I am a member of the Marine Robotics Group in the Computer Science and Artificial Intelligence Lab (CSAIL), where I'm advised by John Leonard.
My research lies at the intersection of machine learning and autonomous robotic navigation. I'm particularly interested in two sorts of problems: achieving robust machine learning on robotic systems to the benefit of navigation tasks, and applying constraints imposed by the physical environment to aid in learning on robots. My research is funded in part by an NSF Graduate Research Fellowship.
Previously I have worked on distributed learning algorithms for underwater exploration with application to biological surveying tasks. Before that, I was an undergraduate student at Stevens Institute of Technology where I did research on robot mapping in the Robust Field Autonomy Lab under Brendan Englot.
Recently, some friends in the MIT Graduate Program in Science Writing put together a documentary that covered some of the underwater exploration research my colleagues in the MIT/WHOI Joint Program and I have done.
- T. Shan, K. Doherty, J. Wang, and B. Englot, "Bayesian Generalized Kernel Inference for Terrain Traversability Mapping", 2nd Annual Conference on Robot Learning (CoRL). October 2018. < pdf , video >
- K. Doherty, G. Flaspohler, N. Roy, and Y. Girdhar, "Approximate Distributed Spatiotemporal Topic Models for Multi-Robot Terrain Characterization", IEEE International Conference on Intelligent Robots and Systems (IROS). October 2018. < pdf >
Best Paper Award Finalist (6 finalists of 1,254 accepted)
- K. Doherty, Y. Girdhar, "Unsupervised Spatial-Semantic Maps for Human-Robot Collaboration in Communication-Constrained Environments," IEEE International Conference on Intelligent Robots and Systems (IROS). Poster. September 2017. < pdf >
- K. Doherty, Learning-aided 3D Occupancy Mapping for Mobile Robots, Stevens Institute of Technology, Bachelor's Thesis, 2017. < pdf, slides >
- K. Doherty, J. Wang, and B. Englot, "Bayesian Generalized Kernel Inference for Occupancy Map Prediction," Proceedings of the IEEE International Conference on Robotics and Automation. May 2017. < pdf, code >