Skip to main content

TinyML for Tiny Robots

By 15 march

Track: Robotics and AI / Data

Date and Time: 15 Mar 2024 11:40-13:00

Organisers: Daniele Palossi, Luca Benini

Main questions to be answered: What do we need to make an extremely limited palm-sized robot autonomous?

Additional questions: How to get high energy efficiency in ultra-low-power (ULP) hardware architectures?

Additional questions 2: How can we optimally exploit all the computational resources of mW-scale processors?

Workshop Description: Miniaturized autonomous robots leveraging machine and deep learning-based perception algorithms are gaining momentum both in academia and industry. However, making these cm-scale platforms intelligent and autonomous poses paramount challenges due to their extremely limited form factor and payload. The type of sensors, memories, and computational resources they can host aboard is constrained to the mW-scale power envelope. This workshop will explore this novel field, from the hardware viewpoint to the embedded systems and their tools, up to the final robotic applications. By building from a solid hardware perspective, the audience will be introduced to the challenges and novel solutions encompassing the entire design and development spectrum.

Intended Outcome: Workshop discussion topics of common interest, success stories, use cases, etc, Workshop on recent developments in technology or applications

Approach: 00:00 – 00:05 (5’) Workshop opening 00:05 – 00:20 (15’) Presentation 1 (ULP hardware design) 00:20 – 00:35 (15’) Presentation 2 (embedded systems and tools for ML/DL) 00:35 – 00:50 (15’) Presentation 3 (TinyML applications aboard miniaturized robots) 00:50 – 01:15 (25’) Open discussion with the panel and the audience, including Q&A 01:15 – 01:20 (5’) Workshop closing

Transferability in Robotics

By 15 march

Track: Autonomy /collaborative and cloud

Date and Time: 15 Mar 2024 11:40-13:00

Organisers: Rebecca Schedl-Warpup, Aude Billard, Danica Kragic Jensfelt

Main questions to be answered: What does transferability in different subdisciplines of robotics mean?

Additional questions: What are most pressing scientific question for increasing transferability?

Additional questions 2: What, When and How should be transferred?

Workshop Description: Transferability in Robotics is a key step to achieving sufficient scale and robustness in order to make robots ubiquitous in our everyday lives. The concept of transferability covers a wide range of topics such as i) Embodiment transfer – transferring from one robotic platform to another while considering their different embodiments, ii) Task/skill transfer – transferring methods or capabilities from one task to another, and iii) Knowledge transfer – transferring high-level concepts from one to another. These different areas also have different definitions of transferability and employ different approaches (e.g., representation learning, reinforcement learning, meta-learning, sim2real, interactive learning) for the respective task. While each of these fields has made headway in its own right, to really push forward the state of the art in transferability, a combination of contributions from the different fields is needed. The EU Horizon project euRobin aims to achieve transferability by not focusing on any specific sub-category but to share knowledge in a higher/more abstract way. The goal of this workshop is to combine the advances made in the individual fields into a more global picture by facilitating a common understanding of transferability, as well as highlighting contributions and encouraging collaborations between the different areas.

Intended Outcome: Information about community involvement and services offered (e.g. DIHs, open calls, platforms, …), Workshop discussion topics of common interest, success stories, use cases, etc, Workshop on recent developments in technology or applications, Workshop covering material new to ERF that the Robotics community should engage with, Workshop expected to create a roadmap or white paper

Approach: Presentation of several concepts and solutions of transferability within the euROBIN project o Alin Albu-Schäffer: introduction to transferability in euROBIN project (5 min). o Ales Ude: introduction to transferability in robotics, presentation of speakers (5 min). o Andrej Gams: task/skill transfer (12 min). o Bernardo Fichera: machine learning to robotics (12 min). o Rudolph Triebel: knowledge transfer (12 min). o Ilias El Makrini: embodiment transfer (12 min). Open discussion (15 min) involving Session Chair (Ales Ude), speakers, and panel (Markus Vincze, Anibal Ollero, and Uwe Kockermann). Conclusions from workshop (7 min).

Contributors: Alin Albu Schäffer (euROBIN Project Coordinator, Confirmed), DLR German Aerospace Center , Institute of Robotics and Mechatronics. Aleš Ude (Session Chair, Confirmed), Jožef Stefan Institute, Humanoid and Cognitive Robotics Lab (HCR). Andrej Gams (Speaker, Confirmed), Department of Automatics, Biocybernetics and Robotics, Jožef Stefan Institute, Ljubljana, Slovenia. Bernardo Fichera (Speaker, Confirmed), Learning Algorithms and Systems Laboratory, École polytechnique fédérale de Lausanne. Rudolph Triebel (Speaker, Confirmed), German Aerospace Center (DLR) and Karlsruhe Institute of Technology (KIT). Ilias El Makrini (Speaker, Confirmed), Vrije Universiteit Brussel, Faculty of Applied Sciences, Robotics & Multibody Research Group. Markus Vincze (Panel, Confirmed), TU Wien. Anibal Ollero (Panel, Confirmed), University of Seville. Uwe Köckermann (Panel, Confirmed), Örebro University

Further Information: https://arxiv.org/abs/2311.18044

Human-machine interaction, a critical success factor for microrobotics

By 15 march

Track: Control and virtualisation

Date and Time: 15 Mar 2024 11:40-13:00

Organisers: Maxime Etievant, Sinan HALIYO, Claudio PACCHIEROTTI

Main questions to be answered: How do user interface and user experience play a fundamental role in a user’s performance and confidence in micro-robotics ?

Additional questions: How can the user experience be tailored to the physical conditions of the microworld?

Additional questions 2: How can HMI be used to facilitate learning and skills development ?

Workshop Description: The growing need for miniaturization, whether for minimally invasive operations or for the creation of highly integrated miniature products, is driving the development of microrobotics. While the structure of robots has largely evolved to adapt to the particular physical conditions governing the microworld, the human-machine interaction remains a promising field. At the same time, the willingness to include the human element in the loop in order to address issues of adaptability, resilience and sustainability is encouraging a focus on HMI. The aim of the workshop is therefore to bring together scientific experts from across Europe, to facilitate discussions and to exchange expertise and best practices. Emulation, new ideas and possibility of partnerships can be expected.

Intended Outcome: Workshop on recent developments in technology or applications, Workshop discussion topics of common interest, success stories, use cases, etc

Approach: 80 min splitted into approximatly : • 45 min of pitches • 25 min of Q&A and discussion • 5 min of poll for the creation of the next WS at ERF2025

Contributors: – ISIR/Sobronne University, Paris, France – Sinan HALYIO / Gilles BAILLY – Scuola Superiore Sant’Anna, Pisa, Italy – Arianna Menciassi – IRISA-CNRS/Univ Renne, Renne, France – Claudio Pacchierotti

Plenary Lecture – Robo-driver: the enabler for the revolution of personal mobility

By 15 march
Talk title:
Robo-driver: the enabler for the revolution of personal mobility

 

Abstract
In the next 30 years a revolution is expected in the mobility model: the traditional personal mobility model (based on big, fossil-fuel-powered, personal-ownership cars) will be almost entirely replaced by Mobility-As-A-Service, autonomous, electric/H2 cars. This “revolution” aims to make a quantum leap in the overall efficiency of the mobility system, and to contribute to the improvement of the safety and sustainability of vehicles. This revolution will also deeply affect the structure of the entire automotive industry (layers, players, etc.).
Among the main technology megatrends, the autonomous-driving technology has a special/key role: not only is (by far) the most challenging from a technical point of view, but it will play the role of booster/catalyzer of all the other megatrends.
The plenary speech aims to provide a high-level view of this technology revolution, highlighting the role and the impact of the autonomous-driving technology.

SEE LECTURE

Pushing the limits of Space robotics

By 15 march

08:30 – 08:34  
Welcome to the audience
Miguel Olivares-Mendez and Carlos Perez del Pulgar

08:34 – 08:38   
Single-photon vision for navigating complex visual fields
David Rodriguez

08:38 – 08:42   
Haptics, latency and trustworthiness in human-robot interaction for space applications
Joe Loucas and Antonia Tzemanaki

08:42 – 08:46   
Pushing the limits of Space Robotics using legged robots
Hendrik Kolvenbach

08:46 – 08:50   
Latest advancements on orbital and planetary operations
Tom Becker and Thomas Voegele

08:50 – 08:54   
Closing remarks
Miguel Olivares-Mendez and Carlos Perez del Pulgar

08:54 – 09:50   
Interactive Poster Session    

Academic Track – Robotic technologies for novel aircraft systems

By 15 march

Track: Academic Track

Date and Time: 15 Mar 2024 08:30-09:50

Organisers: Konstantin Kondak, Marco Muraccini, Federico Capucci

Main questions to be answered: Challenges and opportunities provided by collaborative robotics on the automation and robotics value chain

Workshop Description: In recent years, collaborative robotics has emerged as a transformative force in various industries, promising increased productivity, safety, and flexibility in manufacturing processes. However, the integration of collaborative robots (cobots) into existing workflows presents unique challenges and opportunities that require careful consideration and innovative solutions. The workshop will feature presentations from experts in the field, case studies highlighting successful collaborative robotics deployments, and interactive sessions where attendees can share their experiences and learn from their peers. Through this collaborative exchange of knowledge and ideas, participants will gain insights into best practices, emerging trends, and opportunities provided by collaborative robotics.

Intended Outcome: Workshop discussion topics of common interest, success stories, use cases, etc

Approach: First Part: 5 x 10 minutes speeches involving industrial and academic partners presenting success stories and research activities Second Part: 30 minutes interactive session to share ideas, experiences, emerging trends

Robotics & AI: Transforming Sustainable Recycling & Remanufacturing

By 15 march

Track: Sustainability

Date and Time: 15 Mar 2024 08:30-09:50

Organisers: Sharath Chandra Akkaladevi, Franziska Kirstein, Karol Janik

Main questions to be answered: Unleashing the Potential: What are the existing applications of Robotics and AI in recycling and remanufacturing, and how can Robotics and AI technologies revolutionize and support sustainable recycling and production?

Additional questions: Tackling Challenges: What are the primary challenges that Robotics & AI can address recycling, and remanufacturing and what barriers hinder the adoption of Robotics & AI for sustainable recycling and remanufacturing?

Additional questions 2: Balancing Act: How can the above challenges and barriers be overcome to integrate Robotics & AI into recycling and remanufacturing processes, considering a holistic approach of technical, economic, environmental and social aspects?

Workshop Description: The workshop delves into the cutting-edge intersection of technology, sustainability, and industrial transformation. The industrial landscape is undergoing a profound revolution, where businesses are not only seeking increased productivity but also prioritizing sustainability and adaptability to dynamic supply chain shifts. This transformative shift demands a reevaluation of how materials and resources are utilized and can be recycled, reused, and remanufactured. Traditionally labor-intensive and fraught with challenges, Robotics and AI offer promising solutions to reshape recycling, and remanufacturing processes. This workshop will explore various application areas, including fashion, battery and composite material recycling, to gain a comprehensive understanding of the impact of Robotics and AI in diverse sectors. The presented talks span both technical and business viewpoints, showcasing the holistic approach required to address challenges and seize opportunities in sustainable production. This workshop offers up-to-date with the latest advancements in recycling and remanufacturing, uncovering how Robotics and AI are shaping the future of these industries. Join us at this workshop to be at the forefront of the Robotics and AI revolution in contributing to a more sustainable, efficient, and environmentally conscious industrial landscape. Expected * Trigger information exchange between academia and industry (end users) about the current challenges and possible solutions for sustainable recycling and remanufacturing with application of robotics * Update with the latest advancements in recycling and remanufacturing, particularly in how Robotics and AI are driving change in the context of sustainability and technology integration * A position paper on the results of the workshop and share it, e.g., with the respective topic group/s (TG sustainability). E.g. a white paper Overall, the expected outcome is to inform, inspire, and empower participants to engage with the evolving intersection of technology, sustainability, and industrial transformation, with a focus on Robotics and AI. The workshop aims to equip attendees with knowledge and perspectives that can drive positive change in their professional endeavors and contribute to a more sustainable future.

Intended Outcome: Workshop on recent developments in technology or applications

Approach: 80 Minute Slot 00:00 – 00:03 Opening comments by the organizers (Setting the Expectations) 00:03 – 00:45 5 impulse talks (Academia, End Users) 00:50 – 01:15 Panel discussion (4-6 speakers as panelists) + Discussion with Audience 01:15 – 01:20 Concluding remarks by the organizers (Feedback on Expectations)

Contributors: Five Speakers from Industry and Research: 1. Kat Thiel, Manchester Fashion Institute, UK 2. Gianmarco Griffini, Politecnico di Milano, Italy 3. Fotios Konstantinidis, ICCS, Greece 4. Agata Suwala, MTC, UK, 5. Michael Hofmann, PROFACTOR GmbH, Austria

Further Information: https://www.profactor.at/en/news-en/erf_2023_workshop_roboitcs_ai https://www.roboticsforsustainability.eu/post/erf-2024-workshop-on-robotics-ai-transforming-sustainable-recycling-remanufacturing https://aiprism.eu/invitation-to-the-erfs-2024-workshop-and-insight-session-on-robotics-ai/ https://www.soprano-project.org/single-post/erf-2024-workshop-on-robotics-ai-transforming-sustainable-recycling-remanufacturing

Safe adaptation for long term autonomy and human robot interaction

By 15 march

Track: Autonomy /collaborative and cloud

Date and Time: 15 Mar 2024 08:30-09:50, room Borgo

Organisers: LORENZO NATALE, Giorgio Cannata, Francesco Grella

Main questions to be answered – Q1: Is it possible to develop systems that optimize effectiveness in human robot interaction while adhering to safety constraints?

Main questions to be answered – Q2: What are the challenges on the adoption of formal methods for the verification of robot behaviors?

Main questions to be answered – Q3: What are the potential benefits of proxy-tactile sensing for manipulation tasks in complex unstructured environments?

Workshop Description: To achieve autonomy in unstructured environments while interacting with humans, robots need to be able to adapt to different operational conditions, face unexpected situations and guarantee safety. These challenges are tackled by the HE projects Sestosenso and CONVINCE, although from different perspectives. Sestosenso proposes a new sensing technology, cognitive perception and control algorithms based on proximity and tactile sensors for safe autonomy and interaction. CONVINCE, on the other hand, proposes a deliberation layer able to detect unexpected situations and deploy contingency actions to guarantee safe operation. The goal of this workshop is to disseminate the aims and challenges of the projects showcase the initial results of their activities, discuss common challenges and find potential synergies between the projects. For further information on the projects check out the project websites: http://sestosenso.eu/ https://convince-project.eu/ and workshop page: https://sites.google.com/view/erf2024roboticsafeadaptation/home

Intended Outcome: Workshop on recent developments in technology or applications

Approach: We chose an 80 minutes slot. Introduction 5 minutes Introduction to CONVINCE and description of Use cases (25 minutes) Speakers: Lorenzo Natale, Istituto Italiano di Tecnologia Michaela Klauck (Robert Bosch GmbH) Razane Azrou (Commissariat à l’Énergie Atomique et aux Énergies Alternatives) Introduction to SESTOSENSO and description of Use cases (25 minutes) Speakers: Giorgio Cannata, (Università degli Studi di Genova) Jelizaveta Konstantinova (OCADO Technology) Francesco Grella (Università degli Studi di Genova) Marco Camurri (Libera Università di Bolzano) Discussion and questions 20 minutes Concluding remarks 5 minutes We would like to link this introductory workshop to an insight session where the methodologies of the two projects and the progress will be discussed.

Contributors: Confirmed speakers: Lorenzo Natale, Istituto Italiano di Tecnologia Michaela Klauck (Robert Bosch GmbH) Razane Azrou (Commissariat à l’Énergie Atomique et aux Énergies Alternatives) Giorgio Cannata, (Università degli Studi di Genova) Jelizaveta Konstantinova (OCADO Technology) Francesco Grella (Università degli Studi di Genova) Marco Camurri (Libera Università di Bolzano)

Further Information: https://sites.google.com/view/erf2024roboticsafeadaptation/home

Robotics challenges in conservation ecology

By 15 march

Track: Specific operating environments

Date and Time: 15 Mar 2024 08:30-09:50

Organisers: Fabio Remondino, Ulrik Pagh Schultz Lundquist, Tom Richardson

Main questions to be answered: How can robots be deployed in daily ecology practices that encompass complex tasks and need real-time reliable solutions to scale up wildlife and habitat condition monitoring?

Additional questions: How can computer-vision-driven technologies, such as deep learning, be applied to robot-collected data to generate innovative discoveries and support ecological studies and habitat monitoring?

Additional questions 2: How can we innovate robot design, operations, and control to support the needs of ecology and nature conservation while minimising their environmental impact?

Workshop Description: Autonomous robots for ecology and biodiversity conservation applications are generally underused, being regarded as expensive hi-tech tools with limited autonomy and intelligence that can only relieve workers of physical fatigue or repetitive tasks in large-scale and highly-regular areas. Skill requirement of workers to operate such robots is also a barrier that impedes deployment, as are current regulations that make it difficult to deploy fully autonomous robotics solutions, for example drones operate Beyond Visual Line of Sight (BVLOS). Further, experience and requirements exchange between ecologists and industry is largely lacking (with a few important exceptions) and that likely hinders the effective development and use of automated solutions in conservation ecology. To boost the use of robotics in monitoring of nature and the environment, with an overall goal of biodiversity conservation, and to overcome actual open technological issues, we must show how robots (aerial, land, and underwater) can learn to navigate and operate in environments that are highly complex, dense and rapidly changing, and how they are able to support decisions for biologists and ecologists. In conservation ecology there are scenarios which have tasks that are difficult to automate, and where speed, consistency, versatility, robustness and safety perception are fundamental. In this workshop, we will explore these topics through reports and best practices related to wildlife and habitat conservation within three EU projects, two recently funded and one close to completion: ‘MAMBO’ – Modern Approaches to the Monitoring of Biodiversity; ‘WildDrone’ – Autonomous Drones for Nature Conservation Missions; and ‘Natural Intelligence‘ Robotic Monitoring of Habitats. Together, these projects provide perspectives from different levels of technological readiness: low (WildDrone), mid (Natural Intelligence), and high (MAMBO). Insights from experts in the field that are trying to solve different challenges and improve capabilities will give the possibility to open up collaborations and discuss possible solutions for the sector. Speakers from these project as well as from relevant European industrial partners and regulatory/institutional bodies will be involved. Expected Outcomes: 1. Trigger information exchanges between technology providers (academia & industry) and end-users about the challenges and emerging autonomous robotic solutions for nature conservation; 2. Networking and new collaborations among players in the field at national and international level; 3. A white paper stemming from the results of the workshop to highlight open issues, support new developments and stimulate further adoption of aerial robotics for conservation ecology.

Intended Outcome: Workshop expected to create a roadmap or white paper, Workshops engaging non-roboticists to understand needs/goals (policy, commercial, technical), Workshop discussion topics of common interest, success stories, use cases, etc

Approach: The workshop will be conducted with the following agenda – 00:00-00:05: Opening by organizers – 00:05-00:45: 5 invited talks (research, industry, regulatory) reporting their perspectives and experiences – 00:45-01:15: Roundtable session with panelists from academia, industry, and regulatory bodies to discuss solutions and open issues for nature conservation – 01:15-01:20: Concluding remarks by the organizers

Contributors: Invited speakers and panelists – Fabio Remondino, Fondazione Bruno Kessler (FBK), Trento, Italy (WildDrone project) – Jesper Erenskjold Moeslund, ECOS, University of Aarhus (MAMBO project) – Manolo Garabini, Research Center “E. Piaggio”, University of Pisa (Natural Intelligence project) – NN: Relevant European industrial partner – NN: Representative of relevant European regulatory/institutional body