publications

2018

  1. O. Marom, B. Roman. Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning. Neural Information Processing Systems (NIPS), 2018.

  2. T. Taniguchi, E. Ugur, M. Hoffmann, L. Jamone, T. Nagai, B. Rosman, T. Matsuka, N. Iwahashi, E. Oztop, J. Piater, F. Worgotter. Symbol Emergence in Cognitive Developmental Systems: a Survey. IEEE Transactions on Cognitive and Developmental Systems, 2018. [arXiv link]

  3. R. Fisher, B. Rosman, V. Ivan. Real-time Motion Planning in Changing Environments Using Topology-based Encoding of Past Knowledge. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018.

  4. B. van Niekerk, S. James, A. Earle, B. Rosman. Will it Blend? Composing Value Functions in Reinforcement Learning. To appear, Lifelong Learning: A Reinforcement Learning Approach Workshop at FAIM, July 2018.

  5. S. James, B. Rosman, G. Konidaris. Learning to Plan with Portable Symbols. ICML/IJCAI/AAMAS 2018 Workshop on Planning and Learning, 2018.

  6. B. van Eden, B. Rosman. Robots for Disaster Management. Women in Science without Borders, 2018.

  7. A. Earle, A. Saxe, B. Rosman. Hierarchical Subtask Discovery with Non-Negative Matrix Factorization. Proceedings of the Sixth International Conference on Learning Representations, 2018.

  8. C. Innes, A. Lascarides, S.V. Albrecht, S. Ramamoorthy, B. Rosman. Reasoning about Unforeseen Possibilities During Policy Learning. Technical Report, 2018. [arXiv link]

  9. N. Makondo, M. Hiratsuka, B. Rosman, and O. Hasegawa. A Non-linear Manifold Alignment Approach to Robot Learning from Demonstrations. Journal of Robotics and Mechatronics, 30(2), 2018.

  10. N. Makondo, B. Rosman, O. Hasegawa. Accelerating model learning with inter-robot knowledge transfer. IEEE International Conference on Robotics and Automation, 2018.

  11. O.C. Gorur, B. Rosman, F. Sivrikaya, S. Albayrak. Social Cobots: Anticipatory Decision-Making for Collaborative Robots Incorporating Unexpected Human Behaviors. ACM/IEEE International Conference on Human-Robot Interaction, 2018.

  12. R. Ajoodha, B. Rosman. Learning the Influence Structure between Partially Observed Stochastic Processes using IoT Sensor Data. SmartIoT: AI Enhanced IoT Data Processing for Intelligent Applications at AAAI-18, 2018.

  13. O. Marom, B. Rosman. Belief Reward Shaping in Reinforcement Learning. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018. [supplementary material]

2017

  1. J. Perlow, B. Rosman, B. Hayes, P. Ranchod. Raw Material Selection for Object Construction. PRASA-RobMech International Conference. PRASA-RobMech International Conference, 2017.

  2. R. Ajoodha, B. Rosman. Tracking Influence between Naive Bayes Models using Score-Based Structure Learning. PRASA-RobMech International Conference, 2017.

  3. A. Earle, A. Saxe, B. Rosman. Hierarchical Subtask Discovery With Non-Negative Matrix Factorization. Workshop on Lifelong Learning: A Reinforcement Learning Approach at ICML, 2017.

  4. L. Darlow, B. Rosman. Fingerprint Minutiae Extraction using Deep Learning. International Joint Conference on Biometrics, 2017.

  5. B. van Niekerk, A. Damianou, B. Rosman. Online Constrained Model-based Reinforcement Learning. Uncertainty in Artificial Intelligence, 2017.

  6. A. Saxe, A. Earle, B. Rosman. Hierarchy Through Composition with Multitask LMDPs. International Conference on Machine Learning, 2017. [supplementary material]

  7. O.C. Gorur, B. Rosman, G. Hoffman, S. Albayrak. Toward Integrating Theory of Mind into Adaptive Decision-Making of Social Robots to Understand Human Intention. Workshop on the Role of Intentions in Human-Robot Interaction at the International Conference on Human-Robot Interaction, 2017.

  8. S. James, G.D. Konidaris, and B. Rosman. An Analysis of Monte Carlo Tree Search. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017.

2016

  1. A. Saxe, A. Earle, B. Rosman. Hierarchy through Composition with Linearly Solvable Markov Decision Processes. Technical report, 2016. [arXiv link]

  2. M. Hiratsuka, N. Makondo, B. Rosman, O. Hasegawa. Trajectory Learning from Human Demonstrations via Manifold Mapping. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2016.

  3. R. Berman, R. Benade, B. Rosman, P. Nordengen. Hyperformance: Predicting High-speed Performance of a B-Double. Fourteenth International Symposium on Heavy Vehicle Transport Technology, 2016.

  4. S. James, B. Rosman and G. Konidaris. An Investigation into the Effectiveness of Heavy Rollouts in UCT. General Intelligence in Game-Playing Agents (GIGA'16) Workshop at IJCAI, 2016.

  5. P. Hernandez-Leal, M. Taylor, B. Rosman, E. L. Sucar, E. Munoz de Cote. A Bayesian approach for Learning and Tracking Switching, Non-stationary Opponents. Autonomous Agents and Multiagent Systems, 2016.

  6. B. Rosman, M. Hawasly, S. Ramamoorthy. Bayesian Policy Reuse. Machine Learning Journal, 104(1), pp. 99-127, 2016. [arXiv link].

  7. P. Hernandez-Leal, M. Taylor, B. Rosman, E. L. Sucar, E. Munoz de Cote. Identifying and Tracking Switching, Non-stationary Opponents: a Bayesian Approach. Workshop on Multiagent Interaction without Prior Coordination (MIPC), at AAAI, 2016.

2015

  1. R. Berman, R. Benade, B. Rosman. Autonomous Prediction of Performance-based Standards for Heavy Vehicles. PRASA-RobMech International Conference, 2015.

  2. R. Ajoodha, R. Klein, B. Rosman. Single-labelled Music Genre Classification Using Content-Based Features. PRASA-RobMech International Conference, 2015.

  3. N. Makondo, B. Rosman, O. Hasegawa. Knowledge Transfer for Learning Robot Models via Local Procrustes Analysis. IEEE-RAS International Conference on Humanoid Robots, 2015.

  4. P. Ranchod, B. Rosman, G. Konidaris. Nonparametric Bayesian Reward Segmentation for Skill Discovery Using Inverse Reinforcement Learning. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2015.

  5. B. Rosman, B. Hayes, B. Scassellati. Enhancing Agent Safety through Autonomous Environment Adaptation. Proceedings of the 5th joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. Providence, Rhode Island, USA, August 13-16, 2015.

  6. A. Kleinhans, B. Rosman, M. Michalik, B. Tripp, R. Detry. G3DB: A Database of Successful and Failed Grasps with RGB-D Images, Point Clouds, Mesh Models and Gripper Parameters (extended abstract). Workshop on Robotic Hands, Grasping, and Manipulation, at the IEEE International Conference on Robotics and Automation, 2015.

  7. B. Rosman, S. Ramamoorthy. Action Priors for Learning Domain Invariances. IEEE Transactions on Autonomous Mental Development, 2015.

2014

  1. B. van Eden, B. Rosman, D. Withey, T. Ratshidaho, M. Keaikitse, D. Masha, A. Kleinhans, A. Shaik. CHAMP: a Bespoke Integrated System for Mobile Manipulation. RobMech/PRASA/AfLaT, 2014.

  2. B. Rosman. Context-based Online Policy Instantiation for Multiple Tasks and Changing Environments. RobMech/PRASA/AfLaT, 2014.

  3. B. Rosman. Behavioural Domain Knowledge Transfer for Autonomous Agents. AAAI Fall Symposium on Knowledge, Skill, and Behavior Transfer in Autonomous Robots, 2014.

  4. B. Rosman. Feature Selection for Domain Knowledge Representation through Multitask Learning. IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob), 2014.

  5. A. Kleinhans, R. Detry, S. Thill, B. Rosman, B. Tripp. Modelling primate control of grasping for robotics applications. Second Workshop on Affordances: Visual Perception of Affordances and Functional Visual Primitives for Scene Analysis (in conjunction with ECCV), 2014.

  6. B. Rosman. Learning Domain Abstractions for Long Lived Robots. PhD Thesis. The University of Edinburgh. 2014.

  7. M.M.H. Mahmud, B. Rosman, S. Ramamoorthy, P. Kohli. Adapting interaction environments to diverse users through online action set selection. In Proc. AAAI Workshop on Machine Learning for Interactive Systems (AAAI-MLIS), 2014.

  8. B. Rosman, S. Ramamoorthy. Giving Advice to Agents with Hidden Goals. In Proc. International Conference on Robotics and Automation (ICRA), 2014.

  9. B. Rosman, S. Ramamoorthy, M.M.H. Mahmud, P. Kohli. On user behaviour adaptation under interface change. In Proc. International Conference on Intelligent User Interfaces (IUI), 2014.

  10. M.M.H. Mahmud, M. Hawasly, B. Rosman, S. Ramamoorthy. Clustering Markov Decision Processes for Continual Transfer. Submitted to the Journal of Machine Learning Research, 2014. [arXiv link]

2013 and earlier

  1. S. Ramamoorthy, M.M.H. Mahmud, B. Rosman, P. Kohli. Latent-variable MDP models for adapting the interaction environment of diverse users. Technical Report, University of Edinburgh, 2013.

  2. B. Rosman, S. Ramamoorthy. What Good are Actions? Accelerating Learning using Learned Action Priors. In Proc. 2012 IEEE International Conference on Development and Learning (ICDL-EpiRob). [Paper of Excellence Award]

  3. B. Rosman, S. Ramamoorthy. A Multitask Representation using Reusable Local Policy Templates. In Proc. AAAI 2012 Spring Symposium Series on Designing Intelligent Robots: Reintegrating AI.

  4. B. Rosman, S. Ramamoorthy. Learning Spatial Relationships between Objects. International Journal of Robotics Research, Special Issue on Semantic Perception for Robots in Indoor Environments. September 2011; vol. 30, 11: pp. 1328-1342.

  5. B. Rosman, S. Ramamoorthy. A Game Theoretic Procedure for Learning Hierarchically Structured Strategies. In Proceedings of 2010 IEEE International Conference on Robotics and Automation, May 3-8, 2010, Anchorage, Alaska, USA.

  6. B. Rosman. Game-Theoretic Procedures for Learning Structured Strategies from Demonstration. MSc Dissertation. The University of Edinburgh. 2009.

  7. B. Rosman. Calculation of Molecular Vibrational Normal Modes. Computational and Applied Mathematics Honours Dissertation. The University of the Witwatersrand. 2008.

  8. B. Rosman. Similarity of Abstract Images. Computer Science Honours Dissertation. The University of the Witwatersrand. 2007.

  9. S. Rauchas, B. Rosman, G.D. Konidaris and I.D. Sanders. Language Performance at High School and Success in First Year Computer Science. In Proceedings of the 37th SIGCSE Technical Symposium on Computer Science Education, pages 398-402, March 2006.