An energy aware Q-learning framework for comprehensive coverage path planning in unknown complex environments
Yao Xue, Chee Keong Tan, Wai Peng Wong · 2025
Read An energy aware Q-learning framework for comprehensive coverage path planning in unknown complex environments by Yao Xue, Chee Keong Tan, Wai Peng Wong (2025) 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-12749843.txt.
Description
Yao Xue, Chee Keong Tan, and Wai Peng Wong published this 2025 study on teaching rescue robots to cover unknown, wrecked terrain without running dry. After disasters, coverage path planning decides where a robot sweeps for survivors, and classic algorithms balk at rubble and surprise. Their learner, PERM-QN, wraps Q-learning with three upgrades.
A dynamic reward keeps coverage, path length, and energy use in shifting balance as the mission evolves. Prioritized replay rehearses the most instructive past moves, speeding convergence. A memory network recognizes familiar terrain shapes and reuses routes, cutting redundant wandering. In simulated disaster zones of rising complexity the system covered more ground, more completely, than traditional planners. The authors pitch it for real search-and-rescue fleets.
Catalog record
| CREATOR | Yao Xue, Chee Keong Tan, Wai Peng Wong |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |