An improved Q-learning approach for rescue path planning in mass casualty incidents under damaged road network conditions
Sheng Wang, Jingrong Yang, Peng Yang · 2026
Read An improved Q-learning approach for rescue path planning in mass casualty incidents under damaged road network conditions by Sheng Wang, Jingrong Yang, Peng Yang (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-13316011.txt.
Description
Sheng Wang and colleagues propose, in a 2026 study, an improved Q-learning method for rescue path planning after mass casualty incidents under damaged roads. Earthquakes and similar disasters wreck road networks, rendering pre-disaster maps obsolete and making routes unknown and dynamic. Older static planners struggle in such settings, while standard learning agents fall into local optima and fail rescue safety requirements. The authors combine tuned trial cooling with experience replay in a Q-learning algorithm.
Cooling regulates exploration live, letting the agent escape local traps in damaged environments. Experience replay reuses key path experiences, improving speed. Experiments showed fast online re-planning in response to road updates. The method provides a confident decision aid for urgent post-disaster rescue, balancing access against safety. The authors present it as a lifeline tool for emergency units racing the golden hour, when arrival determines victim survival and operation success.
Catalog record
| CREATOR | Sheng Wang, Jingrong Yang, Peng Yang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 71 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |