Proprioceptive wake classification by a body with a passive tail
Source abstract
Abstract
Abstract The remarkable ability of some marine animals to identify flow structures and parameters using complex non-visual sensors, such as lateral lines of fish and the whiskers of seals, has been an area of investigation for researchers looking to apply this ability to artificial robotic swimmers, which could lead to improvements in autonomous navigation and efficiency. Several species of fish in particular have been known to school effectively, even when blind. Beyond specialized sensors like the lateral lines, it is now known that some fish use purely proprioceptive sensing, using the kinematics of their fins or tails to sense their surroundings. In this paper we show that the kinematics of a body with a passive tail encode information about the ambient flow, which can be deciphered through machine learning. We demonstrate this with experimental data of the angular velocity of a hydrofoil with a passive tail that lies in the wake generated by an upstream oscillating body. Using convolutional neural networks, we show that with the kinematic data from the downstream body with a tail, the wakes can be better classified than in the case of a body without a tail. This superior sensing ability exists for a body with a tail, even if only the kinematics of the main body are used as input for the machine learning. This shows that beyond generating ‘additional inputs’, passive tails modulate the response of the main body in manner that is useful for hydrodynamic sensing. These findings have clear application for improving the sensing abilities of bioinspired swimming robots.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Biomimetic flight and propulsion mechanisms · Underwater Vehicles and Communication Systems · Fluid Dynamics and Vibration Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (53)
Show source-provided references
1. Hydrodynamics of fishlike swimming10.1146/annurev.fluid.32.1.33 ↗
2. Biomimetic survival hydrodynamics and flow sensing10.1146/annurev-fluid-122414-034329 ↗
3. Gait and speed selection in slender inertial swimmers10.1073/pnas.1419335112 ↗
4. An efficient swimming machine10.1038/scientificamerican0395-64 ↗
5. Biological inspiration: from carangiform fish to multi-joint robotic fish10.1016/S1672-6529(09)60184-0 ↗
6. Biorobotics: using robots to emulate and investigate agile locomotion10.1126/science.1254486 ↗
7. Innovation in underwater robots: biologically inspired swimming snake robots10.1109/MRA.2015.2506121 ↗
8. Upwash exploitation and downwash avoidance by flap phasing in ibis formation flight10.1038/nature12939 ↗
9. Passive propulsion in vortex wakes10.1017/S0022112005007925 ↗
10. Passive and active flow control by swimming fishes and mammals10.1146/annurev.fluid.38.050304.092201 ↗
11. The hydrodynamics of eel swimming: I. Wake structure10.1242/jeb.00968 ↗
12. Body-induced vortical flows: a common mechanism for self-corrective trimming control in boxfishes10.1242/jeb.01356 ↗
13. Not just going with the flow10.1511/2013.101.114 ↗
14. Flapping wing aerodynamics: progress and challenges10.2514/1.29263 ↗
15. Tracking wakes: the nocturnal predatory strategy of piscivorous catfish10.1073/pnas.121026298 ↗
16. The importance of the lateral line in nocturnal predation of piscivorous catfish10.1242/jeb.01129 ↗
17. A blind fish can school10.1126/science.982056 ↗
18. The kármán gait: novel body kinematics of rainbow trout swimming in a vortex street10.1242/jeb.00209 ↗
19. A review of fish swimming mechanics and behaviour in altered flows10.1098/rstb.2007.2082 ↗
20. The role of the lateral line and vision on body kinematics and hydrodynamic preference of rainbow trout in turbulent flow10.1242/jeb.02487 ↗
21. The flow fields involved in hydrodynamic imaging by blind Mexican cave fish (Astyanax fasciatus). Part I: open water and heading towards a wall10.1242/jeb.040741 ↗
22. Model-based observer and feedback control design for a rigid Joukowski foil in a Karman vortex street10.1088/1748-3190/aaa97f ↗
23. Hydrodynamic pressure sensing with an artificial lateral line in steady and unsteady flows10.1088/1748-3182/7/3/036004 ↗
24. Flow-relative control of an underwater robot10.1098/rspa.2012.0671 ↗
25. Bio-inspired flow sensing and control: autonomous rheotaxis using distributed pressure measurements
26. Unsteady dmd-based flow field estimation from embedded pressure sensors in an actuated airfoil10.2514/6.2019-0346 ↗
27. Nonlinear estimation-based dipole source localization for artificial lateral line systems10.1088/1748-3182/8/2/026005 ↗
28. An artificial lateral line system using ipmc sensor arrays10.1080/19475411.2011.650233 ↗
29. Parylene-coated bioinspired artificial hair cell for liquid flow sensing10.1016/j.mee.2012.07.072 ↗
30. Distant touch hydrodynamic imaging with an artificial lateral line10.1073/pnas.0609274103 ↗
31. Online state estimation of a fin-actuated underwater robot using artificial lateral line system10.1109/TRO.2019.2956343 ↗
32. Seal whiskers detect water movements10.1038/28303 ↗
33. Touch sensation by pectoral fins of the catfish10.1098/rspb.2015.2652 ↗
34. The function of fin rays as proprioceptive sensors in fish10.1038/ncomms2751 ↗
35. Mechanosensation is evolutionarily tuned to locomotor mechanics10.1073/pnas.1616839114 ↗
36. Fins as mechanosensors for movement and touch-related behaviors10.1093/icb/icy065 ↗
37. Fish can save energy via proprioceptive sensing10.1088/1748-3190/ac165e ↗
38. Classifying vortex wakes using neural networks10.1088/1748-3190/aaa787 ↗
39. Training bioinspired sensors to classify flows10.1088/1748-3190/aaef1d ↗
40. Detecting exotic wakes with hydrodynamic sensors10.1007/s00162-019-00493-z ↗
41. A machine learning approach to classify kinematics and vortex wake modes of oscillating foils10.2514/6.2021-2947 ↗
42. Recent advances in physical reservoir computing: a review10.1016/j.neunet.2019.03.005 ↗
43. Next generation reservoir computing10.1038/s41467-021-25801-2 ↗
44. Learning hydrodynamic signatures through proprioceptive sensing by bioinspired swimmers10.1088/1748-3190/abd044 ↗
45. Deep learning for time series classification: a review10.1007/s10618-019-00619-1 ↗
46. Use of the hough transformation to detect lines and curves in pictures10.1145/361237.361242 ↗
47. Flying and swimming animals cruise at a Strouhal number tuned for high power efficiency10.1038/nature02000 ↗
48. Neocognitron: A self-organizing neural network model for a mechanism of visual pattern recognition10.1007/BF00344251 ↗
49. Convolutional neural networks for time series classification10.21629/JSEE.2017.01.18 ↗
50. Early stopping-but when?10.1007/3-540-49430-8_3 ↗
51. Embodied hydrodynamic sensing and estimation using Koopman modes in an underwater environment10.23919/ACC53348.2022.9867211 ↗
52. Why should I trust you?’: Explaining the predictions of any classifier10.1145/2939672.2939778 ↗
53. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation10.1371/journal.pone.0130140 ↗