Inverse Kinematics Implementation Techniques in Robotics

Benjamin Zhang

doi:10.54097/vejx7557

Authors

Benjamin Zhang

DOI:

https://doi.org/10.54097/vejx7557

Keywords:

Robotics; Inverse Kinematics; Algorithms; Deep Learning.

Abstract

Inverse kinematics is crucial for offering precision in controlling robotic mechanisms, making them versatile for intricate roles in fields like manufacturing, medical services, and digital animation. It also facilitates innovations in automation, efficiency, and safety, thereby boosting overall performance in diverse industries. This review aims to present an overview of how deep learning techniques are employed in inverse kinematics, targeting researchers seeking to explore different approaches in this field. When calculating the inverse kinematics using the traditional approach, the complexity and non-linearity of a high degree of freedom robotic systems can pose limitations and lead to suboptimal results. Comparing different models of deep learning, this review focuses on the potential of deep learning as a suitable alternative approach for solving inverse kinematic problems. Also, it provides guidelines for researchers in utilizing deep learning for inverse kinematics applications while emphasizing the ethical and societal implications that arise from these advancements. Further emphasis is on the significance of case studies, insights into real-world applications, the challenges encountered, and future directions for research. Overall, this review covers various aspects of deep learning models' implementation in inverse kinematics. It also informs them about the potential of these models in advancing the field of inverse kinematics, paving the way for more precise and adaptive robotic movements, improved human-robot interactions, and greater autonomy in a wide range of industries.

Downloads

Download data is not yet available.

References

Cheng A.H.-D., and D. Ouazar. Analytical solutions. Seawater intrusion in coastal aquifers—concepts, methods, and practices. Dordrecht, Springer Netherlands, 1999, pp 163-191.

Gao Ruihua. Inverse kinematics solution of Robotics based on neural network algorithms. Journal of Ambient Intelligence and Humanized Computing, 2020, 11(12): 6199-6209.

Rokbani Nizar, and Adel M. Alimi. Inverse kinematics using particle swarm optimization, a statistical analysis. Procedia Engineering, 2013, 64(1): 1602-1611.

Hardesty L., Explained: Neural networks, MIT News, MIT Press, Cambridge, USA Apr. 14, 2017. https://news.mit.edu/2017/explained-neural-networks-deep-learning-0414.

O'Shea, Keiron, Ryan Nash. An introduction to convolutional neural networks. arXiv preprint, 1511.08458 (2015).

Sherstinsky, Alex. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D: Nonlinear Phenomena, 2020, 404: 132306. doi.org/10.1016/j.physd.2019.132306

Rojas Raul, Raúl Rojas. "The backpropagation algorithm." in Neural networks: a systematic introduction, Springer, Berlin, Heidelberg, 1996, pp. 149-182.

Choi Dami, Christopher J., et al. On empirical comparisons of optimizers for deep learning. arXiv preprint, 1910.05446 (2019).

Chandan S., Shah J., et al. “Chapter Two - Inverse Kinematics Analysis of 7-degree of Freedom Welding and Drilling Robot Using Artificial Intelligence Techniques,” ScienceDirect, Amsterdam, 2021, pp. 15-23

Wang Xiaoqi, Liu Xing, Chen Lerui, and Hu Heyu, Deep learning Damped Least Squares Method for Inverse Kinematics of Redundant Robots, 2021, 171: 108821.doi.org/10.1016/j.measurement.2020.108821.

Doersch, Carl. Tutorial on variational autoencoders. arXiv preprint 1606.05908 (2016).

Cahuantzi, Roberto, Xinye Chen, et al. A comparison of LSTM and GRU networks for learning symbolic sequences, in Science and Information Conference, Cham: Springer Nature, Switzerland, 2023, pp. 771-785.

Li, Yuxi. Deep reinforcement learning: An overview. arXiv preprint arXiv:1701.07274 (2017).

Taud Hind, and J. F. Mas. “Multilayer perceptron (MLP).” in Geomatic approaches for modeling land change scenarios, Springer, Cham. 2018, pp. 451-455.

Hester Todd, Vecerik Matej, Pietquin Oliveir, et al. Deep q-learning from demonstrations, in Proceedings of the AAAI conference on artificial intelligence, AAAI Press, Washington, DC, 2018, pp. 1-8, doi.org/10.1609/aaai. v32i1.11757

Noble William S., What is a support vector machine? Nature biotechnology, 2006, 24(12): 1565-1567.

Van Dyk David A., and Meng XiaoLi. The art of data augmentation. Journal of Computational and Graphical Statistics, 2001, 10(1): 1-50.

K. Rink, “Time Series Forecast Error Metrics you should know,” Medium, http://towardsdatascience.com/time-series-forecast-error-metrics-you-should-know-cc88b8c67f27

Pierzchlewicz Paweł A., et al. multi-hypothesis 3D human pose estimation metrics favor miscalibrated distributions. arXiv preprint:2210.11179 (2022).

Acemoglu, Daron, and Pascual Restrepo. Robots and jobs: Evidence from US labor markets. Journal of political economy, 2020, 128(6): 2188-2244.

M. Angel, “Medium,” Medium. http://medium.com/compendium/https-medium-com-mab-55055-what-is-fatml-and-why-should-you-care-dfb36e51f2f4.

A. A. Morgan, J. Abdi, M. A. Q. Syed, G. E. Kohen, P. Barlow, and M. P. Vizcaychipi, “Robots in Healthcare: a Scoping Review,” Current Robotics Reports, 2022, 3(4): 271-280 doi.doi.org/10.1007/s43154-022-00095-4.

Çiğdem Ş., Meidute-Kavaliauskiene I., and Yıldız B., Industry 4.0 and Industrial Robots: A Study from the Perspective of Manufacturing Company Employees, Logistics, 2023 7(1): 17.

T. Solberg, “Transforming animation with machine learning,” Embark Studios, https://medium.com/embarkstudios/transforming-animation-with-machine-learning-27ac694590c