Teaching & Training Students for Cognitive Robotics
The field of cognitive robotics has been rapidly advancing in recent years, with the potential to revolutionize various industries such as healthcare, retail, manufacturing, and transportation. As a result, there is an increasing demand for professionals with the knowledge and skills necessary to design, develop, and implement cognitive robotics systems. This demand is where the workshop “Teaching and Training Students for Cognitive Robotics” becomes of utmost importance.
The implementation and design of cognitive robot systems is a challenging process which requires an overview of the physics of robots & their environments, sensors & sensor data, perception, probabilistic state estimation, knowledge representation and reasoning, robot learning, task and motion control, and cognitive architectures. It takes just as much effort to consider these issues when designing robots as it does to teach the entirety of robotics. How can we establish and foster the capabilities to understand the interrelation of constituent system parts and how systems work over time and within the context of larger systems (system thinking), the decomposition, pattern recognition, abstraction, and algorithm design (computational thinking), strategies, processes and abstraction (mathematical thinking), the ability to make reasoned decisions (decision making), the awareness on how technology impacts society (sustainability), and the intrinsic motivation and willingness to solve challenges of robotics (motivation)?
In this workshop, we address this very challenge by systematizing a best practice from experienced teachers and researchers. How is it possible to integrate the needs of all stakeholders? What are the perspectives of students, educators, and researchers, as well as state of the art in cognitive robotics? All of these considerations should also include the demands of society on the subject of cognitive robotics.
To ensure the most comprehensive picture of teaching and learning cognitive robotics, the workshop actively involves the participants. Each session of the workshop is dedicated to a specific question framed by a keynote speech. Based on the previous day, participants will formulate their experiences in groups and then discuss them in plenary.
|time||October 1st, 2023
|08:30 – 08:45||Opening Session – Michael Beetz, Jörn Syrbe|
|08:45 – 10:00||Session 1: Research-oriented Teaching – Michael Beetz|
|10:00 – 11:00||Coffee break|
|11:00 – 11:45||Session 2: Chad Jenkins|
|11:45 – 12:30||Session 3: Bruno Siciliano|
|12:30 – 13:30||Lunch|
|13:30 – 14:15||Session 4: Karinne Ramirez-Amaro|
|14:15 – 15:00||Session 5: David Vernon|
|15:00 – 16:00||Coffee break|
|16:00 – 16:45||Session 6: Jean Oh
|16:45 – 17:30||Session 7: Serena Ivaldi
Content of the workshop
- System thinking - understanding of interrelation of system's constituent parts and how systems work over time and within the context of larger systems. To achieve this, students must be enabled to develop an understanding of a system's structure, the dynamic behavior of a system, system at a different scale, and reduce the complexity of a system (cf Ross D. Arnold & Jon Wade, 2015). Applied to robotics, a roboticist needs to develop an awareness of the purpose of a robotic system as well as an understanding of the characteristics of a robotic system. In short: A roboticist must overview the hardware system, the software components, as well as, the implications of a developing environment.
- Computational thinking - Decomposition, pattern recognition, abstraction, and algorithmic design.
Teaching cognitve robotics includes the capability to decompose a complex problem or task into easy to solvable or understandable subtasks.
Following the decomposition, subtasks are solved by identifying patterns. These solutions are based on experience and known problem solving processes.
Understanding these patterns allows it to focus on the most relevant aspects of the problem. Unimportant aspects of the problem are omitted. The focus is on the relevant details. The initial problem is greatly simplified.
Finally the understanding of tasks, subtasks, patterns, and abstractions can be defined in rules or algorithms.
- Mathematical thinking - problem solving and strategies, modeling of processes and objects, abstraction of objects and processes (Kodde-Buitenhuis, 2015)
- Decision making - the ability to make reasoned decisions
- Technology impact awareness - the ability to understand and reflect the effect of the developed system (Sustainability competence)
- Active learning - the intrinsic motivation and willingness to solve challenges of robotics
In higher education and vocational training there are a number of didactic approaches that have been established in the recent past. One of these approaches is Constructive Alignment (Biggs 1996), which includes teaching and learning methods as well as assessment methods and intended learning goals. In brief, Biggs and Tang (2011) summarize the goal of student-centered teaching as follows: Learners must be given the opportunity to achieve the intended learning goals through the teaching and learning content provided. This easily comprehensible demand on teaching and learning processes ultimately results in skills or competences that students can incorporate into their learning personas and apply in later contexts. The workshop will focus on an exemplary methodology that is being used in the preparation of the teaching of a new master's program in cognitive robotics at the University of Bremen, Germany. In this course, research-oriented teaching is used alongside the ideas of Constructive Alignment, in which students can approach topics and tools of research in the field of cognitive robotics in an interactive and immersive teaching and learning environment that is currently under construction.
Part of this conception of teaching is the AVIVA method (Städeli et. al. 2010), which originated in Switzerland. This method focuses on the active design of learning phases by the learners, in which phases of learning are directed to the respective content and prior knowledge of the learners. After this connection to previous knowledge, new content is introduced and later applied and evaluated by the students. This concept will be discussed with the participants and invited guests through further examples, e.g. the introduction of a robotics major at Michigan University or the robotics course at CMU Africa.
Each session of the workshop is addressing the challenge of cognitive robotics and invites the participants to discuss based on their experience. To enable the participants to approach the respective aspect, invited speakers will give a keynote speech and open the topic’s discussion. The results of the discussion will be recorded on an online whiteboard. The presentations are short-form presentations. With this workshop we address (early career) researchers, educators, and policy makers in the field of research,governance as well as education. Thinking about teaching robotics in general and cognitive robotics in particular and how to enable roboticists to develop capabilities to solve robotic problems is challenging. The “Teaching & Training students for Cognitive Robotics” workshop will add the teaching and learning perspective to IROS 2023.
 R. D. Arnold and J. P. Wade, “A Definition of Systems Thinking: A Systems Approach,” Procedia Computer Science, vol. 44, pp. 669–678, 2015, doi: 10.1016/j.procs.2015.03.050.
 P. Drijvers, H. Kodde-Buitenhuis, and M. Doorman, “Assessing mathematical thinking as part of curriculum reform in the Netherlands,” Educ Stud Math, vol. 102, no. 3, pp. 435–456, 2019, doi: 10.1007/s10649-019-09905-7.
 J. Biggs, “Enhancing teaching through constructive alignment,” High Educ, vol. 32, no. 3, pp. 347–364, Oct. 1996, doi: 10.1007/BF00138871.
 C. Städeli, A. Grassi, K. Rhiner, and W. Obrist, Eds., Kompetenzorientiert unterrichten: das AVIVA-Modell, 1. Aufl. Bern: hep, der Bildungsverlag, 2010.
 J. B. Biggs and C. S. Tang, Teaching for quality learning at university: what the student does, 4th edition. Maidenhead, England New York, NY: McGraw-Hill, Society for Research into Higher Education & Open University Press, 2011.
We aim to initiate a sustainable dialogue on best practices of didactic approaches of teaching cognitive robotics. In order to foster the exchange between researchers, students, teachers and policy makers, we intend to initiate a workshop series and to publish the results of the ongoing discussion.
The workshop will be supported by the Collaborative Research Center "Everyday Activity Science and Engineering (EASE)," funded by the German Research Foundation (DFG) at the University of Bremen. The workshop supported by the infrastructure project "Integrated e-Learning for Cognitive Robotics (IntEL4CoRo)", funded by the German Federal Ministry of Education and Research (BMBF).