Rahma, Hayah Jamila (2026) Pengembangan Sistem Navigasi Dalam Ruangan Berbasis LiDAR Dan Radar-Ultrawideband Dengan Algoritma D* Lite Untuk Penyandang Tunanetra. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5023221048-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5023221048-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (10MB) | Request a copy |
Abstract
Penyandang tunanetra menghadapi keterbatasan dalam melakukan navigasi di dalam ruangan akibat keterbatasan alat bantu konvensional, terutama dalam menentukan posisi, mendeteksi rintangan, dan melakukan perencanaan jalur saat terdapat rintangan dinamis. Penelitian ini mengembangkan sistem navigasi indoor berbasis radar Ultra-Wideband (UWB), sensor LiDAR Lite v3 HP, sensor Inertial Measurement Unit (IMU) BNO055, dan algoritma D* Lite untuk mendukung mobilitas penyandang tunanetra. Sistem memanfaatkan radar UWB DW1000 untuk positioning, IMU BNO055 untuk deteksi orientasi, LiDAR untuk deteksi rintangan statis dan dinamis, serta haptic feedback sebagai panduan navigasi. Algoritma D* Lite digunakan untuk menghasilkan jalur optimal dan memperbarui lintasan secara real-time berdasarkan perubahan lingkungan yang dideteksi oleh sensor LiDAR. Pengujian jarak pada Radar UWB menunjukkan hasil pengukuran dengan nilai Root Mean Square Error (RMSE) terkecil sebesar 0.0211 m dan koefisien determinasi sebesar 0,9987. Sensor LiDAR Lite v3 HP memiliki standar deviasi pengukuran sebesar 1.10 cm pada jarak 100 cm, dan field of view sebesar 0.46. Pada pengujian sistem, sensor LiDAR berhasil mendeteksi rintangan statis dan dinamis serta memperbarui occupancy grid secara real-time, sehingga algoritma D* Lite mampu melakukan 15 kali replanning pada metode eksperimen rintangan dinamis dengan rata-rata waktu replanning sebesar 0.228 ms, sementara sebagian besar subjek normal dan tunanetra berhasil mencapai target navigasi dengan tingkat keberhasilan hingga 100%. Hasil perbandingan algoritma menunjukkan bahwa keunggulan keduanya bersifat kontekstual. D* Lite menunjukkan keunggulan yang lebih konsisten pada metode eksperimen dengan frekuensi replanning tinggi, sejalan dengan rata-rata waktu replanning yang tercatat pada rentang 0.024-0.344 detik, sementara A* menunjukkan keunggulan pada beberapa metode eksperimen dengan kondisi lingkungan yang relatif statis. Hasil penelitian ini menunjukkan bahwa sistem yang dikembangkan dapat membantu meningkatkan kemandirian tunanetra dalam melakukan navigasi di dalam ruangan.
==================================================================================================================================
Visually impaired individuals face limitations in performing indoor navigation due to the constraints of conventional assistive tools, particularly in determining position, detecting obstacles, and planning paths in the presence of dynamic obstacles. This research develops an indoor navigation system based on Ultra-Wideband (UWB) radar, a LiDAR Lite v3 HP sensor, an Inertial Measurement Unit (IMU) BNO055 sensor, and the D* Lite algorithm to support the mobility of visually impaired individuals. The system utilizes DW1000 UWB radar for positioning, the BNO055 IMU for orientation detection, LiDAR for static and dynamic obstacle detection, and haptic feedback as a navigation guide. The D* Lite algorithm is used to generate an optimal path and update the trajectory in real time based on environmental changes detected by the LiDAR sensor. Distance testing on the UWB radar showed measurement results with the smallest Root Mean Square Error (RMSE) value of 0.0211 m and a coefficient of determination of 0.9987. The LiDAR Lite v3 HP sensor had a measurement standard deviation of 1.10 cm at a distance of 100 cm, with a field of view of 0.46°. In system testing, the LiDAR sensor successfully detected both static and dynamic obstacles and updated the occupancy grid in real time, enabling the D* Lite algorithm to perform 15 replanning instances in the dynamic obstacle experimental scenario, with an average replanning time of 0.228 ms, while most normal and visually impaired subjects successfully reached the navigation target with a success rate of up to 100%. The algorithm comparison results indicate that the advantages of both algorithms are context-dependent. D* Lite showed a more consistent advantage in experimental scenarios with high replanning frequency, consistent with the recorded average replanning time in the range of 0.024-0.344 seconds, while A* showed an advantage in several experimental scenarios with relatively static environmental conditions. The results of this research indicate that the developed system can help improve the independence of visually impaired individuals in performing indoor navigation.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Algoritma D-star Lite, Haptic feedback, Inertial Measurement Unit, LiDAR, Radar Ultra-Wideband, Tunanetra. ======================================================================================D-star Lite Algorithm, Haptic Feedback, LiDAR, Inertial Measurement Unit, Ultra-Wideband Radar, Visually Impaired. |
| Subjects: | T Technology > TA Engineering (General). Civil engineering (General) > TA1573 Detectors. Sensors |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Biomedical Engineering > 11410-(S1) Undergraduate Thesis |
| Depositing User: | Hayah Jamila Rahma |
| Date Deposited: | 03 Aug 2026 07:52 |
| Last Modified: | 03 Aug 2026 07:52 |
| URI: | http://repository.its.ac.id/id/eprint/142281 |
Actions (login required)
 |
View Item |