As robot technology enters a new era, multi-task robot manipulation has entered high-quality development. Sticking to the people-oriented philosophy, people propose synergistic effects to better meet the complex environment and diverse needs. Based on the dynamic evolution of evolutionary deep learning, the researchers construct a theoretical analysis framework for the synergistic effect of multi-task robot manipulation according to the logic of adaptation, optimization, enhancement, and evaluation. It can explain the synergistic effect of collaborative learning and optimization mechanisms involving deep learning and evolutionary algorithms. Moreover, from the perspective of the actual changes and practices of multi-task robot manipulations, we explore the possibility of moving toward high-quality development. Multi-task robot manipulation aims to provide users with results that meet the expected standards and continuously improve operation quality and user satisfaction. Therefore, we should take measures such as strengthening the collaboration based on course learning, constructing the mechanism of the interaction mechanism and optimization between the evolutionary strategy and simulator, and establishing the collaborative effect evaluation system of the PILCO framework, realize the high-quality collaborative effect of multi-task robot manipulation, promote the development of robot technology and meet the needs of users.

Heyang Xiao. A Review of the Application of Evolutionary Deep Learning in Solving the Multi-task Robot Manipulation Synergy Effect. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 9: 38-42. https://doi.org/10.25236/AJCIS.2023.060906.

[1] Nguyen H, La H. Review of deep reinforcement learning for robot manipulation[C]//2019 Third IEEE International Conference on Robotic Computing (IRC). IEEE, 2019: 590-595.

[2] Adegboye A, Ojeka S A, Tolase O, et al. Technology penetration and human development nexus in middle-income countries: the synergy effect of inclusive resources distribution [J]. Information Technology for Development, 2022, 28(4): 860-874.

[3] Lee R, Lee J H, Garrett T C. Synergy effects of innovation on firm performance[J]. Journal of Business Research, 2019, 99: 507-515.

[4] Ge G, Cheng X, Liao M, et al. A review of the synergy effect in multi-break VCBs [J]. IEEE Transactions on Plasma Science, 2018, 47(1): 671-679.

[5] Camero A, Toutouh J, Stolfi D H, et al. Evolutionary deep learning for car park occupancy prediction in smart cities[C]//Learning and Intelligent Optimization: 12th International Conference, LION 12, Kalamata, Greece, June 10–15, 2018, Revised Selected Papers 12. Springer International Publishing, 2019: 386-401.

[6] Ghoniem R M, Algarni A D, Refky B, et al. Multi-modal evolutionary deep learning model for ovarian cancer diagnosis [J]. Symmetry, 2021, 13(4): 643. 

[7] Fujino S, Hatanaka T, Mori N, et al. Evolutionary deep learning based on deep convolutional neural network for anime storyboard recognition[J]. Neurocomputing, 2019, 338: 393-398.

[8] Shridhar M, Manuelli L, Fox D. Perceiver-actor: A multi-task transformer for robotic manipulation [C] // Conference on Robot Learning. PMLR, 2023: 785-799.