ETH Zurich

Canvas Category Consultancy : Research : Academic

Website | Blog | LinkedIn | Video

Primary Location Zรผrich, Switzerland

ETH Zurich โ€“ Where the future begins. Freedom and individual responsibility, entrepreneurial spirit and open-mindedness: ETH Zurich stands on a bedrock of true Swiss values. Our university for science and technology dates back to the year 1855, when the founders of modern-day Switzerland created it as a centre of innovation and knowledge. At ETH Zurich, students discover an ideal environment for independent thinking, researchers a climate which in-spires top performance. Situated in the heart of Europe, yet forging connections all over the world, ETH Zurich is pioneering effective solutions to the global challenges of today and tomorrow.

Assembly Line

AI robotic arm to tackle labour shortages: Swiss startup mimic grabs $2.5M funding

๐Ÿ“… Date:

๐Ÿ”– Topics: Funding Event

๐Ÿข Organizations: mimic, Founderful, ETH Zurich

In the race to develop the first commercially available humanoid robot primarily concentrated in the US, mimic has closed a pre-seed round of $2.5 million. The round was led by early-stage Swiss investor Founderful, which invested in Isospec Analytics, together with participation from German-based fund, UK-based, which invested in UltiHash, and a lineup of angel investors.

Spinning out from the research university ETH Zurich, mimic was founded by researchers Elvis Nava, Stefan Weirich, Stephan-Daniel Gravert, and Benedek Forrai in 2024. The founding team was working at the intersection of robotics and AI under Professor Robert Katzschmannโ€™s Soft Robotic Labs when they became increasingly convinced that the latest developments in large-scale generative AI models would upend a multitude of industries, beyond just language and image generation.

As per the company, its solution will enable a robot with humanoid hands to understand and imitate any behaviour, simply by watching a human perform it. This deviates from the conventional robotic solutions and focuses on specific use cases. Since each use case requires expensive ad-hoc engineering and comprehensive pre-programmed movements, robots are only able to complete the narrowly specific task they are designed for. Most use cases are stationary and do not require a full humanoid robot with legs, so they have developed a robotic arm.

Read more at TFN

ETH spin-offs develop high-performance batteries

๐Ÿ“… Date:

โœ๏ธ Author: Deborah Kyburz

๐Ÿ”– Topics: Multilayer Curtain Coating

๐Ÿข Organizations: BTRY, 8inks, ETH Zurich

Moritz Futscher and Abdessalem Aribia, the two founders of BTRY, have therefore developed a solid-state battery that consists of thin layers, which can shorten the charging time many times over. The two researchers entirely forego liquids both during the manufacturing process and for the components of their battery. The solid-state batteries that are currently being developed by BTRY have the major advantage of being very resistant to temperature fluctuations. They can therefore be used both at very high temperatures, such as in sensors that detect vapour leaks, and at very low temperatures, for example during the transportation of medicines.

ETH spin-off 8inks stands out from other battery manufacturers with its innovative production technology. It aims to use this to replace the manufacturing standard for lithium-ion batteries that has remained largely unchanged for the last 30 years โ€“ the so-called slot die technique. Paul Baade, founder of 8inks, has developed a technique called โ€œmultilayer curtain coatingโ€. By applying several thin coats of the active material in which the lithium-ion is stored, the coating technique can be tailored to the applicable requirements. Owing to the variety in terms of the thickness and material properties of the individual layers, the technique supports, among other things, the scaling of solid-state batteries. Another advantage of the technique is that the coating speed of the battery electrodes can be vastly accelerated and is therefore optimally suited to meet the rising demand.

Read more at ETH News

Automated machine tool dynamics identification for predicting milling stability charts in industrial applications

๐Ÿ“… Date:

โœ๏ธ Authors: Vahid Ostad Ali Akbari, Christian Schuppisser, Michal Kuffa, Konrad Wegener

๐Ÿ”– Topics: Machine Tool, Chatter

๐Ÿข Organizations: ETH Zurich

As the machine tool dynamics at the tooltip is a crucial input for chatter prediction, obtaining these dynamics for industrial applications is neither feasible through experimental impact testing for numerous tool-holder-spindle combinations nor feasible through physics-based modeling of the entire machine tool due to their sophisticated complexities and calibrations. Hence, the often-chosen path is a mathematical coupling of experimentally measured machine tool dynamics to model-predicted tool-holder dynamics. This paper introduces a novel measurement device for the experimental characterization of machine tool dynamics. The device can be simply mounted to the spindle flange to automatically capture the corresponding dynamics at the machine tool side, eliminating the need for expertise and time-consuming setup efforts thus presenting a viable solution for industries. The effectiveness of this method is evaluated against conventional spindle receptance measurement attempts using impact tests. The obtained results are further validated in the prediction of tooltip dynamics and stability boundaries.

Read more at Industrial Machinery Digest

ABB acquires Sevensense, expanding leadership in next-generation AI-enabled mobile robotics

๐Ÿ“… Date:

๐Ÿ”– Topics: Acquisition

๐Ÿข Organizations: ABB, Sevensense, ETH Zurich

ABB announced that it has acquired Swiss start-up Sevensense, a leading provider of AI-enabled 3D vision navigation technology for autonomous mobile robots (AMRs). Sevensense was founded in 2018 as a spin-off from Swiss technical University, ETH Zurich.

