SWARM2025

WORKSHOPS

Workshop 1
Harsh environment robotics – Prof. Fumi Matsuno

  1. Fuel cell system development for harsh environment at F-REI – Akihiro IIYAMA, Go Matsuo, Tetsuya Kamihara, Keiji Okada, Atsuko Fukaya, Satoru Imazu, and Masanari Yanagisawa1
    Drones flying in harsh environments are expected to require long flight times and large payloads, which are difficult to achieve with conventional batteries. We are conducting research and development on the application of hydrogen-fueled polymer electrolyte fuel cells to drones, focusing mainly on weight reduction and durability. An overview of the research and development will be reported.
  2. Fluid powered robots for harsh environments – Koichi Suzumori2
    Fluid-powered robots (pneumatic or hydraulic robots) that the author has developed to date are introduced. Pneumatics realizes lightweight and compliance, while hydraulics realizes high power density and environmental resistance. They can be used in harsh environments (rain, dust, shock, unknown environment, etc.).
  3. Aerial Interception of Multiple Drones by Multiple Distributed Chasers with Batch Deployments – Nontaphat Charuvajana1, Panithan Rithburi2, Sutthiphong Srigrarom3, Boo Cheong Khoo3 and Florian Holzapfel42
    In this paper, we investigate the problem of air-to-air drone interception for counter-UAS operations, using multi-agent reinforcement learning, strategic surrounding approaches and sequences of deployments. The intruding drones are modelled by Boid Algorithm, analogous to flocks of birds. The fleet of interceptors (agents) are assigned to intercept or chase the intruders mid-air at designated area in batch deployments. For intercepting or catching purpose, we applied the StringNet strategy and greedy strategy to break, herd and encircle several subgroups of targets. We also apply task allocation algorithm to assign each of the agent to track and look for specific target within the subgroup. This allows better chasing effectiveness, when there are limited numbers of intercepting drones, assume equalled to or smaller than the intruding drones. The heuristic task allocation framework is modeled as matching and optimization problem. The preliminary mix-integer, non-linear problem (MINLP) formulations are based on probability of interception and resource readiness. The interceptors are deployed in sequences of batches allowing follow-up action. The single deployment performs better in term of action time, however, the batches deployments give higher success rate due to clearer task assignments. Preliminary works have shown that the combination of the proposed Hunting, heuristic task allocation and batch deployment performed well for as many as 15 intruders, and by 15 interceptors with 100% interceptions.
  4. Transfer of Skill from Human to Robot – Kouhei Ohnishi3
    There are many atypical tasks which are easily accomplished by the human but are very difficult for the robot. In most of such cases, the human skills are indispensable but they can not be digitized nor transferred by the communication line. That prevents the robot to use the human skills in such tasks. The paper shows how we can transfer the human skills to the robot. In the proposed strategy, two types of AI are necessary which are corresponding to human cerebrum and cerebellum. The experimental examples based upon this strategy shows that the robot can accomplish sensitive tasks which are carried out only by the human.
  5. Intelligent, Autonomous and Swarm Control of Robots in Harsh Environment (Keynote Talk) – Masayoshi Tomizuka4
    Japan has many earthquake sources and volcanic zones, and is prone to heavy rains. Although the occurrence of disasters cannot be avoided, it should be possible to save people’s lives and prevent the damage from spreading by utilizing AI and robotics technology. Fukushima Institute of Research Education and Innovation (F-REI) conducts research on intelligent, autonomous and swarm control of robots in harsh environment. Robots include Autonomous Unmanned Aerial Vehicles (AUVs) and Autonomous Unmanned Ground Vehicles (UGVs), and AI support them as enabling technology. AUVs and AGVs have complementary strengths, and their combined use generates synergy. Autonomous AUVs and AGVs are examples of mechatronic systems and they continue to evolve as new decision making methodologies and sensor and computation technologies are introduced. F-REI’s initial research focuses on surveying disaster areas and rescue activities in collaboration with human workers, but in the future, one of our goals is to develop technology that can respond at all points during a disaster, such as evacuation guidance and reconstruction activities, in addition to rescue.
  1. F-REI ↩︎
  2. [1] National University of Singapore, Computer Science Dept, Singapore
    [2] Technical University of Munich Asia, Singapore
    [3] National University of Singapore, Mechanical Engineering Dept, Singapore
    [4] Technical University of Munich, Institute of Flight Systems Dynamics, Germany ↩︎
  3. Keio University and F-REI ↩︎
  4. Autonomous, Intelligent, and Swarm Control Research Unit – University of California Berkeley and F-REI ↩︎

