AI-Enhanced Thermal–Visual–Inertial Odometry and Autonomous Planning for GPS-Denied Search-and- Rescue Robotics
Islam T. Almalkawi, Sabya Shtaiwi, Alaa Alhowaide, Manel Guerrero Zapata · 2026
Read AI-Enhanced Thermal–Visual–Inertial Odometry and Autonomous Planning for GPS-Denied Search-and- Rescue Robotics by Islam T. Almalkawi, Sabya Shtaiwi, Alaa Alhowaide, Manel Guerrero Zapata (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13119551.txt.
Description
Almalkawi and co-authors present in 2026 a ground robot for search and rescue where GPS fails, as in collapsed or underground sites. Single sensor systems degrade under smoke, dust, and clutter. Their stack fuses thermal, visual, inertial, and acoustic cues in a low cost, efficient design.
Thermal visual odometry with zero velocity updates holds position against drift. A multimodal graph module detects survivors, reaching an F1 score of 0.69 and an area under curve of 0.98 in their tests. A reinforcement planner steers under uncertainty. Trials reported full mission completion, with a trade off between completion, speed, and collisions against a baseline planner.
Catalog record
| CREATOR | Islam T. Almalkawi, Sabya Shtaiwi, Alaa Alhowaide, Manel Guerrero Zapata |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 61 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |