Program
09:00AM - 09:30AM
Check In (Tea and Coffee will be provided)
09:30AM - 10:00AM
Topic. Touch science and engineering in biorobotics and bionics
Speaker:: Calogero M. Oddo, Sant'Anna School of Advanced Studies, Italy
The talk discusses selected case studies of machine learning and bioinspired AI methods applied to biomedical mechanosensing technologies.
In the presented scientific approach, biorobotic systems are developed by capitalising on a fertile interaction between biomedical engineering and neuroscience, so that the advancements of neuroscientific research can lead to the development of more effective neuroAI technologies, which in turn so that the advancements of neurocientific research can lead to the development of more effective neuroAI technologies, which in turn contribute to the fundamental understanding of physiological processes.
A first family of case studies is with bionic hand prostheses to restore rich tactile skills, such as the encoding of force, shape, compliance and texture in upper limb amputees. The developed biorobotic technologies and artificial intelligence methods, based on information encoding with neuromorphic spikes emulating physiological tactile representation, is being applied in the upper limb amputees. The developed biorobotic technologies and artificial intelligence methods, based on information encoding with neuromorphic spikes emulating physiological tactile representation, is being applied in a variety of sensory augmentation scenarios.
The second family of transducers discussed is with Fiber Bragg Gratings (FBGs), jointly with meta- and deep- learning methods, to monitor respiratory activity and heart biomechanics in wearable and implantable sensors for telemedicine. The second family of transducers discussed is with Fiber Bragg Gratings (FBGs), jointly with meta- and deep- learning methods, to monitor respiratory activity and heart biomechanics in wearable and implantable sensors for telemedicine. further discussed in tactile sensing tasks aiming at the manipulation of fragile and deformable objects, by combining FEM and machine learning to augment the training datasets, and for sensorising the full area of anthropomorphic robotic arms for humanoids.
10:00AM - 10:30AM
Topic. Bioinspired Multimodal Robots: Elevating Interaction in Complex and Diverse Environments
Speaker:: Li Wen, Beihang University, China
Animals in their natural habitats exhibit extraordinary multimodal locomotion, exemplifying their remarkable capacity to effortlessly switch between different movement modes. This unique ability enables them to rapidly adapt to various environmental challenges, evade predators, and optimise strategies for capturing prey. This unique ability enables them to rapidly adapt to various environmental challenges, evade predators, and optimise strategies for capturing prey. multimodal motion, designed to navigate unstructured and dynamic environments while fulfilling complex tasks. During this talk, I will showcase three compelling examples of multimodal motion. compelling examples of multimodal robots that leverage soft materials and highly adaptable structures: 1) a multimodal robot engineered to cross air- water boundaries and hitchhiking, and 2) a robot that is capable of achieving multimodal motion while fulfilling complex tasks. water boundaries and hitchhiking on complex surfaces, 2) an octopus-inspired soft robotic arm equipped with stretchable electronics that provide bending and suction capabilities for interacting with the environment, and 3) a miniature morphable robot designed for deep-sea exploration, demonstrating multiple locomotion modes, and Furthermore, I will discuss several critical challenges that needs to be tackled to elevate the operational potentials of multimodal robots. potentials of multimodal robots, ultimately paving the way for enhanced operational capabilities in unstructured and dynamically changing environments in the future. I will discuss several critical challenges that needs to be tackled to elevate the operational potentials of multimodal robots, ultimately paving the way for enhanced operational capabilities in unstructured and dynamically changing environments in the future.
10:30AM - 11:00AM
Topic.From Automation to Autonomy: Machine Learning for Next-generation Robotics
Speaker: Sethu Vijayakumar, University of Edinburgh / The Alan Turing Institute, UK
The use of AI and Robotics in our society is becoming ubiquitous and inevitable across various walks of life. The new generation of robots work much more closely with humans, other robots and interact significantly with the environment around it. As a result, the key paradigms are shifting from isolated decision making systems to one that involves shared control -- with significant autonomy devolved to the robot platform; and end-users in the loop making only high level decisions.
This session will introduce powerful machine learning technologies ranging from robust multi-modal sensing, shared representations, scalable real-time learning and adaptation, and compliant actuation that are enabling us to reap the benefits of increased autonomy while still feeling securely in control – with focus on latest algorithmic and hardware developments.
This also raises some fundamental questions: while the robots are ready to share control, what is the optimal trade-off between autonomy and control that we are comfortable with?
Domains where this debate is relevant include deployment of robots in surgical interventions, extreme environments, self-driving cars, asset inspection, repair & maintenance, factories of the future and assisted living technologies including exoskeletons and prosthetics to list a few.
11:00AM - 11:30AM
Topic. Versatile and Dynamic Legged Robots: From Hardware Design to Control Algorithms
Speaker: Hae-Won Park, Korea Advanced Institute of Science and Technology (KAIST), South Korea
Biological legged animals have inspired the design of robots that replicate their ability to navigate complex and challenging environments. However, recent advances in hardware technology and algorithmic development have opened up possibilities for legged robots to achieve functionalities and performance beyond biological inspiration. However, recent advances in hardware technology and algorithmic development have opened up possibilities for legged robots to achieve functionalities and performance beyond biological inspiration. Realising such capabilities in robotic systems may require unique hardware designs, accurate models that capture hardware characteristics, and effective control algorithms that fully utilize these features. In this talk, I will present novel legged robot hardware designs that enable unique functions and improved performance, such as agile climbing of vertical walls. and learning-based approaches that effectively harness these novel hardware features to enable agile and robust operations in challenging environments.
11:30AM - 12:00AM
Topic. Embodied Intelligence for Aerial Robots
Speaker: Fei Gao, Zhejiang University, China
The convergence of robotics and artificial intelligence is revolutionising autonomous control for aerial robots and swarms in complex, dynamic environments. This talk presents state-of-the-art navigation algorithms, focusing on: (1) physics-informed modelling and optimization solvers for (1) physics-informed modelling and optimization solvers for high-dynamics, disturbance-rich, constrained scenarios; (2) Vision-Language-Action (VLA) frameworks for generalised decision-making; and (3) data-driven control for high-agricultural environments. data-driven control for high-agility flight. Real-world validations underscore the practical impact of these methods. breakthroughs in aerial swarm intelligence, showing marked gains in adaptability, robustness, and scalability. These contributions provide both theoretical grounding and actionable insight. We further examine recent breakthroughs in aerial swarm intelligence, showing marked gains in adaptability, robustness, and scalability. These contributions provide both theoretical grounding and actionable insights for the next generation of large-scale intelligent aerial systems.
