Liu Y et al. (2023), Design and Realization of a Novel Robotic Manta...

ECB-ART-51694

Biomimetics (Basel) 2023 Aug 04;84:. doi: 10.3390/biomimetics8040345.

Show Gene links Show Anatomy links

Design and Realization of a Novel Robotic Manta Ray for Sea Cucumber Recognition, Location, and Approach.

Liu Y , Liu Z , Yang H , Liu Z , Liu J .

???displayArticle.abstract???
Sea cucumber manual monitoring and fishing present various issues, including high expense and high risk. Meanwhile, compared to underwater bionic robots, employing autonomous underwater robots for sea cucumber monitoring and capture also has drawbacks, including low propulsion efficiency and significant noise. Therefore, this paper is concerned with the design of a robotic manta ray for sea cucumber recognition, localization, and approach. First, the developed robotic manta ray prototype and the system framework applied to real-time target search are elaborated. Second, by improved YOLOv5 object detection and binocular stereo-matching algorithms, precise recognition and localization of sea cucumbers are achieved. Thirdly, the motion controller is proposed for autonomous 3D monitoring tasks such as depth control, direction control, and target approach motion. Finally, the capabilities of the robot are validated through a series of measurements. Experimental results demonstrate that the improved YOLOv5 object detection algorithm achieves detection accuracies (mAP@0.5) of 88.4% and 94.5% on the URPC public dataset and self-collected dataset, respectively, effectively recognizing and localizing sea cucumbers. Control experiments were conducted, validating the effectiveness of the robotic manta ray's motion toward sea cucumbers. These results highlight the robot's capabilities in visual perception, target localization, and approach and lay the foundation to explore a novel solution for intelligent monitoring and harvesting in the aquaculture industry.

???displayArticle.pubmedLink??? 37622950
???displayArticle.pmcLink??? PMC10452072
???displayArticle.link??? Biomimetics (Basel)
???displayArticle.grants??? [+]

???attribute.lit??? ???displayArticles.show???

References [+] :

Hirschmüller, Stereo processing by semiglobal matching and mutual information. 2008, Pubmed

	Figure 1. The design drawings and prototype of the robotic manta ray. (a) the overall rendering of the robotic manta ray. (b) the prototype of the robotic manta ray.
	Figure 2. The interior layout of robotic manta ray.
	Figure 3. The bottom layout of the robotic manta ray. (a) The overall rendering of the robotic manta ray. (b) The prototype of the robotic manta ray.
	Figure 4. Undulation analysis of manta ray.
	Figure 5. The construction of the pectoral fin. (a) Overall structure of the pectoral fin. (b) Schematic diagram of undulation propulsion mode. (c) Schematic diagram of flapping propulsion mode.
	Figure 6. The diagram of the YOLOv5s-ST network structure.
	Figure 7. Swin Transformer Block.
	Figure 8. The flowchart of binocular positioning.
	Figure 9. The structure of the approach controller.
	Figure 10. Fuzzy output. (a) The three-dimensional surface plots of ΔKp. (b) The three-dimensional surface plots of ΔKi. (c) The three-dimensional surface plots of ΔKd.
	Figure 11. Comparison of detection results of URPC datasets.
	Figure 12. Comparison chart of training results of URPC dataset.
	Figure 13. Comparison of detection results of self-collected datasets.
	Figure 14. Comparison chart of training results of self-collected dataset.
	Figure 15. The experiment of binocular positioning.
	Figure 16. The experiment environment of motion control. (a) Experimental environment. (b) The scenario where the robot is swimming in the open pool.
	Figure 17. Depth change curve of the closed-loop depth control.
	Figure 18. Snapshots of the depth control for the robotic manta ray.
	Figure 19. Yaw angle change curve of direction control.
	Figure 20. The screenshots of the approach motion and underwater sea cucumber localization video sequences.
	Figure 21. The two-dimensional coordinate changes of the sea cucumber.
	Figure 22. The distance variation curve between robotic manta ray and sea cucumber.