Khoshrav Doctor

Khoshrav Doctor

Ph.D. student in Computer Science at the University of Massachusetts, Amherst. Working at the Laboratory for Perceptual Robotics

Publications

Learning Intrinsically Motivated Transition Models for Autonomous Systems

Published in IEEE International Conference on Development and Learning (ICDL), 2022

Studies mechanism for embodied agents to build experiential models of interaction to support autonomous decision making

Recommended citation: K. Doctor, H. Ghosh and R. Grupen, "Learning Intrinsically Motivated Transition Models for Autonomous Systems," 2022 IEEE International Conference on Development and Learning (ICDL), London, United Kingdom, 2022, pp. 9-14, doi: 10.1109/ICDL53763.2022.9962188. http://khoshrav.github.io/files/LearningIntrinsicallyMotivatedTransitionModelsICDL2022.pdf

Evaluating Sensorimotor Abstraction on Curricula for Learning Mobile Manipulation Skills

Published in IEEE International Conference on Development and Learning (ICDL), 2022

Investigates strategies for learning heirarcial skills in a landscape of attractors.

Recommended citation: O. Youngquist, A. Spiro, K. Doctor and R. Grupen, "Evaluating Sensorimotor Abstraction on Curricula for Learning Mobile Manipulation Skills," 2022 IEEE International Conference on Development and Learning (ICDL), London, United Kingdom, 2022, pp. 75-80, doi: 10.1109/ICDL53763.2022.9962221. http://khoshrav.github.io/files/EvaluatingSensorimotorAbstractiononCurriculaICDL_2022.pdf

A Unified Multi-Faceted Video Summarization System

Published in , 2017

This paper addresses automatic summarization and search in visual data comprising of videos, live streams and image collections in a unified manner. In particular, we propose a framework for multi-faceted summarization which extracts keyframes (image summaries), skims (video summaries) and entity summaries (summarization at the level of entities like objects, scenes, humans and faces in the video).

Recommended citation: Sahoo, A., Kaushal, V., Doctor, K., et al.\ 2017, arXiv:1704.01466 http://khoshrav.github.io/files/video-summarization.pdf

PowerShare: A distributed processing system for Android devices

Published in International Conference of Communication and Electronic Systems, 2016

PowerShare is an implementation of a Distributed processing system for Android devices. It allows users to reduce the runtime of long tasks by forming a WiFi Peer to Peer network and splitting the data to be processed across nodes in the network.

Recommended citation: V. P. Kumar, S. Jayawant, K. Doctor and S. Vidhani, PowerShare: A distributed processing system for Android devices, 2016 International Conference on Communication and Electronics Systems (ICCES), Coimbatore, 2016, pp. 1-5. doi: 10.1109/CESYS.2016.7889989s http://khoshrav.github.io/files/PowerShare.pdf