Search

Lab Automation facilitates high-throughput processes and improves reproducibility and efficiency while removing human action, primary source of contaminating particles. Handling poses a risk of contamination due to close contact with the objects. We propose a novel gripper (CrocoGrip) relying on compliant mechanisms to reduce the amount of contaminating particles generated by the gripper rather than preventing their emission, the latter being the common approach in current grippers. Our novel gripper is actuated by linear solenoids and purely relies on deformation for its motion. As a result, abrasive behavior and, therefore, the generation of particles is reduced without the need for additional sealing. We experimentally proved that only particles smaller than 3.0µm are emitted by the gripper, with a large proportion of the particles being generated by the actuation. The CrocoGrip fulfills the demands of ISO14644 class 5. The gripping relies on the deformation energy of the compliant mechanism, making the gripping energy-efficient and safe. The maximum gripping force achieved by the CrocoGrip was 5.5N. Because the force transmitted to the handling object depends on the design of the gripping jaws, which are interchangeable, the force can be reduced for more sensible handling objects. Using three different sets of jaws, CrocoGrip was able to handle a microplate in SBS-standard, a 50mL Falcon tube, and a Ø60mm Petri dish using a robotic arm. Due to the monolithic design of the CrocoGrip and, as a result, the need for few components, we achieve a simplicity of design, making cleaning, sterilization and maintenance easy, even for nonexperts. The CrocoGrip exploits the advantages of compliant mechanisms, especially for applications requiring clean-room environments. This approach of compliant-mechanism-based grippers enables an increase in the cleanliness of handling processes without an increase in system complexity of the gripper to facilitate the lab automation of highly sensible processes, such as in tissue engineering.

Neural network-based nonlinear system identification is crucial for various multi-step ahead prediction tasks, including model predictive control and digital twins. These applications demand models that are not only accurate but also efficient in training and deployment. While current state-of-the-art neural network-based methods can identify accurate models, they often become prohibitively slow when scaled to achieve high accuracy, limiting their use in resource-constrained or time-critical applications. We propose FranSys, a Fast recurrent neural network-based method for multi-step ahead prediction in non-autoregressive System Identification. FranSys comprises three key innovations: 1) the first non-autoregressive RNN model structure for multi-step ahead prediction that enables much faster training and inference compared to autoregressive RNNs by separating state estimation and prediction into two specialized sub-models, 2) a state distribution alignment training technique that enhances generalizability and 3) a prediction horizon scheduling method that accelerates training by progressively increasing the prediction horizon. We evaluate FranSys on three publicly available benchmark datasets representing diverse systems, comparing its speed and accuracy against state-of-the-art RNN-based multi-step ahead prediction methods. The evaluation includes various prediction horizons, model sizes, and hyperparameter optimization settings, using both our own implementations and those from related work. Results demonstrate that FranSys is 10 to 100 times faster in training and inference with the same and often higher accuracy on test data than state-of-the-art RNN-based multi-step ahead prediction methods, particularly with long prediction horizons. This substantial speed improvement enables the application of larger neural network-based models with longer prediction horizons on resource-constrained systems in time-critical tasks, such as model predictive control and online learning of digital twins. The code of FranSys is publicly available.