UBISS 2026 - Workshops & Instructors

Workshop A: MINIMALISM IN ROBOTICS

Maximum number of participants to be enrolled to the workshop: 24

Robot hardware, software, and onboard models (like LLMs) grow ever more complicated. In contrast, this workshop’s theme is the exploration of simple robots, seeking to understand how to reduce the complexity of robots. Though increasing sophistication may appear on the surface to be an inevitable byproduct of progress, there are at least two strong motivations for simplifying robots: (i) For researchers, simple robots can shed light on foundational scientific questions including, for instance, the resources necessary to achieve certain tasks; (ii) For developers, simplicity can engender answers to crucial engineering questions regarding manufacturability and marketability.

The workshop will examine the various resources utilized by a robot and describe metrics to turn these many forms of resources into dimensions which help characterize a given robot. Different notions of complexity —spanning various dimensions of sensing, actuation, computation, and communication— will be explored, as well as various means to reason about these notions. These include conceptual/theoretical tools (e.g., that allow the comparison of one robot to another), and also computational ones (e.g., that allow various forms of “compression” or simplification). The workshop will examine some limits (such as lower-bounds and impossibility results) and why some problems are inherently hard (in terms of computational complexity).

The workshop will have participants participate in a variety of “tracks” including elements that mix design, implementation, modification, evaluation, and analysis of robots.

By the end of the workshop, attendees would:

Be familiar with several dimensions of robotic complexity, and be able to list metrics for quantifying or comparing these aspects, and to relate different approaches in terms of these metrics;
Be able to connect and discuss several current ideas in robotics with their historical antecedents;
Understand the concept of information spaces and list several examples;
Be able to relate and contrast filtering and planning problems;
Show some familiarity with several problems in robotic complexity reduction that are known to be computationally intractable;
Be capable of analyzing novel robotic problems in order to propose simple robots that use resources in potentially innovative ways.

Prospective participants are expected to be familiar with some modern programming languages, some mathematics, ideally discrete (e.g., formal languages, automata) and continuous (calculus), or both. We do not assume prior experience with programming for robots or AI problems, but it can’t hurt.

Instructors:

Assistant Professor Alexandra Nilles, Western Washington University, USA
Assistant Professor Başak Sakçak, Maastricht University, The Netherlands
Professor Dylan Shell, Texas A&M University, USA

Alexandra Nilles is an Assistant Professor of Computer Science (Robotics) at Western Washington University. She received her Ph.D. in Computer Science from the University of Illinois at Urbana-Champaign. Following her Ph.D., she was a Postdoctoral Associate at the Collective Embodied Intelligence lab at Cornell University. She has also worked at robotics start-ups; her experience spans from theoretical motion planning, to field robotics, to bio-inspired design. Her work has been published in venues including IROS, WAFR, and RoboSoft. She has been recognized as a Cyber-Physical Systems Rising Star, and a Microsoft Future Leader in Robotics and AI.
Website

Başak Sakçak is an Assistant Professor of Robotics in the Department of Advanced Computing Sciences at Maastricht University. She received her PhD in Information Technology (Systems and Control) from Politecnico di Milano. Following her doctorate, she held positions as a Postdoctoral Researcher at Politecnico di Milano, a Senior Research Fellow at the University of Oulu, and a Visiting Scholar at the Massachusetts Institute of Technology. She was the recipient of an Academy of Finland Postdoctoral Grant. Her research aims to understand the fundamental limits of sensing, filtering, and planning, and to design and analyze methods and algorithms that enable robots to accomplish prescribed tasks. Her work focuses on robot motion planning under complex constraints, including differential, topological, and ones resulting from human-centric criteria, with particular interest in optimal planning and control under single or multiple optimization objectives. More recently, she has been interested in the theoretical limitations of processing and representing information grounded in robot embodiment and task specifications. Her work has been published both in Robotics and in Control Systems conferences and journals.
Website

Dylan Shell is a professor at Texas A&M University. He is a roboticist, having received degrees in computational & applied mathematics and computer science (from the University of the Witwatersrand, South Africa), and his M.S. and Ph.D. in computer science from the University of Southern California. His research aims to synthesize and analyze complex, intelligent behavior in systems that exploit their physical embedding to interact with the physical world. His lab works on formulations and algorithms for novel problems, such as those involving complex constraints (e.g., topological, information disclosure, sparse observability and communication) or non-traditional objectives (e.g., answering questions, or demanding compelling narrative structure). He expends effort in seeking out and addressing fundamental computational questions in robotics, producing work that has a sharper focus on foundations than most other researchers working in the area of robotics, with a deep interest in the fundamental information requirements for robot tasks, including basic limits and compression of representations. He has published papers on multi-robot task allocation, robotics for emergency scenarios, biologically inspired multiple robot systems, multi-robot routing, estimation of group-level swarm properties, minimalist manipulation, rigid-body simulation and contact models, human-robot interaction, and robotic theatre. His work has been funded by the NSF, and DARPA; and he has been the recipient of the Montague Teaching award, the George Bekey Service award, and the NSF Career award.
Website

Workshop B: ROBUST PERCEPTION AND SAFETY-AWARE PLANNING

Maximum number of participants to be enrolled to the workshop: 25

Autonomous systems increasingly operate in noisy, dynamic, human-populated environments. To be trustworthy and effective, they must perceive reliably, anticipate human motion, and plan and control actions with explicit safety guarantees. This workshop provides doctoral students (and advanced MSc/BSc, postdocs, and professionals) with a practice‑oriented path from robust perception through human tracking and motion prediction to safety‑aware planning and control – culminating in a tangible group deliverable. Participants will learn how to integrate estimation, learning, prediction, and control into a coherent autonomy stack and evaluate its safety and performance.

Upon completion, participants will be able to:

Characterize perception and estimation challenges under noise and uncertainty; select appropriate fusion and filtering methods.
Design and evaluate human tracking & motion prediction pipelines, choosing metrics and validating against domain shift.
Formulate safety‑aware planning problems with explicit constraints and risk models; apply reachability and MPC to guarantee safety.
Quantify uncertainty and propagate it through prediction and planning for risk‑aware decision‑making.
Integrate perception, prediction, planning, and control into a coherent autonomy stack and demonstrate performance & safety with reproducible experiments.

The workshop is targeted to doctoral students (primary), plus MSc/BSc candidates, postdocs, and industry/public sector professionals. To do well, participants are expected to have skills and knowledge in programming (Python is required, C++ would be helpful), tools (ROS2 basics, Git, Linux shell), machine learning (deploying learning based algorithms (LSTM, VAE), any ML stack (Jupyter/NumPy/PyTorch/TensorFlow)), mathematics (linear algebra, probability and statistics, optimization, control theory), perception (familiarity with cameras/LiDAR/IMU, basic filtering (EKF/UKF) and calibration concepts) and hardware (basic experience in working with simple robots, e.g. turtlebots).

Instructors:

Professor Simo Särkkä, Aalto University, Finland
Assistant Professor Tomasz Kucner, Aalto University, Finland
Assistant Professor Dominik Baumann, Aalto University, Finland
Assistant Professor Shankar Deka, Aalto University, Finland

Simo Särkkä received his Master of Science (Tech.) degree in engineering physics and mathematics, and Doctor of Science (Tech.) degree in electrical and communications engineering from Helsinki University of Technology, Espoo, Finland, in 2000 and 2006, respectively. Currently, he is a Full Professor at Aalto University (started 2015, tenured 2019, full from 2024) and an Adjunct Professor (= Docent) with Tampere University and LUT University. He is also a Fellow of European Laboratory for Learning and Intelligent Systems (ELLIS), PI of ELLIS Institute Finland, and the leader of AI Across Fields (AIX) program and AI for Health SIG in Finnish Center for Artificial Intelligence (FCAI).
Website

Tomasz Kucner is an Assistant Professor in the Department of Electrical Engineering and Automation at Aalto University, specializing in mobile robotics and autonomous systems. He earned his Ph.D. in Computer Science from Örebro University, Sweden, and has extensive experience in developing algorithms that enable robots to operate safely and efficiently in dynamic, human-populated environments. His research focuses on human-aware navigation, motion prediction, and dynamic environment mapping, leveraging AI and machine learning to advance autonomous systems. Tomasz has authored and co-authored several book chapters and numerous peer-reviewed publications presented at leading conferences such as ICRA and IROS.
Website

Dominik Baumann received the Dipl.-Ing. degree from the Dresden University of Technology, Dresden, Germany, in 2016 and the Ph.D. degree from KTH Stockholm, Stockholm, Sweden, in 2020, both in electrical engineering. He is currently an Assistant Professor with Aalto University, Espoo, Finland. He was a joint Ph.D. student with the Max Planck Institute for Intelligent Systems, Stuttgart/Tübingen, Germany, and KTH Stockholm. After his Ph.D., he was a Postdoctoral Researcher with RWTH Aachen University, Aachen, Germany, and Uppsala University, Uppsala, Sweden. His research interests include learning and control for networked multi-agent systems. Dr. Baumann was the recipient of the best paper award at the 2019 ACM/IEEE International Conference on Cyber-Physical Systems, the best demo award at the 2019 ACM/IEEE International Conference on Information Processing in Sensor Systems, and the Future Award of the Ewald Marquardt Foundation. He is currently Chair of the Finland section of the joint chapter of the IEEE Control Systems, Robotics and Automation, and Systems, Man, and Cybernetics societies.
Website

Shankar Deka is an Assistant Professor of Automatic Control in the Department of Electrical Engineering and Automation at Aalto University, Finland. He received his PhD in Mechanical Science and Engineering from the University of Illinois at Urbana-Champaign, USA, in 2019. He previously held postdoctoral researcher positions at KTH Royal Institute of Technology, Stockholm in 2022-2023 and University of California, Berkeley during 2019-2022. His research focus is on nonlinear stability theory, reachability analysis, robust and optimal control, and learning for dynamics and controls, with applications to certifiably safe medical robotics and precision agriculture. Dr. Deka is on the editorial board Unmanned Systems, a board member of IEEE CSS Finland Chapter, and affiliated with the Finnish Center for Artificial Intelligence.
Website

Workshop C: ROBOT MAKERS: EXPRESSION THROUGH ROBOTICS

Maximum number of participants to be enrolled to the workshop: 24

The explosion of Maker spaces and rapid fabrication tools has promised to enable the easy creation of physical objects. Invented a cool, new fork-spoon combo? Now you print it out immediately. Want your lamp to turn on when you wave at it? Grab a microcontroller and a sensor, and you are good to go. All of these off-the-shelf components are readily available to the public, making engineering more accessible than ever.

But how does one figure out how to combine these different supplies into a functional device? What is the most effective path to realizing new ideas? How can we propagate this knowledge and skill to the next generation of Makers?

In this workshop, we will focus on designing, developing, debugging, and demonstrating new robots that incorporate existing and state-of-the-art rapid fabrication technologies. Students will explore the interplay between physical fabricated objects and electronics and learn how to incorporate actuation, sensing, and intelligent control into rapidly fabricated mechanisms, thus opening opportunities for Making new smart devices to enhance our everyday lives.

As part of the workshop, the instructors will outline design approaches and fabrication processes for a variety of rapid prototyping tools, including (but not limited to):

additive manufacturing (e.g. 3d printing),
planar subtractive manufacturing (e.g. laser cutting),
casting and molding,
microcontroller programming (e.g. Arduino),
off-the-shelf sensors, actuators, and other devices, and
free and open source software and development environments.

With this knowledge, we will aim to tackle the following questions:

How can anyone ideate and then create their own physical artifacts with specified properties and behaviors?
How can this creation be done in a technically rigorous way to maximize success while minimizing the requirements on formal engineering training?
How can we use our designs to connect to a broader set of other people?

Students will explore these questions through mini-labs and a final showcase.

This workshop would be well suited for participants from a variety of backgrounds and professional experiences, including, but not limited to, students in engineering, science, architecture, and art. It will be most beneficial to students who have some previous experience with at least one of the listed technologies and a desire to learn how to integrate it seamlessly with the others. Students will have access to the tools and machinery in the Super Fab Lab Oulu. They will perform basic programming tasks and draw models using software provided as part of the workshop.

Instructors:

Associate Professor Ankur Mehta, University of California, Los Angeles, USA
Associate Professor Cynthia Sung, University of Pennsylvania, USA

Ankur Mehta is an Associate Professor of Electrical and Computer Engineering at UCLA, and directs the Laboratory for Embedded Machines and Ubiquitous Robots (LEMUR). Pushing towards his visions of a future filled with robots, his research interests involve printable robotics, rapid design and fabrication, control algorithms and architectures, and multi-agent networks. Prior to joining the UCLA faculty, Prof. Mehta was a postdoc at MIT’s Computer Science and Artificial Intelligence Laboratories investigating design automation for printable robots. Before that, he conducted research as a graduate student at UC Berkeley in wireless sensor networks and systems, small autonomous aerial robots and rockets, control systems, and micro-electro-mechanical systems (MEMS). Prof. Mehta received the NSF CAREER award in 2018, and was named a Samueli Fellow in 2015. He has received best paper awards in the 2015 IEEE Robotics & Automation Magazine and 2014 International Conference on Intelligent Robots and Systems (IROS). When not in the lab, Ankur enjoys puzzles, ultimate frisbee, board games, and social dancing.
Website

Cynthia Sung is an Associate Professor in the Department of Mechanical Engineering and Applied Mechanics (MEAM) and a member of the General Robotics, Automation, Sensing & Perception (GRASP) lab at the University of Pennsylvania. She completed a Ph.D. (2016) in Electrical Engineering and Computer Science at MIT, advised by Prof. Daniela Rus, and a B.S. (2011) in Mechanical Engineering from Rice University. Her research interest is computational design and fabrication for robotic systems, with a particular focus on origami-inspired and compliant robots. She is the recipient of a 2023 ONR Young Investigator award, 2019 NSF CAREER award, 2020 Johnson & Johnson Women in STEM2D Scholars Award, and a 2017 Popular Mechanics Breakthrough Award.
Website