A new research paper explores adaptive operator selection methods for solving the electric autonomous dial-a-ride problem (EADARP) under uncertainty. The study focuses on a bilevel large neighborhood search framework, comparing six different selection strategies including fixed greedy, regret-based, random, deterministic rule-based, performance-adaptive ALNS, and LLM-based state-aware selection. Results indicate that while performance is similar on smaller problem instances, differences emerge with larger and more constrained EADARP scenarios, suggesting no single strategy is universally optimal. AI
IMPACT This research could lead to more efficient and reliable autonomous ride-sharing services by improving the optimization of vehicle routing under uncertain conditions.
RANK_REASON The cluster contains a research paper published on arXiv detailing a novel approach to a specific problem. [lever_c_demoted from research: ic=1 ai=0.7]
Read on arXiv cs.NE (Neural & Evolutionary) →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →