Innovation in (Soft) Robotics and Control
ETH Distinguished Seminar in Robotics, Systems, and Control (151-0623-00)
Welcome to the (soft) Robotics, Vision, and Controls Talks series hosted by ETH Zürich. These open talks focus on innovations in (soft) robotics, computer vision, and control systems, and are held in a hybrid format at ETH Zürich’s main campus.
About the Series
Schedule:
- Fridays at 16:00 CET in HG G5 (in-person) or via Zoom
- Location: ETH Zürich
- Join via Zoom
Next Talk
From Rigid Mechanics to Soft Intelligence: Controlling What We Cannot Fully Actuate
Speaker: Prof. Dr. Cosimo Della Santina
Affiliation: TU Delft, Netherlands
Date: November 28, 2025
Time & Location: 16:00 sharp ; ETH HG G5
Abstract
A growing part of the robotics community is moving beyond fully actuated, rigid, and transparent actuation paradigms. This shift introduces new challenges in controlling these unconventional artificial bodies. In this short lecture, using soft robotics as a representative case study, we explore how highly underactuated mechanical systems can be governed through simple, model-based control strategies. The resulting closed loops prove both robust and effective, capable of managing the complexity and uncertainty inherent to real-world interaction.
Bio
Cosimo Della Santina received the Ph.D. degree (cum laude) in Robotics from the University of Pisa in 2019. He is currently an Associate Professor at TU Delft (The Netherlands) and a Guest Research Scientist at the German Aerospace Center (DLR) in Munich. From 2017 to 2019, he was a Visiting Ph.D. student and Postdoctoral Fellow at the Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology. Between 2020 and 2021, he served as a Senior Postdoctoral Researcher and Guest Lecturer at the Technical University of Munich. His research focuses on endowing unconventional robotic systems—especially those with elastic and soft components—with motor intelligence grounded in physics-based modeling and control theory. Dr. Della Santina co-directs the Delft AI Lab SELF and is a recipient of the NWO Veni Fellowship. His work has been recognized with the 2020 Georges Giralt Ph.D. Award, the 2023 IEEE RAS Early Career Award, and an ERC Starting Grant in 2024. In 2025, he co-founded the Swiss start-up Embodied AI, which develops safe and capable robots designed to operate in human environments.
All Upcoming Talks
From Rigid Mechanics to Soft Intelligence: Controlling What We Cannot Fully Actuate
Speaker: Prof. Dr. Cosimo Della Santina
Affiliation: TU Delft, Netherlands
Date: November 28, 2025
Time & Location: 16:00 sharp ; ETH HG G5
More info
Abstract
A growing part of the robotics community is moving beyond fully actuated, rigid, and transparent actuation paradigms. This shift introduces new challenges in controlling these unconventional artificial bodies. In this short lecture, using soft robotics as a representative case study, we explore how highly underactuated mechanical systems can be governed through simple, model-based control strategies. The resulting closed loops prove both robust and effective, capable of managing the complexity and uncertainty inherent to real-world interaction.
Bio
Cosimo Della Santina received the Ph.D. degree (cum laude) in Robotics from the University of Pisa in 2019. He is currently an Associate Professor at TU Delft (The Netherlands) and a Guest Research Scientist at the German Aerospace Center (DLR) in Munich. From 2017 to 2019, he was a Visiting Ph.D. student and Postdoctoral Fellow at the Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology. Between 2020 and 2021, he served as a Senior Postdoctoral Researcher and Guest Lecturer at the Technical University of Munich. His research focuses on endowing unconventional robotic systems—especially those with elastic and soft components—with motor intelligence grounded in physics-based modeling and control theory. Dr. Della Santina co-directs the Delft AI Lab SELF and is a recipient of the NWO Veni Fellowship. His work has been recognized with the 2020 Georges Giralt Ph.D. Award, the 2023 IEEE RAS Early Career Award, and an ERC Starting Grant in 2024. In 2025, he co-founded the Swiss start-up Embodied AI, which develops safe and capable robots designed to operate in human environments.
Unified Resilient Autonomy across Robot Configurations
Speaker: Prof. Dr. Kostas Alexis
Affiliation: Norwegian University of Science and Technology (NTNU), Norway
Date: December 05, 2025
Time & Location: 16:00 ; ETH HG G3
More info
Abstract
State-of-the-art autonomy methods remain fragmented with controllers, sensor fusion pipelines, and learning algorithms typically tailored to narrow robot morphologies and operating regimes. This specialization has historically been necessary to achieve operational results, but inevitably limits generalization and slows the pace of innovation. A common blueprint for autonomy is necessary. This talk outlines a vision toward Unified Resilient Autonomy that is applicable across diverse robot configurations, whether flying, aquatic, or ground systems. By pursuing a common autonomy architecture and leveraging the lessons learned from its broad evaluation in extreme conditions, we demonstrate resilient functionality that transfers across embodiments. The discussion will highlight both the underlying methods that enable this unification as well as concrete results from field testing in unconventional environments - such as subterranean settings, ship ballast tanks, and submarine bunkers.
Bio
Prof. Dr. Kostas Alexis is a Professor at the Department of Engineering Cybernetics at the Norwegian University of Science and Technology (NTNU), head of the Autonomous Robot Lab, and Director of the Norwegian Centre for Embodied AI. Together with his team, he conducts research on resilient robotic autonomy, exploring how autonomous systems can operate in high-risk, uncertain environments by presenting resourcefulness, robustness, and redundancy. Focusing on enhancing and safeguarding the autonomy capabilities of robotic systems, his research cuts across model-based optimization for control, sensor fusion, path planning, and learning algorithms for navigation. Prof. Alexis has served as Principal Investigator in major international grants both in Europe and the US, and was the PI and team lead of Team CERBERUS, winners of the DARPA Subterranean Challenge.
Designing Human–Robot Synergies for Socio-Economic Impact
Speaker: Prof. Dr. Dino Accoto
Affiliation: KU Leuven, Belgium
Date: December 12, 2025
Time & Location: 16:00 ; ETH HG G5
More info
Abstract
The concept of embodied intelligence, i.e., the emergence of intelligent capabilities from the interaction between body, environment, and computational processes, is by now well-established in robotics. In the recent past, major advances in software have attracted the attention of both the general public and the productive sector toward artificial intelligence; in parallel, expectations have grown regarding personal robotics and intelligent automation. Large language models operate within digital interfaces, thus testifying how AI requires “a body” to generate real effects in the physical world. In this context, robotics faces a dual challenge/opportunity. On the one hand, it must respond to the expectations of society, which anticipates tangible benefits in daily life; on the other hand, it must meet the needs of the productive sector, which is called upon to address socio-economic megatrends, unprecedented in the history of technology, namely the marked ageing of the active population and the growing shortage of labour. With regards to the first challenge, the body of the robot represents the vehicle through which it can act safely and effectively in the world, in line with the principles of structural intelligence (the hardware aspect of embodied intelligence). With regard to the second, the crucial issue lies in identifying the optimal balance between automation and human labour. The prospect of complete automation, the so-called “lights-out factories”, is, according to many studies, hardly feasible and surely not fully consistent with the European vision of Industry 5.0. In summary, it is essential to ensure that the body of the robot facilitates interaction with humans, in industrial as well as non-industrial domains, guaranteeing productivity and safety while generating synergies with positive outcomes for all stakeholders: the private user, the individual operator, industry, and society as a whole. Having this scenario in the background, the presentation will introduce design approaches and mechatronic devices developed for the achievement of structural intelligence in different domains. It will also illustrate on-going projects aimed at making the robot a tool at the service of productivity in socio-economically challenging contexts, while at the same time being respectful of human factors and capable of enhancing human skills and experience.
Bio
Prof. Dino Accoto received his PhD in BioRobotics from Scuola Superiore Sant’Anna di Pisa, Italy, in 2002. He had previously been selected as an honor student of Engineering at the same institution. He was Assistant Professor of Biomedical Engineering at Scuola Superiore Sant’Anna from 2003 to 2006, following an early period as visiting scholar at Stanford University, USA. He later joined Università Campus Bio-Medico di Roma, Italy, where he was appointed Associate Professor of Industrial Bioengineering in 2015. In 2018 he moved to Nanyang Technological University, Singapore, before taking up his current appointment as Professor at KU Leuven, Belgium, in 2022. Prof. Accoto has co-founded three companies in the microengineering and robotics field, serving as managing partner, CTO, and CEO. He is the first inventor on several patent families, ranging from compliant sensors and actuators to complete robotic systems for medical and industrial applications. His research interests center on a biomechatronic design approach to human–robot interaction, human assistance and augmentation, with a focus on agile automation. Since 2023, Prof. Accoto has been the holder of the MOVU Robotics Chair at KU Leuven, Belgium.
Recent Past Talks
Voluntary: Swiss Robotics Day in Lausanne
()
November 2025
Autonomous Materials for Increased Agility and Endurance in Robots
Prof. Dr. Robert Shepherd (Cornell University, USA)
November 2025
Developing Generalist Robots
Prof. Dr. Chelsea Finn (Stanford University, USA)
October 2025
Archives
- Spring 2025 - 14 talks on soft robotics, foundation models, and embodied AI
- More semesters coming soon…