Paul G. Stankiewicz — accepted AI-conference papers

2018

A Motion Planning Approach for Marsupial Robotic Systems

Paul G. Stankiewicz, Stephen Jenkins, Galen E. Mullins, Kevin C. Wolfe, Matthew S. Johannes, Joseph L. Moore

IROS 2018poster

This paper outlines an algorithmic approach for the automatic coordination and planning of heterogeneous multi-robot teams. Specifically, this work addresses the marsupial-based subset of multi-robot teams, where “carrier” robots transport and deploy “passenger” robots. The approach starts with a hi…

Cited by 8 Source ↗Scholar ↗

2018

Accelerated Testing and Evaluation of Autonomous Vehicles via Imitation Learning

Galen E. Mullins, Austin G. Dress, Paul G. Stankiewicz, Jordan D. Appler, Satyandra K. Gupta

ICRA 2018poster

In this paper, we investigate the use of surrogate agents to accelerate test scenario generation for autonomous vehicles. Our goal is to train the surrogate to replicate the true performance modes of the system. We create these surrogates by utilizing imitation learning with deep neural networks. By…

Cited by 26 Source ↗Scholar ↗

2017

Automated generation of diverse and challenging scenarios for test and evaluation of autonomous vehicles

Galen E. Mullins, Paul G. Stankiewicz, Satyandra K. Gupta

ICRA 2017poster

We propose a novel method for generating test scenarios for a black box autonomous system that demonstrate critical transitions in its performance modes. In complex environments it is possible for an autonomous system to fail at its assigned mission even if it complies with requirements for all subs…

Cited by 126 Source ↗Scholar ↗