Workshop 2
Muscle to Mobility (M2): Crafting Soft Robots with Bioinspired Design Principles

This workshop on bioinspired soft robotics aims to bridge biological science and robotics engineering, focusing on the creation of innovative, modular, and adaptive soft robots that can replicate the complex behaviors observed in natural systems. Biological information, such as muscle deformation, tissue composition, and movement dynamics, plays a fundamental role in developing soft robots that can execute sophisticated, lifelike actions. In neuroscience terms, the goal is to understand high-dimensional neuronal networks, including network complexity, interdependencies, and how learning shapes network solutions. The workshop will explore developing a self-organizing neuronal network model of spinal cord circuitry that operates through attractor dynamics, achieving multiple solutions based on the biomechanics of the body. Participants will examine how dynamically evolving sensory synergies stabilize muscle synergies to achieve natural, underactuated movements. This model will include a dynamic, sensorized biomechanical body with skeletal bones, joints, muscles, and skin. These insights will provide the attendees a deep understanding of how to transform biological concepts to develop the soft robotics platform through a creative design process. The workshop will provide a plug-and-play framework for designing soft robotic systems based on the motion dynamics of invertebrates or vertebrates, integrating components such as skeletal bone, connective tissues, and muscle tissues—each optimized for specific functions. For instance, in invertebrates, skeletal bone provides structural support, connective tissue offers flexibility, and muscle tissue delivers soft, compliant, and contractile capabilities. Participants will explore the development process for soft robotic modules, visualized in three phases: understanding biological movement, designing actuators inspired by this movement, and employing a novel manufacturing technique to create precise, dynamic soft systems. A key goal of this workshop is to inspire curiosity and creativity among participants by providing an interactive and interdisciplinary learning experience—from formulating biological hypotheses to designing and fabricating bioinspired robotic modules that mirror natural behaviors. By leveraging the synergy between biology and robotics, attendees will gain insights into creating innovative, adaptive soft robots capable of performing complex tasks, ultimately advancing the field of soft robotics toward more versatile, sustainable, and intelligent systems.

Schedule

  • 9:00 – 9:15 Welcome and Opening Remarks
    Speaker: Saravana, Henrik and Etienne
  • 9:15 – 9:40 Neuroscience Control Strategies
    Speaker: Prof. Dr. Henrik Jörntell
    Title: Neuroscience Control Strategies for soft tissues
  • 9:40 – 10:05 Simulating Movement Science
    Speaker: Dr. Hari Teja
    Title: Computational and neural basis of flexible sensorimotor control in biological systems
  • 10:05 – 10:30 Control of bioinspired Robots
    Speaker: Prof. Poramate Manoonpong
    Title: Embodied Intelligence in Soft Robotics: From Morphological to Neural Computation
  • 10:30 – 10:55 Human Robotics
    Speaker: Prof. Dr. Etienne Burdet
    Title: TBA
  • 10:55 – 11:20 Soft Robotics
    Speaker: Prof. Dr. Cecilia Laschi
    Title: Embodied Intelligence in Octopus-Inspired Soft Robotics
  • 11:20 – 11:45 Bioinspired Design Process
    Speaker: Dr. Junior Rojas (Asst Prof. Dr. Saravana)
    Title: Soft-Body Simulation for Modeling Motor Behavior and Morphogenesis
  • 11:45 – 12:05 Panel discussion
    Speaker: Panelist (all speakers)
  • 12:05 – 12:15 Tank you note

Talk Details

Talk 1

Title: Neuroscience Control Strategies for soft tissues
Presenter: Henrik Jörntell,Professor of Neurophysiology, at the Department of Experimental Medical Science, Lund University, Lund, Sweden
Abstract: This talk will illustrate the tremendous gain in information richness that arises in a dynamic, sensorized biomechanical body due to the intrinsic compliances in biological tissue. How does the brain cope with and draw advantage of this information richness in the dynamic’s domain? It will be illustrated that the neuronal circuitry of the CNS is in fact ideal to achieve multiple solutions under such conditions, and that this can be utilized to achieve highly efficient underactuated control. 

