As an ADAPT funded PhD researcher you will have access to a network of 85 global experts and over 250 staff as well as a wide multi-disciplinary ecosystem across 8 leading Irish universities. We can influence and inform your work, share our networks and collaborate with you to increase your impact, and accelerate your career opportunities. Specifically we offer:
Next generation service robots offer the potential to provide efficient, flexible, and reliable performance across a range of environments that may be occupied with human users. This introduces challenges around enhancing the autonomous performance of the robot, such that it can monitor and model multiple users, making its behaviour more predictable and understandable to nearby observers. The performance of the robot must be robust to a range of different use-contexts and users, ranging from co-workers trained to use the robot to members of the public. Research in human-robot interaction, situated conversational systems, and even in the automotive space has tended to focus exclusively on a direct user engaged in a task with the system, or on safety critical issues such as avoiding collisions. The middle ground of users that might complete tasks alongside service robots, or even users that may simply need to engage the robot during its own activities have been largely unexplored.
This PhD will look at the issue of user model construction and constructive task-oriented feedback in service robotics. The focus will be on real world deployments where the novelty factor will be minimized — thus leading to richer real-world insights into the human-robot relationship. Rather than having to build a robot from scratch or rely on robots not capable of completing real world tasks, this work will where possible take advantage of existing robot platforms to address the specific challenges around modelling of multiple users in collaborative environments, and the benefits of merging the conversational modality with non-conversational communication channels. As such, the goal here is not to study interaction from a robot as human perspective, but instead from a robot perspective where the conversational and gestural modalities are just one form of interaction. This research will take a data driven approach with a focus on situated interaction. A work plan involving ethnographic studies, software and systems development, and end user studies is envisaged.
The position is best suited to a computer engineering or computer science student (or related) with a background in data science and NLP and with some experience of programming robots, preferably using the robot operating system (ROS).
Each application should only consist of
Informal inquiries can be directed to Robert Ross via email [robert.ross@tudublin.ie]