Program
Néstor García, Technology Centre of Catalonia Eurecat, ES
Title: Rapid Skill Learning with Hand-Held Grippers in IntelliMan
Abstract: Eurecat presented recent advances to the Universal Manipulation Interface – a low-cost, hand-held gripper that streamlines robot teaching through smarter event detection and enhanced motion tracking, using sensor fusion and EKF. Integrated into the IntelliMan project, the system enables intuitive skill transfer in real-world agricultural and manufacturing settings. Demonstrations showed how robots can continuously learn to adapt, detect execution flaws, and acquire new knowledge for complex manipulation across diverse use cases.
Abstract: Eurecat presented recent advances to the Universal Manipulation Interface – a low-cost, hand-held gripper that streamlines robot teaching through smarter event detection and enhanced motion tracking, using sensor fusion and EKF. Integrated into the IntelliMan project, the system enables intuitive skill transfer in real-world agricultural and manufacturing settings. Demonstrations showed how robots can continuously learn to adapt, detect execution flaws, and acquire new knowledge for complex manipulation across diverse use cases.
Dimitrios Giakoumis, CERTH, GR
Title: Advancing the Physical Intelligence and Performance of
Robots Towards Human-Like Object Manipulation
Abstract: This presentation will introduce the main concept of the EC-funded (HE) MANiBOT project, which aims to empower bi-manual, mobile, service robots with advanced physical capabilities that allow them to perform a wide variety of manipulation tasks, with highly diverse objects, in a human-like manner and performance, in diverse, challenging environments. The talk will discuss MANiBOT's adaptive multi-level robot cycles approach that enables it to handle complex tasks, the MANiBOT robotic concept, and the enabling technologies on advanced environment understanding, efficient manipulation techniques, robot cognitive functions, and physical intelligence.
Abstract: This presentation will introduce the main concept of the EC-funded (HE) MANiBOT project, which aims to empower bi-manual, mobile, service robots with advanced physical capabilities that allow them to perform a wide variety of manipulation tasks, with highly diverse objects, in a human-like manner and performance, in diverse, challenging environments. The talk will discuss MANiBOT's adaptive multi-level robot cycles approach that enables it to handle complex tasks, the MANiBOT robotic concept, and the enabling technologies on advanced environment understanding, efficient manipulation techniques, robot cognitive functions, and physical intelligence.
João Silvério, German Aerospace Center, DE
Title: Leveraging uncertainty and interactive guidance for robot
skill acquisition
Abstract: When acquiring new manipulation skills, robots must navigate uncertainty while leveraging interactive guidance to adapt to dynamic, real-world environments. By employing uncertainty-aware motion primitives to model and refine skills and constrained reinforcement learning to explore within safe and practical limits, robots can unify human demonstrations, corrective feedback, and task constraints. In this talk, I will present recent results on uncertainty-aware, human-centered frameworks that facilitate adaptive and reliable robot learning in manipulation tasks.
Abstract: When acquiring new manipulation skills, robots must navigate uncertainty while leveraging interactive guidance to adapt to dynamic, real-world environments. By employing uncertainty-aware motion primitives to model and refine skills and constrained reinforcement learning to explore within safe and practical limits, robots can unify human demonstrations, corrective feedback, and task constraints. In this talk, I will present recent results on uncertainty-aware, human-centered frameworks that facilitate adaptive and reliable robot learning in manipulation tasks.
Rudolph Triebel, German Aerospace Center, DE
Title: From the Lab to the Kitchen: Data-efficient Learning and
Sim2Real in the EU-Project euRobin
Abstract: This presentation outlines the EU-Project euRobin's approach to advancing data-efficient learning and simulation-to-reality (Sim2Real) transfer for robotics. Focusing on robotic manipulation tasks, it explores how perception systems can classify, detect, and track objects, estimate their poses, and identify functional grasps. The project emphasizes overcoming key challenges like inverse problems, the open-world assumption, and adapting from controlled lab environments to complex real-world settings such as kitchens. Through simulated training, virtual environments, and real-world transfer, euRobin aims to develop cognition-enabled, transferable embodied AI for robust robotic applications.
Abstract: This presentation outlines the EU-Project euRobin's approach to advancing data-efficient learning and simulation-to-reality (Sim2Real) transfer for robotics. Focusing on robotic manipulation tasks, it explores how perception systems can classify, detect, and track objects, estimate their poses, and identify functional grasps. The project emphasizes overcoming key challenges like inverse problems, the open-world assumption, and adapting from controlled lab environments to complex real-world settings such as kitchens. Through simulated training, virtual environments, and real-world transfer, euRobin aims to develop cognition-enabled, transferable embodied AI for robust robotic applications.
Christian Henkel, Bosch Research, DE
Title: How we tell the robot what to do? Deliberation in
CONVINCE
Abstract: In this workshop talk, we explore the question: How do we tell a robot what to do? focusing on deliberation within the CONVINCE project. Deliberation, also known as task-planning or mission-planning, is essential for enabling robots to operate autonomously and adaptively in dynamic environments.
We will present the tools and approaches developed in CONVINCE, including formal methods, machine learning, and anomaly detection, and discuss how these support robust decision-making. Drawing from insights gained through the Deliberation Working Group and a ROSCon workshop, we will address key open questions: - What do users need to enable effective robot autonomy? - How does deliberation differ from traditional industrial robot programming? - How can we balance low-code solutions with flexible configuration? - How do we ensure explainability and interpretability, aligning with Industry 5.0 principles?
This talk aims to engage the audience in a discussion on the unique challenges of modern deliberation, fostering ideas for bridging the gap between robot programming and autonomous behavior.
Abstract: In this workshop talk, we explore the question: How do we tell a robot what to do? focusing on deliberation within the CONVINCE project. Deliberation, also known as task-planning or mission-planning, is essential for enabling robots to operate autonomously and adaptively in dynamic environments.
We will present the tools and approaches developed in CONVINCE, including formal methods, machine learning, and anomaly detection, and discuss how these support robust decision-making. Drawing from insights gained through the Deliberation Working Group and a ROSCon workshop, we will address key open questions: - What do users need to enable effective robot autonomy? - How does deliberation differ from traditional industrial robot programming? - How can we balance low-code solutions with flexible configuration? - How do we ensure explainability and interpretability, aligning with Industry 5.0 principles?
This talk aims to engage the audience in a discussion on the unique challenges of modern deliberation, fostering ideas for bridging the gap between robot programming and autonomous behavior.
