Research Interests:
Autonomous robotics, Motion Planning & Prediction, Human-Robot Interaction shaping
Research Description:
Recently my research and engineering work tackles challenging Motion, Planning and Prediction tasks in the domain of autonomous driving.
My doctoral thesis pursues fast and scalable interactive robot motion planning that is intention-aware. Specifically my work focusses on real-time distributed navigation, constructing interactive motion models of other agents for counterfactual reasoning over their possible goals and intentions. This involves a variety of subproblems ranging from light-weight iterative planners for fluid pedestrian avoidance to intention prediction in dense multi-agent setups. A particularly unique aspect of my approach is that I consider issues such as agent awareness or share-of-effort in navigation. I am also interested in causal structure learning and the use of natural language in human-robot interaction problems.
Other Interests:
Robot football, amateur robotics film making.
Publications: Google Scholar
S. Penkov, A. Bordallo, S. Ramamoorthy, Physical symbol grounding and instance learning through demonstration and eye tracking, IEEE International Conference on Robotics and Automation, 2017.
Preprint, Video, Bibtex
F. Previtali, A. Bordallo, L. Iocchi, S. Ramamoorthy, Predicting Future Agent Motions for Dynamic Environments, IEEE/AMLA International Conference on Machine Learning and Applications (ICMLA), 2016.
Preprint, Publisher's link, Bibtex
J. Cano Reyes, D. White, A. Bordallo, C. McCreesh, P. Prosser, J. Singer, V. Nagarajan, Task variant allocation in distributed robotics, Robotics: Science and Systems (R:SS), 2016.
Preprint, Publisher's link, Bibtex
J. Cano Reyes, A. Bordallo, V. Nagarajan, S. Ramamoorthy, S. Vijayakumar, Automatic configuration of ROS applications for near-optimal performance, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016.
Preprint, Publisher's link, Bibtex
S. Penkov, A. Bordallo, S. Ramamoorthy, Inverse eye tracking for intention inference and symbol grounding in human-robot collaboration, Robotics: Science and Systems Workshop on Planning for Human-Robot Interaction, 2016.
Preprint, Publisher's link, Bibtex
A. Bordallo, F. Previtali, N. Nardelli, S. Ramamoorthy, Counterfactual reasoning about intent for interactive navigation in dynamic environments, In Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2015.
Preprint, Video, Publisher's link, Bibtex
F. Previtali, A. Bordallo, S. Ramamoorthy,
IRL-based prediction of goals for dynamic environments, IEEE International Conference on Robotics and Automation (ICRA) 2015, Workshop on Machine Learning for Social Robotics.
Preprint