Human-in-the loop planning for assistive smart environments

Extend state-of-the-art planning techniques to multirobot scenarios involving humans in assistive smart environments
Description of the Project: 

This project will explore the use of automated planning techniques in smart environments involving multiple robots and humans. The goal is to consider assisted living scenarios (e.g., preparing a meal, cleaning a room, etc.) where collaborative human-robot interaction is required to build plans for shared goals, where each agent (including the human) carries out part of the planned activities based on their abilities. A number of planning techniques will be investigated to generate such “human-in-the-loop” plans, including epistemic planning and temporal planning. Appropriate interfaces to these tools will be developed in ROS to integrate them with existing robot and smart environment ecosystems. Experiments involving multiple robot platforms (e.g., Pepper, Tiago) and human participants will be performed to assess developed tools in common scenarios.

Resources required: 
Heriot-Watt Robotarium Living Lab
Project number: 
First Supervisor: 
Heriot-Watt University
Second Supervisor(s): 
First supervisor university: 
Heriot-Watt University
Essential skills and knowledge: 
Strong programming skills
Desirable skills and knowledge: 
Knowledge of recent planning systems, familiarity with ROS, experience with robot systems

M.E. Foster & R. Petrick (2017). Separating Representation, Reasoning, and Implementation for Interaction Management: Lessons from Automated Planning. Dialogues with Social Robots: Enablements, Analyses, and Evaluation, Lecture Notes in Electrical Engineering, 427:93-107.

C. Geib, B. Craenen, and R. Petrick (2016). Generating Collaborative Behaviour through Plan Recognition and Planning. ICAPS 2016 Workshop on Distributed and Multiagent Planning (DMAP), pages 98-105.

R. Petrick and M.E. Foster (2013). Planning for Social Interaction in a Robot Bartender Domain. International Conference on Automated Planning and Scheduling (ICAPS), pages 389-397.

Mauro Dragone et al. (2015). A cognitive robotic ecology approach to self-configuring and evolving AAL systems. Eng. Appl. of AI 45: 269-280.