The project has a large human-robot interaction (HRI) component. We aim to develop a toolbox (see image) where teachers can define customized lessons that are then run-on social robots. The movements and actions defined in the lessons should run on multiple kinds of robots (e.g., Nao and another type of robot). Some possible areas that may be interesting to examine are:
- Defining a generic structure for specifying actions: Teachers define the lessons where the robot should execute action, but the ROSA Toolbox will run on multiple kinds of robots, not all robots have the same abilities. For example, part of a lesson may call for the robot to “point” at a specific object; how is an equivalent “pointing action” done with a robot that may not have arms?
- Related to the idea above, research and define a way to express the capabilities of different robots so that a proper action from above can be determined.
- Explore different mechanisms for how a robot can help hold motivation or re-engage a child with ASD in a lesson. One reason robots are being used in the project is that children with ASD find them interesting, but the robot needs to keep a child’s motivation through lessons over a longer period. What mechanisms or software can the robot use to help maintain the child’s motivation? How can these mechanisms be tailored to each child?
- Something else related to robot control and sensing that will be useful to the ROSA project.
1.Starting point for references
Some possible references that may start as a useful starting point include:
[1] B. Scassellati, H. Admoni, and M. Matarić, “Robots for Use in Autism Research,” Annual Review of Biomedical Engineering, vol. 14, no. 1, pp. 275–294, 2012, doi: 10.1146/annurev-bioeng-071811-150036.
[2] A. Brivio, K. Rogacheva, M. Lucchelli, and A. Bonarini, “A soft, mobile, autonomous robot to develop skills through play in autistic children,” Paladyn, Journal of Behavioral Robotics, vol. 12, no. 1, pp. 187–198, Jan. 2021, doi: 10.1515/pjbr-2021-0015.
[3] T. Schulz, J. Torresen, and J. Herstad, “Animation Techniques in Human-Robot Interaction User Studies: a Systematic Literature Review,” ACM Trans. Hum.-Robot Interact., vol. 8, no. 2, Jun. 2019, doi: 10.1145/3317325.
[4] I. van den Berk-Smeekens et al., “Adherence and acceptability of a robot-assisted Pivotal Response Treatment protocol for children with autism spectrum disorder,” Scientific Reports, vol. 10, no. 1, p. 8110, May 2020, doi: 10.1038/s41598-020-65048-3.
[5] P. Abad et al., “Integrating an Autonomous Robot on a Dance and New Technologies Festival,” in ROBOT 2017: Third Iberian Robotics Conference, Cham, 2018, pp. 75–87. doi: 10.1007/978-3-319-70833-1_7.
2.Project tasks
A suggested set of tasks for implementing the generic control mechanism could be the following:
- Create an overview of technologies and methods for working with the selected topic
- Define and implement a proposed solution for your selected topic (an algorithm, software, rapid prototype, etc.)
- Test the solution (e.g., on the project’s robots in a school setting with children, or just in a lab, this will depend on the topic chosen).
- Write master thesis report
3.Course background
- IN4140 Introduction to robot technology or good familiarity with ROS will be necessary to work with the robots.
- IN4050 Introduction to artificial intelligence and machine learning can be useful for implementing or understanding algorithms
- IN5590 Rapid Prototyping of Robotic Systems may be useful if you want to add to a robot
- IN5490 Advanced Topics in Artifical Intelligence for Intelligent Systems can be helpful for understanding how to read articles and write your masters.
4.Contact
- External advisor: Trenton Schulz (trenton@nr.no)
- Internal advisor: Jim Tørresen (jimtoer@ifi.uio.no)