Enhanced UAV Navigation in Cluttered Environments via a BS-CYOLOv5 Multi-Sensor Approach Article Swipe
Chahira Cherif
,
Mohammed MAIZA
,
Samira Chouraqui
,
Abdelmalik Taleb‐Ahmed
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.21203/rs.3.rs-7605109/v1
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.21203/rs.3.rs-7605109/v1
Unmanned Aerial Vehicles (UAVs) are critical for applications like aerial surveillance, disaster response, and urban air mobility. Operating safely in these dynamic environments requires robust autonomous navigation and obstacle avoidance capabilities. While traditional methods depend on predefined rules and sensor-based heuristics, they often lack the real-time adaptability needed for complex scenarios. To address this limitation, we propose BS-CYOLOv5, a novel framework that integrates a Deep Learning (DL)-based Backtracking Search-optimized Customized YOLOv5 architecture. This system unifies multi-sensor data processing, real-time obstacle detection, and dynamic path planning. The model was trained and evaluated on the UAV Autonomous Navigation Dataset from Kaggle, consisting of 10000 labeled UAV flight samples gathered from RGB cameras, LiDAR, IMU, and GPS sensors. The data was split into 80% for training, 10% for validation, and 10% for testing, with min-max normalization applied to improve model performance and generalization. For obstacle detection, the CYOLOv5 model provides high-accuracy, real-time identification. The Backtracking Search Algorithm (BSA) then optimizes navigation by dynamically recalibrating flight paths for efficiency and collision avoidance while simultaneously fine-tuning the detection model's hyperparameters. Experimental results demonstrate the framework's effectiveness, showing statistically significant improvements over state-of-the-art baselines. The model achieved 98.10% obstacle detection accuracy, alongside high precision (97.52%), recall (97.54%), F1-score (97.28%), and Intersection over Union (96.1%) metrics. Comprehensive ablation studies and cross-validation confirmed the robustness of our approach. This work contributes to the advancement of intelligent UAV systems by successfully merging state-of-the-art DL with evolutionary optimization, paving the way for greater autonomy and safety in real-world operations.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.21203/rs.3.rs-7605109/v1
- https://www.researchsquare.com/article/rs-7605109/latest.pdf
- OA Status
- gold
- References
- 24
- OpenAlex ID
- https://openalex.org/W4414862113
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4414862113Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.21203/rs.3.rs-7605109/v1Digital Object Identifier
- Title
-
Enhanced UAV Navigation in Cluttered Environments via a BS-CYOLOv5 Multi-Sensor ApproachWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-10-06Full publication date if available
- Authors
-
Chahira Cherif, Mohammed MAIZA, Samira Chouraqui, Abdelmalik Taleb‐AhmedList of authors in order
- Landing page
-
https://doi.org/10.21203/rs.3.rs-7605109/v1Publisher landing page
- PDF URL
-
https://www.researchsquare.com/article/rs-7605109/latest.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://www.researchsquare.com/article/rs-7605109/latest.pdfDirect OA link when available
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
24Number of works referenced by this work
Full payload
| id | https://openalex.org/W4414862113 |
|---|---|
| doi | https://doi.org/10.21203/rs.3.rs-7605109/v1 |
| ids.doi | https://doi.org/10.21203/rs.3.rs-7605109/v1 |
| ids.openalex | https://openalex.org/W4414862113 |
| fwci | 0.0 |
| type | preprint |
| title | Enhanced UAV Navigation in Cluttered Environments via a BS-CYOLOv5 Multi-Sensor Approach |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11133 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.9980000257492065 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2202 |
| topics[0].subfield.display_name | Aerospace Engineering |
| topics[0].display_name | UAV Applications and Optimization |
| topics[1].id | https://openalex.org/T10191 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9979000091552734 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2202 |
| topics[1].subfield.display_name | Aerospace Engineering |
| topics[1].display_name | Robotics and Sensor-Based Localization |
| topics[2].id | https://openalex.org/T10586 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9932000041007996 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Robotic Path Planning Algorithms |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | doi:10.21203/rs.3.rs-7605109/v1 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://www.researchsquare.com/article/rs-7605109/latest.pdf |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | posted-content |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.21203/rs.3.rs-7605109/v1 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5049217061 |
| authorships[0].author.orcid | https://orcid.org/0009-0007-2373-2772 |
| authorships[0].author.display_name | Chahira Cherif |
| authorships[0].affiliations[0].raw_affiliation_string | Ahmed Benbella Oran 1 University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Chahira CHERIF |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Ahmed Benbella Oran 1 University |
| authorships[1].author.id | https://openalex.org/A5117440016 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Mohammed MAIZA |
| authorships[1].affiliations[0].raw_affiliation_string | Ahmed Benbella Oran 1 University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Mohammed MAIZA |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Ahmed Benbella Oran 1 University |
| authorships[2].author.id | https://openalex.org/A5055259389 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-4870-5531 |
| authorships[2].author.display_name | Samira Chouraqui |
| authorships[2].countries | DZ |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I3124969661 |
| authorships[2].affiliations[0].raw_affiliation_string | Faculty of Mathematics and Computer Science, University of Sciences and Technology of Oran, ALGERIA |
| authorships[2].institutions[0].id | https://openalex.org/I3124969661 |
| authorships[2].institutions[0].ror | https://ror.org/02nbj1r55 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I3124969661 |
| authorships[2].institutions[0].country_code | DZ |
| authorships[2].institutions[0].display_name | Université des Sciences et de la Technologie d'Oran Mohamed Boudiaf |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Samira CHOURAQUI |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Faculty of Mathematics and Computer Science, University of Sciences and Technology of Oran, ALGERIA |
| authorships[3].author.id | https://openalex.org/A5088214859 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-7218-3799 |
| authorships[3].author.display_name | Abdelmalik Taleb‐Ahmed |
| authorships[3].countries | FR |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I2279609970, https://openalex.org/I70348806 |
| authorships[3].affiliations[0].raw_affiliation_string | Polytechnic University of Hauts-de-France, University of Lille |
| authorships[3].institutions[0].id | https://openalex.org/I70348806 |
| authorships[3].institutions[0].ror | https://ror.org/02ezch769 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I70348806 |
| authorships[3].institutions[0].country_code | FR |
| authorships[3].institutions[0].display_name | Université Polytechnique Hauts-de-France |
| authorships[3].institutions[1].id | https://openalex.org/I2279609970 |
| authorships[3].institutions[1].ror | https://ror.org/02kzqn938 |
| authorships[3].institutions[1].type | education |
| authorships[3].institutions[1].lineage | https://openalex.org/I2279609970 |
| authorships[3].institutions[1].country_code | FR |
| authorships[3].institutions[1].display_name | Université de Lille |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Abdelmalik TALEB-AHMED |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Polytechnic University of Hauts-de-France, University of Lille |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.researchsquare.com/article/rs-7605109/latest.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Enhanced UAV Navigation in Cluttered Environments via a BS-CYOLOv5 Multi-Sensor Approach |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T11133 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.9980000257492065 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2202 |
| primary_topic.subfield.display_name | Aerospace Engineering |
| primary_topic.display_name | UAV Applications and Optimization |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.21203/rs.3.rs-7605109/v1 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://www.researchsquare.com/article/rs-7605109/latest.pdf |
| best_oa_location.version | acceptedVersion |
| best_oa_location.raw_type | posted-content |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.21203/rs.3.rs-7605109/v1 |
| primary_location.id | doi:10.21203/rs.3.rs-7605109/v1 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://www.researchsquare.com/article/rs-7605109/latest.pdf |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | posted-content |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.21203/rs.3.rs-7605109/v1 |
| publication_date | 2025-10-06 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W4316506832, https://openalex.org/W4402514017, https://openalex.org/W4387662490, https://openalex.org/W4223962571, https://openalex.org/W3213229121, https://openalex.org/W4312706015, https://openalex.org/W4401070701, https://openalex.org/W3215745779, https://openalex.org/W3110903244, https://openalex.org/W3181605115, https://openalex.org/W3194398395, https://openalex.org/W4318483688, https://openalex.org/W3207833010, https://openalex.org/W3164652846, https://openalex.org/W4280576745, https://openalex.org/W4385774421, https://openalex.org/W4386269701, https://openalex.org/W2752782242, https://openalex.org/W2997747012, https://openalex.org/W2963351448, https://openalex.org/W1987092188, https://openalex.org/W4391214262, https://openalex.org/W4410097553, https://openalex.org/W4392990512 |
| referenced_works_count | 24 |
| abstract_inverted_index.a | 59, 64 |
| abstract_inverted_index.DL | 235 |
| abstract_inverted_index.To | 52 |
| abstract_inverted_index.by | 159, 231 |
| abstract_inverted_index.in | 20, 247 |
| abstract_inverted_index.of | 101, 218, 227 |
| abstract_inverted_index.on | 36, 92 |
| abstract_inverted_index.to | 135, 224 |
| abstract_inverted_index.we | 56 |
| abstract_inverted_index.10% | 124, 128 |
| abstract_inverted_index.80% | 121 |
| abstract_inverted_index.For | 141 |
| abstract_inverted_index.GPS | 114 |
| abstract_inverted_index.RGB | 109 |
| abstract_inverted_index.The | 86, 116, 151, 189 |
| abstract_inverted_index.UAV | 94, 104, 229 |
| abstract_inverted_index.air | 16 |
| abstract_inverted_index.and | 14, 28, 39, 82, 90, 113, 127, 139, 166, 204, 213, 245 |
| abstract_inverted_index.are | 5 |
| abstract_inverted_index.for | 7, 49, 122, 125, 129, 164, 242 |
| abstract_inverted_index.our | 219 |
| abstract_inverted_index.the | 45, 93, 144, 172, 179, 216, 225, 240 |
| abstract_inverted_index.was | 88, 118 |
| abstract_inverted_index.way | 241 |
| abstract_inverted_index.Deep | 65 |
| abstract_inverted_index.IMU, | 112 |
| abstract_inverted_index.This | 73, 221 |
| abstract_inverted_index.data | 77, 117 |
| abstract_inverted_index.from | 98, 108 |
| abstract_inverted_index.high | 197 |
| abstract_inverted_index.into | 120 |
| abstract_inverted_index.lack | 44 |
| abstract_inverted_index.like | 9 |
| abstract_inverted_index.over | 186, 206 |
| abstract_inverted_index.path | 84 |
| abstract_inverted_index.that | 62 |
| abstract_inverted_index.then | 156 |
| abstract_inverted_index.they | 42 |
| abstract_inverted_index.this | 54 |
| abstract_inverted_index.with | 131, 236 |
| abstract_inverted_index.work | 222 |
| abstract_inverted_index.(BSA) | 155 |
| abstract_inverted_index.10000 | 102 |
| abstract_inverted_index.Union | 207 |
| abstract_inverted_index.While | 32 |
| abstract_inverted_index.model | 87, 137, 146, 190 |
| abstract_inverted_index.novel | 60 |
| abstract_inverted_index.often | 43 |
| abstract_inverted_index.paths | 163 |
| abstract_inverted_index.rules | 38 |
| abstract_inverted_index.split | 119 |
| abstract_inverted_index.these | 21 |
| abstract_inverted_index.urban | 15 |
| abstract_inverted_index.while | 169 |
| abstract_inverted_index.(UAVs) | 4 |
| abstract_inverted_index.98.10% | 192 |
| abstract_inverted_index.Aerial | 2 |
| abstract_inverted_index.LiDAR, | 111 |
| abstract_inverted_index.Search | 153 |
| abstract_inverted_index.YOLOv5 | 71 |
| abstract_inverted_index.aerial | 10 |
| abstract_inverted_index.depend | 35 |
| abstract_inverted_index.flight | 105, 162 |
| abstract_inverted_index.needed | 48 |
| abstract_inverted_index.paving | 239 |
| abstract_inverted_index.recall | 200 |
| abstract_inverted_index.robust | 25 |
| abstract_inverted_index.safely | 19 |
| abstract_inverted_index.safety | 246 |
| abstract_inverted_index.system | 74 |
| abstract_inverted_index.(96.1%) | 208 |
| abstract_inverted_index.CYOLOv5 | 145 |
| abstract_inverted_index.Dataset | 97 |
| abstract_inverted_index.Kaggle, | 99 |
| abstract_inverted_index.address | 53 |
| abstract_inverted_index.applied | 134 |
| abstract_inverted_index.complex | 50 |
| abstract_inverted_index.dynamic | 22, 83 |
| abstract_inverted_index.greater | 243 |
| abstract_inverted_index.improve | 136 |
| abstract_inverted_index.labeled | 103 |
| abstract_inverted_index.merging | 233 |
| abstract_inverted_index.methods | 34 |
| abstract_inverted_index.min-max | 132 |
| abstract_inverted_index.model's | 174 |
| abstract_inverted_index.propose | 57 |
| abstract_inverted_index.results | 177 |
| abstract_inverted_index.samples | 106 |
| abstract_inverted_index.showing | 182 |
| abstract_inverted_index.studies | 212 |
| abstract_inverted_index.systems | 230 |
| abstract_inverted_index.trained | 89 |
