MobilityBench is an open‑source benchmark built from over 100 000 real user queries that evaluates AI route‑planning agents with a deterministic sandbox, multi‑dimensional metrics, and support for ReAct and Plan‑and‑Execute frameworks, revealing performance gaps between open‑source and closed‑source models.
This article presents a complete front‑end solution for hand‑drawing cycling routes on AMap, applying road‑matching correction, exporting to GPX, adding waypoint‑based route planning, and enhancing map animations with custom setCenter and setFitView functions, all illustrated with full source code.
The 17‑minute video replay of Gaode's Technology Open Day showcases Cui Hengbin’s deep‑dive into AI‑driven route planning, covering pre‑trip, in‑trip, and arrival phases, road‑condition prediction, ETA estimation, dynamic traffic mining, and references to award‑winning research papers.
The article surveys Amap’s AI‑driven mobility solutions—from personalized, multi‑objective route planning using Cell‑Based Routing and bias‑aware sorting, through spatio‑temporal ETA prediction and lightweight BERT‑based traffic‑event mining, to rapid POI freshness updates and a future global scheduling system that coordinates vehicles and signals via multi‑agent reinforcement learning.
DiDi’s route engine, handling over 40 billion daily requests, replaces static graph algorithms with a deep‑reinforcement‑learning system that first learns intersection decisions via behavior‑cloning LSTM models and then refines them through self‑play Q‑learning, using beam‑search decoding to produce globally optimal, low‑deviation routes for ride‑hailing.
At PyCon China 2023, Dada‑JD Daojia’s algorithm team presented their AI‑driven practices for dynamic pricing, route planning, and order assignment, detailing how multi‑dimensional supply‑demand balancing, genetic‑algorithm‑based TSP solutions, and multi‑objective optimization improve real‑time logistics efficiency.