Talk 2

Title: Computational and neural basis of flexible sensorimotor control in biological systems
Presenter: Hari Teja Kalidindi, Postdoctoral Researcher, Donders Institute for Brain, Cognition, and Behaviour at Radboud University
Abstract: How do biological systems achieve highly adaptive, goal-directed movement without relying on massive datasets or computational power? This talk will explore the fundamental principles of how brain controls movements, drawing on modern developments in large-scale brain recordings, dynamical systems and control theory. I will highlight the recent discovery of oscillations in the monkey motor cortex – a critical region for goal-directed movements – demonstrating how these neural dynamics can be generated in randomly connected neural circuits without need for data-driven optimization or learning. I will argue that these principles are key to understanding the efficiency and flexibility of biological motor control.

Talk 3

Title: Embodied Intelligence in Soft Robotics: From Morphological to Neural Computation
Presenter: Poramate Manoonpong, Professor, SDU Biorobotics, University of Southern Denmark (SDU), Denmark
School of Information Science and Technology, Vidyasirimedhi Institute of Science and Technology (VISTEC), Thailand
Abstract: Soft-bodied crawling animals exhibit adaptive, emergent behaviors resulting from the synergy between morphological computation (e.g., a flexible soft body and anisotropic skin) and neural computation (e.g., neural control with synaptic plasticity and memory). However, realizing this synergy in robots remains challenging.
In my talk, I will present our embodied neural control approach that integrates a flexible soft-body structure with asymmetrical abdominal denticles and an adaptive neural control system. The body structure, capable of micro- and macro-deformation, facilitates passive adaptation (achieved through morphological computation), while the adaptive neural control system generates locomotion patterns and enables online learning for active adaptation (achieved through neural computation). This two-level adaptation strategy allows a simple soft robot to passively adapt its body to small perturbations and actively adapt its control in response to larger perturbations. Our approach provides a possible option toward achieving embodied intelligence in soft robotics.

Talk 4

Title: TBA
Presenter: Etienne Burdet,Professor of Human Robotics, Department of Bioengineering – Faculty of Engineering
Abstract: TBA

Talk 5

Title: Embodied Intelligence in Octopus-Inspired Soft Robotics
Presenter: Cecilia Laschi, Provost’s Chair Professor, Department of Mechanical Engineering, College of Design and Engineering, National University of Singapore
Abstract: The octopus provides a compelling model for embodied intelligence, demonstrating how complex bodies can be used efficiently for manipulation, locomotion, and interaction. Motor behavior in octopuses, as in many biological systems, emerges from the interplay between body morphology and the environment. For example, octopus locomotion arises from limbs that shorten and elongate to generate movement without rigid joints, while arm movements exploit softness and extreme deformability to minimize drag and reduce control demands. Translating these principles to robotics highlights strategies that simplify control, reduce computation, and lower energy requirements. Pushing this concept further, purely mechanical designs without electronics can yield biodegradable robots that achieve adaptive behaviors through morphology alone. Such approaches open pathways to sustainable, efficient soft robotic systems that extend far beyond marine applications.

Talk 6

Title: Soft-Body Simulation for Modeling Motor Behavior and Morphogenesis
Presenter: Junior Rojas, Independent researcher
Abstract: This talk will present how soft-body simulation can serve as an effective tool for studying shape and movement. By modeling muscles, soft materials, neural network-based controllers and morphogenesis in virtual environments, we can study how adaptive motor behaviors develop across different body plans. Soft-body simulation offers a versatile framework not only for studying how a body is controlled via muscle actuation, but also for modeling how the body itself takes form as a dynamic mesh topology that, through elastic energy minimization, converges to stable configurations. The talk will include interactive simulations that illustrate these processes in action.

Organizers