Sevensenseโ€™s pioneering navigation technology combines AI and 3D vision, enabling AMRs to make intelligent decisions, differentiating between fixed and mobile objects in dynamic environments. Once manually guided, mobile robots with Visual Simultaneous Localization and Mapping (Visual SLAM) technology create a map that is used to operate independently, reducing commissioning time from weeks to days and enabling the AMRs to navigate in highly complex, dynamic environments alongside people. Maps are constantly updated and shared across the fleet, offering instant scalability without interrupting operations and greater flexibility compared to other navigation technologies.

Read more at ABB News

Holcim launches Phoenix, the first-of-its-kind circular 3D-printed concrete bridge

๐Ÿ“… Date:

๐Ÿ”– Topics: 3D printing, Additive Manufacturing

๐Ÿข Organizations: Holcim, ETH Zurich, incremental3D

Holcim launches Phoenix, the first-of-its-kind 3D-printed concrete masonry bridge built with 10 tons of recycled materials, at its Innovation Hub in Europe. Using its proprietary ECOCycleยฎ circular technology, Holcim developed a custom concrete ink for Phoenix with recycled materials inside. Phoenix demonstrates how circular construction combined with 3D concrete printing can enable low-carbon infrastructure applications.

Circular construction, using computational design and 3D printing, allows for a reduction of up to 50% of the materials used with no compromise in performance. Circular by design, Phoenix stands solely through compression without reinforcement, with blocks that can be easily disassembled and recycled. Holcim and its partners are now exploring how Phoenix could be scaled up to provide more generalized sustainable infrastructure solutions.

Read more at Informed Infrastructure

This 3D printer can watch itself fabricate objects

๐Ÿ“… Date:

โœ๏ธ Author: Adam Zewe

๐Ÿ”– Topics: Additive Manufacturing, 3D Printing

๐Ÿข Organizations: MIT, Inkbit, ETH Zurich

Researchers from MIT, the MIT spinout Inkbit, and ETH Zurich have developed a new 3D inkjet printing system that works with a much wider range of materials. Their printer utilizes computer vision to automatically scan the 3D printing surface and adjust the amount of resin each nozzle deposits in real-time to ensure no areas have too much or too little material.

Since it does not require mechanical parts to smooth the resin, this contactless system works with materials that cure more slowly than the acrylates which are traditionally used in 3D printing. Some slower-curing material chemistries can offer improved performance over acrylates, such as greater elasticity, durability, or longevity.

In addition, the automatic system makes adjustments without stopping or slowing the printing process, making this production-grade printer about 660 times faster than a comparable 3D inkjet printing system.

Read more at MIT News

SonoPrint: Acoustically Assisted Volumetric 3D Printing for Composites

๐Ÿ“… Date:

โœ๏ธ Authors: Prajwal Agrawal, Shengyang Zhuang, Simon Dreher, Sarthak Mitter, Daniel Ahmed

๐Ÿ”– Topics: Additive Manufacturing, Materials Science, Fiber Reinforced Polymers

๐Ÿข Organizations: ETH Zurich

Advancements in additive manufacturing in composites have transformed various fields in aerospace, medical devices, tissue engineering, and electronics, enabling fine-tuning material properties by reinforcing internal particles and adjusting their type, orientation, and volume fraction. This capability opens new possibilities for tailoring materials to specific applications and optimizing the performance of 3D-printed objects. Existing reinforcement strategies are restricted to pattern types, alignment areas, and particle characteristics. Alternatively, acoustics provide versatility by controlling particles independent of their size, geometry, and charge and can create intricate pattern formations. Despite the potential of acoustics in most 3D printing, limitation arises from the scattering of the acoustic field between the polymerized hard layers and the unpolymerized resin, leading to undesirable patterning formation. However, this challenge can be addressed by adopting a novel approach that involves simultaneous reinforcement and printing the entire structure. Here, we present SonoPrint, an acoustically-assisted volumetric 3D printer that produces mechanically tunable composite geometries by patterning reinforcement microparticles within the fabricated structure. SonoPrint creates a standing wave field that produces a targeted particle motif in the photosensitive resin while simultaneously printing the object in just a few minutes. We have also demonstrated various patterning configurations such as lines, radial lines, circles, rhombuses, quadrilaterals, and hexagons using microscopic particles such as glass, metal, and polystyrene particles. Furthermore, we fabricated diverse composites using different resins, achieving 87 microns feature size. We have shown that the printed structure with patterned microparticles increased their tensile and compression strength by โˆผ38% and โˆผ75%, respectively.

Read more at BioRxiv

Using process mining to improve productivity in make-to-stock manufacturing

๐Ÿ“… Date:

โœ๏ธ Authors: Rafael Lorenz, Julian Senoner, Wilfried Sihn, Torbjorn Netland

๐Ÿ”– Topics: Make-to-stock

๐Ÿข Organizations: ETH Zurich, EthonAI

This paper proposes a data-driven procedure to improve productivity in make-to-stock manufacturing. By leveraging recent developments in information systems research, the paper addresses manufacturing systems with high process complexity and variety. Specifically, the proposed procedure draws upon process mining to dynamically map and analyse manufacturing processes in an automated manner. This way, manufacturers can leverage data to overcome the limitations of existing process mapping methods, which only provide static snapshots of process flows. By bridging data and process science, process mining can exploit hitherto untapped potential for productivity improvement. The proposed procedure is empirically validated at a leading manufacturer of sanitary products. The field test leads to three concrete improvement suggestions for the company. This research contributes to the literature on production research by demonstrating a novel use of process mining in manufacturing and by guiding practitioners in its implementation.

Read more at International Journal of Production Research