Small-scale location identification in natural environments with deep learning based on biomimetic sonar echoes
Source abstract
Abstract
Abstract Many bat species navigate in complex, heavily vegetated habitats. To achieve this, the animal relies on a sensory basis that is very different from what is typically done in engineered systems that are designed for outdoor navigation. Whereas the engineered systems rely on data-heavy senses such as lidar, bats make do with echoes triggered by short, ultrasonic pulses. Prior work has shown that ‘clutter echoes’ originating from vegetation can convey information on the environment they were recorded in—despite their unpredictable nature. The current work has investigated the spatial granularity that these clutter echoes can convey by applying deep-learning location identification to an echo data set that resulted from the dense spatial sampling of a forest environment. The Global Positioning System (GPS) location corresponding to the echo collection events was clustered to break the survey area into the number of spatial patches ranging from two to 100. A convolutional neural network (Resnet 152) was used to identify the patch associated with echo sets ranging from one to ten echoes. The results demonstrate a spatial resolution that is comparable to the accuracy of recreation-grade GPS operating under foliage cover. This demonstrates that fine-grained location identification can be accomplished at very low data rates.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Bat Biology and Ecology Studies · Marine animal studies overview · Animal Vocal Communication and Behavior
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (57)
Show source-provided references
1. Use of unmanned vehicles in search and rescue operations in forest fires: advantages and limitations observed in a field trial10.1016/j.ijdrr.2015.07.009 ↗
2. Requirements and limitations of thermal drones for effective search and rescue in marine and coastal areas10.3390/drones3040078 ↗
3. Unsupervised human detection with an embedded vision system on a fully autonomous uav for search and rescue operations10.3390/s19163542 ↗
4. Intelligent coverage path planning for agricultural robots and autonomous machines on three-dimensional terrain10.1007/s10846-013-9834-6 ↗
5. Harvesting robots for high-value crops: State-of-the-art review and challenges ahead10.1002/rob.21525 ↗
6. A surveillance robot with hopping capabilities for home security10.1109/TCE.2009.5373766 ↗
7. Hofmann-Wellenhof · 2012
8. The underwater GPS problem
9. Autonomous underwater vehicle navigation
10. Path planning and navigation inside off-world lava tubes and caves
11. Autonomous system for navigation and surveying in underground mines10.1002/rob.20213 ↗
12. GPS jamming and the impact on maritime navigation10.1017/S0373463308005213 ↗
13. Smartphone GPS accuracy study in an urban environment10.1371/journal.pone.0219890 ↗
14. Technical limitations of GNSS receivers in indoor positioning
15. Sensor integration of 3d map aided gnss and smartphone pdr in urban canyon with dense foliage
16. Probabilistic visual recognition of artificial landmarks for simultaneous localization and mapping
17. Artificial landmark-based underwater localization for auvs using weighted template matching10.1007/s11370-014-0153-y ↗
18. Plant species identification using digital morphometrics: a review10.1016/j.eswa.2012.01.073 ↗
19. The structural and radiative consistency of three-dimensional tree reconstructions from terrestrial lidar10.1016/j.rse.2009.01.017 ↗
20. Automated three-dimensional linear elements extraction from mobile lidar point clouds in railway environments10.3390/infrastructures4030046 ↗
21. An experimental analysis of various multi-channel lidar systems
22. Flash memory in the emerging age of autonomy
23. Foraging behaviour and echolocation in the rufous horseshoe bat (rhinolophus rouxi) of sri lanka10.1007/BF00292166 ↗
24. Neuroethology of bat navigation10.1016/j.cub.2018.04.056 ↗
25. Home-range size and spacing patterns of Macrophyllum macrophyllum (Phyllostomidae) foraging over water10.1644/1545-1542(2005)86[587:HSASPO]2.0.CO;2 ↗
26. Nectar intake and energy expenditure in a flower visiting bat10.1007/BF00379875 ↗
27. Foliage echoes: a probe into the ecological acoustics of bat echolocation10.1121/1.429617 ↗
28. What a plant sounds like: the statistics of vegetation echoes as received by echolocating bats10.1371/journal.pcbi.1000429 ↗
29. Plant acoustic density profile model of ctfm ultrasonic sensing10.1109/7361.983464 ↗
30. Biomimetic detection of dynamic signatures in foliage echoes10.1088/1748-3190/abf910 ↗
31. Large-scale recognition of natural landmarks with deep learning based on biomimetic sonar echoes10.1088/1748-3190/ac4c94 ↗
32. Adafruit ultimate GPS dataSheet
33. Dougherty · 1992
34. Foraging behavior and echolocation of wild horseshoe bats Rhinolophus ferrumequinum and R. hipposideros (Chiroptera, Rhinolophidae)10.1007/BF00302917 ↗
35. Nested mini-batch k-means10.48550/arXiv.1602.02934 ↗
36. Scikit-learn: machine learning in python
37. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis10.1016/0377-0427(87)90125-7 ↗
38. Deep residual learning for image recognition
39. TensorFlow: large-scale machine learning on heterogeneous systems
40. keras
41. Batch normalization: accelerating deep network training by reducing internal covariate shift
42. Deep sparse rectifier neural networks
43. Rethinking the inception architecture for computer vision
44. Goodfellow · 2016
45. Scaling of wingbeat and echolocation pulse emission rates in bats: why are aerial insectivorous bats so small?10.2307/2390068 ↗
46. Echolocation by insect-eating bats: we define four distinct functional groups of bats and find differences in signal structure that correlate with the typical echolocation tasks faced by each group10.1641/0006-3568(2001)051[0557:EBIEB]2.0.CO;2 ↗
47. Sexual dimorphism in echolocation pulse parameters of the cf-fm bat, Hipposideros pratti10.1186/s40555-015-0123-x ↗
48. Multi layer perceptron
49. Cross-validatory choice and assessment of statistical predictions10.1111/j.2517-6161.1974.tb00994.x ↗
50. Murphy · 2012
51. Sanity checks for saliency maps
52. A computational theory for the classification of natural biosonar targets based on a spike code10.1088/0954-898X_14_3_311 ↗
53. Dynamic accuracy of recreation-grade GPS receivers in oak-hickory forests10.1093/forestry/cpu019 ↗
54. The applicability of recreation-grade GNSS receiver (GPS watch, Suunto Ambit Peak 3) in a forested and an open area compared to a mapping-grade receiver (Trimble Juno T41)10.1371/journal.pone.0231532 ↗
55. Detection of passageways in natural foliage using biomimetic sonar10.1088/1748-3190/ac7aff ↗
56. Relative brain size and feeding strategies in the chiroptera10.2307/2407489 ↗
57. Pritsker · 1984