sibley.

The focus of my PhD research was perception, planning, and control for the Parkour Cars project. The project aimed at developing novel high speed perception, planning and control methods to autonomously enable high-speed and agile maneuvers including jumps, loop-the-loops and precise high-speed driving for small robots. These conditions required high fidelity perception and control that can handle the 3D setting of the problem as well as run tractably on hardware in real-time.

3D simulation of the research environment Parkour Cars experimental setup

Publications

A Holistic Framework for Planning, Real-time Control and Model Learning for High-speed Ground Vehicle Navigation Over Rough 3D Terrain

Nima Keivan, Steven Lovegrove, and Gabe Sibley

IROS 2012 Workshop on Robot Motion Planning: Online, Reactive, and in Real-time, 2012

PDF

Realtime Simulation-in-the-loop Control for Agile Ground Vehicles

Nima Keivan and Gabe Sibley

In Proceedings of Towards Autonomous Robotic Systems (TAROS) 2013, 2013 — Best Student Paper

PDF

Asynchronous Adaptive Conditioning for Visual-Inertial SLAM

Nima Keivan and Gabe Sibley

In Proceedings of the International Symposium on Experimental Robotics (ISER) 2014, 2014

PDF

Constant-Time Monocular Self-Calibration

Nima Keivan and Gabe Sibley

In Proceedings of the IEEE International Conference on Robotics and Biomimetics (ROBIO) 2014, 2014

PDF

Online SLAM with any-time self-calibration and automatic change detection

Nima Keivan and Gabe Sibley

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2015, 2015

PDF

Asynchronous adaptive conditioning for visual-inertial SLAM

Nima Keivan and Gabe Sibley

The International Journal of Robotics Research 34 (13), 1573-1589 (IJRR) 2015, 2015

Generative scene models with analytical path-tracing

Nima Keivan and Gabe Sibley

RSS 2015 Workshop on Robot Simulation, 2015

PDF