Regulación de la salida basada en detección de objetos y observadores de alta ganancia en robots de manipulación de líquidos
DOI:
https://doi.org/10.46842/ipn.cien.v30n1a14Palabras clave:
robot de manipulación de líquidos, aprendizaje profundo, identificación de objetos, regulación de salida, reconocimiento de material de laboratorio, observador de alta gananciaResumen
Los robots de manipulación de líquidos han adquirido un papel relevante en los laboratorios modernos gracias a su capacidad para automatizar el pipeteo y la dispensación de líquidos con alta precisión y repetibilidad. Asimismo, los avances en inteligencia artificial han contribuido a áreas de investigación como la biología y la ciencia de materiales, dando lugar a sistemas sofisticados para realizar ensayos complejos. Este artículo presenta una visión general del impacto de las técnicas de inteligencia artificial y los robots de manipulación de líquidos en aplicaciones relacionadas con la preparación de muestras, tales como el cultivo celular, la microscopía y la experimentación ‘in vivo’. En este contexto, se propone la identificación de objetos —específicamente material de laboratorio común— para facilitar las tareas de manipulación de líquidos. El sistema de detección se basa en el clasificador ResNet-50 y el detector YOLO v2. La información proporcionada por el detector se utiliza para la planificación de trayectorias de un sistema robótico. Con el fin de minimizar el error de seguimiento de posición, se propone un esquema de control basado en un observador de alta ganancia y regulación de salida, donde las trayectorias se consideran señales de referencia no modeladas.
Referencias
[1] J. A. Bennett, M. Abolhasani, "Autonomous chemical science and engineering enabled by self-driving laboratories," Chem. Eng. J., vol. 446, no. 2, Art. no. 137100, pp. 1–10, Oct. 2022. doi: https://doi.org/10.1016/j.coche.2022.100831
[2] F. Häse, L. M. Roch, A. Aspuru-Guzik, "Next-generation experimentation with self-driving laboratories," Trends Chem., vol. 1, no. 3, pp. 282–291, Jun. 2019. doi: https://doi.org/10.1016/j.trechm.2019.02.007
[3] M. J. Tamasi, A. J. Gormley, "Biologic formulation in a self-driving biomaterials lab," Cell Rep. Phys. Sci., vol. 3, no. 9, Art. no. 101019, pp. 1–17, Sep. 2022. doi: https://doi.org/10.1016/j.xcrp.2022.101041
[4] J. T. Rapp, B. J. Bremer, P. A. Romero, "Self-driving laboratories to autonomously navigate the protein fitness landscape," Nat. Chem. Eng., vol. 1, no. 1, pp. 97–107, Jan. 2024. doi: https://doi.org/10.1038/s44286-023-00002-4
[5] J. Beal, M. Rogers, "Levels of autonomy in synthetic biology engineering," Mol. Syst. Biol., vol. 16, no. 12, Art. no. e10014, pp. 1–5, Dec. 2020. doi: https://doi.org/10.15252/msb.202010019
[6] R. D. King, et al., "The robot scientist Adam," Computer, vol. 42, no. 8, pp. 46–54, Aug. 2009. doi: https://doi.org/10.1109/MC.2009.270
[7] R. Hickman, P. Bannigan, Z. Bao, A. Aspuru-Guzik, C. Allen, "Self-driving laboratories: A paradigm shift in nanomedicine development," Matter, vol. 6, no. 4, pp. 1071–1081, Apr. 2023. doi: https://doi.org/10.1016/j.matt.2023.02.007
[8] K. Williams et al., "Cheaper faster drug development validated by repositioning of drugs against neglected tropical diseases," J. R. Soc. Interface, vol. 12, no. 104, Art. no. 20141289, pp. 1–9, Mar. 2015. doi: https://doi.org/10.1098/rsif.2014.1289
[9] A. Sparkes et al., "Towards robot scientists for autonomous scientific discovery," Autom. Exp., vol. 2, no. 1, Art. no. 1, pp. 1–11, Jan. 2010. doi: https://doi.org/10.1186/1759-4499-2-1
[10] C. E. Anderson, et al., "Automated liquid handling robot for rapid lateral flow assay development," Anal. Bioanal. Chem., vol. 414, no. 8, pp. 2607-2618, Mar. 2022. doi: https://doi.org/10.1007/s00216-022-03897-9
[11] H. Tegally, J. E. San, J. Giandhari, T. de Oliveira, "Unlocking the efficiency of genomics laboratories with robotic liquid handling," BMC Genomics, vol. 21, no. 1, Art. no. 729, pp. 1–15, Oct. 2020. doi: https://doi.org/10.1186/s12864-020-07137-1
[12] G. Becattini, L. S. Mattos, D. Caldwell, "A fully automated system for adherent cells microinjection," IEEE J. Biomed. Health Inform., vol. 18, no. 1, pp. 83–93, Jan. 2014. doi: https://doi.org/10.1109/JBHI.2013.2248161
[13] G. Singh, K. D. Lagoo, A. V. S. S. Nayan Rao, D. N. Badodkar, "Liquid handling robot for DNA extraction," in Machines, Mechanism and Robotics, K. V. Gangadharan, R. M. Chandelf, S. M. Kulkaru, Eds. Singapore: Springer, 2019, pp. 829–838. doi: https://doi.org/10.1007/978-981-10-8597-0_71
[14] M. Zaleski Cox, P. N. Miklas, A. Soler Garzón, V. Hoyos Villegas, "Automating high throughput screening for anthracnose resistance in common bean using allele specific PCR," Plant Methods, vol. 19, no. 1, Art. no. 102, pp. 1–10, Sep. 2023. doi: https://doi.org/10.1186/s13007-023-01071-5
[15] S. Taguchi, Y. Suda, K. Irie, H. Ozaki, "Automation of yeast spot assays using an affordable liquid handling robot," SLAS Technol., vol. 28, no. 2, pp. 55–62, Apr. 2023. doi: https://doi.org/10.1016/j.slast.2022.12.001
[16] L. Tong-Tong, W. Jian-Wei, S. Qian-Nuan, W. Hui-Feng, P. Jian-Zhang, "An automated, fully-integrated nucleic acid analyzer based on microfluidic liquid handling robot technique," Anal. Chim. Acta, vol. 1239, Art. no. 340662, pp. 1–9, Jan. 2023. doi: https://doi.org/10.1016/j.aca.2022.340698
[17] W. Yu et al., "Pick-up single-cell proteomic analysis for quantifying up to 3000 proteins in a mammalian cell," Nat. Commun., vol. 15, no. 1, Art. no. 1279, pp. 1–14, Feb. 2024. doi: https://doi.org/10.1038/s41467-024-45659-4
[18] M. Alexovič, Y. Dotsikas, P. Bober, J. Sabo, "Achievements in robotic automation of solvent extraction and related approaches for bioanalysis of pharmaceuticals," J. Chromatogr. B, vol. 1092, pp. 402–421, Aug. 2018. doi: https://doi.org/10.1016/j.jchromb.2018.06.037
[19] R. P. Wierenga, S. M. Golas, W. Ho, C. W. Coley, K. M. Esvelt, "PyLabRobot: An open-source, hardware-agnostic interface for liquid-handling robots and accessories," Device, vol. 1, no. 4, Art. no. 100111, pp. 1–13, Oct. 2023. doi: https://doi.org/10.1016/j.device.2023.100111
[20] Y. Xiong, V. Shapaval, A. Kohler, J. Li, P. J. From, "A fully automated robot for the preparation of fungal samples for FTIR spectroscopy using deep learning," IEEE Access, vol. 7, pp. 132763–132774, Sep. 2019. doi: https://doi.org/10.1109/ACCESS.2019.2941704
[21] J. Zhang, W. Wan, N. Tanaka, M. Fujita, K. Takahashi, K. Harada, "Integrating a pipette into a robot manipulator with uncalibrated vision and TCP for liquid handling," IEEE Trans. Autom. Sci. Eng., vol. 21, no. 4, pp. 6051–6070, Oct. 2024. doi: https://doi.org/10.1109/TASE.2023.3312657
[22] P. Sardana et al., "DropletAI: Deep learning-based classification of fluids with different Ohnesorge numbers during non-contact dispensing," Fluids, vol. 8, no. 6, Art. no. 183, pp. 1–15, Jun. 2023. doi: https://doi.org/10.3390/fluids8060183
[23] E. Whitehead, F. Rudolf, H. M. Kaltenbach, J. Stelling, "Automated planning enables complex protocols on liquid-handling robots," ACS Synth. Biol., vol. 7, no. 3, pp. 922–932, Mar. 2018. doi: https://doi.org/10.1021/acssynbio.8b00021
[24] G. N. Kanda et al., "Robotic search for optimal cell culture in regenerative medicine," eLife, vol. 11, Art. no. e77007, pp. 1–25, Jun. 2022. doi: https://doi.org/10.7554/elife.77007
Descargas
Publicado
Número
Sección
Licencia
Derechos de autor 2026 Ricardo Tapia Herrera, Tonatiuh Hernández Cortes, Beatriz Adriana Jaime Fonseca, Jesús Alberto Meda Campaña (Autor/a)
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.