| abstract_inverted_index.unifies | 75 |
| abstract_inverted_index.F1-score | 202 |
| abstract_inverted_index.Learning | 66 |
| abstract_inverted_index.Unmanned | 1 |
| abstract_inverted_index.Vehicles | 3 |
| abstract_inverted_index.ablation | 211 |
| abstract_inverted_index.achieved | 191 |
| abstract_inverted_index.autonomy | 244 |
| abstract_inverted_index.cameras, | 110 |
| abstract_inverted_index.critical | 6 |
| abstract_inverted_index.disaster | 12 |
| abstract_inverted_index.gathered | 107 |
| abstract_inverted_index.metrics. | 209 |
| abstract_inverted_index.obstacle | 29, 80, 142, 193 |
| abstract_inverted_index.provides | 147 |
| abstract_inverted_index.requires | 24 |
| abstract_inverted_index.sensors. | 115 |
| abstract_inverted_index.testing, | 130 |
| abstract_inverted_index.(97.28%), | 203 |
| abstract_inverted_index.(97.52%), | 199 |
| abstract_inverted_index.(97.54%), | 201 |
| abstract_inverted_index.Algorithm | 154 |
| abstract_inverted_index.Operating | 18 |
| abstract_inverted_index.accuracy, | 195 |
| abstract_inverted_index.alongside | 196 |
| abstract_inverted_index.approach. | 220 |
| abstract_inverted_index.avoidance | 30, 168 |
| abstract_inverted_index.collision | 167 |
| abstract_inverted_index.confirmed | 215 |
| abstract_inverted_index.detection | 173, 194 |
| abstract_inverted_index.evaluated | 91 |
| abstract_inverted_index.framework | 61 |
| abstract_inverted_index.mobility. | 17 |
| abstract_inverted_index.optimizes | 157 |
| abstract_inverted_index.planning. | 85 |
| abstract_inverted_index.precision | 198 |
| abstract_inverted_index.real-time | 46, 79, 149 |
| abstract_inverted_index.response, | 13 |
| abstract_inverted_index.training, | 123 |
| abstract_inverted_index.(DL)-based | 67 |
| abstract_inverted_index.Autonomous | 95 |
| abstract_inverted_index.Customized | 70 |
| abstract_inverted_index.Navigation | 96 |
| abstract_inverted_index.autonomous | 26 |
| abstract_inverted_index.baselines. | 188 |
| abstract_inverted_index.consisting | 100 |
| abstract_inverted_index.detection, | 81, 143 |
| abstract_inverted_index.efficiency | 165 |
| abstract_inverted_index.integrates | 63 |
| abstract_inverted_index.navigation | 27, 158 |
| abstract_inverted_index.predefined | 37 |
| abstract_inverted_index.real-world | 248 |
| abstract_inverted_index.robustness | 217 |
| abstract_inverted_index.scenarios. | 51 |
| abstract_inverted_index.BS-CYOLOv5, | 58 |
| abstract_inverted_index.advancement | 226 |
| abstract_inverted_index.contributes | 223 |
| abstract_inverted_index.demonstrate | 178 |
| abstract_inverted_index.dynamically | 160 |
| abstract_inverted_index.fine-tuning | 171 |
| abstract_inverted_index.framework's | 180 |
| abstract_inverted_index.heuristics, | 41 |
| abstract_inverted_index.intelligent | 228 |
| abstract_inverted_index.limitation, | 55 |
| abstract_inverted_index.operations. | 249 |
| abstract_inverted_index.performance | 138 |
| abstract_inverted_index.processing, | 78 |
| abstract_inverted_index.significant | 184 |
| abstract_inverted_index.traditional | 33 |
| abstract_inverted_index.validation, | 126 |
| abstract_inverted_index.Backtracking | 68, 152 |
| abstract_inverted_index.Experimental | 176 |
| abstract_inverted_index.Intersection | 205 |
| abstract_inverted_index.adaptability | 47 |
| abstract_inverted_index.applications | 8 |
| abstract_inverted_index.environments | 23 |
| abstract_inverted_index.evolutionary | 237 |
| abstract_inverted_index.improvements | 185 |
| abstract_inverted_index.multi-sensor | 76 |
| abstract_inverted_index.sensor-based | 40 |
| abstract_inverted_index.successfully | 232 |
| abstract_inverted_index.Comprehensive | 210 |
| abstract_inverted_index.architecture. | 72 |
| abstract_inverted_index.capabilities. | 31 |
| abstract_inverted_index.normalization | 133 |
| abstract_inverted_index.optimization, | 238 |
| abstract_inverted_index.recalibrating | 161 |
| abstract_inverted_index.statistically | 183 |
| abstract_inverted_index.surveillance, | 11 |
| abstract_inverted_index.effectiveness, | 181 |
| abstract_inverted_index.high-accuracy, | 148 |
| abstract_inverted_index.simultaneously | 170 |
| abstract_inverted_index.generalization. | 140 |
| abstract_inverted_index.identification. | 150 |
| abstract_inverted_index.Search-optimized | 69 |
| abstract_inverted_index.cross-validation | 214 |
| abstract_inverted_index.hyperparameters. | 175 |
| abstract_inverted_index.state-of-the-art | 187, 234 |
| abstract_inverted_index.<title>Abstract</title> | 0 |
| cited_by_percentile_year | |
| countries_distinct_count | 2 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile.value | 0.28781224 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |