GenMRP: A Generative Multi-Route Planning Framework for Efficient and Personalized Real-Time Industrial Navigation

2026-02-04

AI Summary

This work addresses the challenge of simultaneously achieving real-time performance, personalization, and path diversity in large-scale road networks—a limitation commonly observed in existing industrial navigation systems. To this end, we propose GenMRP, a novel framework that employs a “skeleton-to-capillary” dynamic subnetwork construction strategy, integrated with an iterative generative mechanism and a refinement-augmentation module. By effectively fusing user history, road attributes, and previously generated paths, GenMRP enables efficient, personalized, and diverse multi-path planning. The approach synergistically combines a Link Cost Model, Dijkstra’s algorithm, and generative optimization, demonstrating state-of-the-art performance in both offline and online settings. Notably, GenMRP has been deployed in a real-world navigation system, and its training and evaluation datasets are publicly released.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Sampling/Simulation-based Search
• Multiagent Systems: Multiagent Planning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Existing industrial-scale navigation applications contend with massive road networks, typically employing two main categories of approaches for route planning. The first relies on precomputed road costs for optimal routing and heuristic algorithms for generating alternatives, while the second, generative methods, has recently gained significant attention. However, the former struggles with personalization and route diversity, while the latter fails to meet the efficiency requirements of large-scale real-time scenarios. To address these limitations, we propose GenMRP, a generative framework for multi-route planning. To ensure generation efficiency, GenMRP first introduces a skeleton-to-capillary approach that dynamically constructs a relevant sub-network significantly smaller than the full road network. Within this sub-network, routes are generated iteratively. The first iteration identifies the optimal route, while the subsequent ones generate alternatives that balance quality and diversity using the newly proposed correctional boosting approach. Each iteration incorporates road features, user historical sequences, and previously generated routes into a Link Cost Model to update road costs, followed by route generation using the Dijkstra algorithm. Extensive experiments show that GenMRP achieves state-of-the-art performance with high efficiency in both offline and online environments. To facilitate further research, we have publicly released the training and evaluation dataset. GenMRP has been fully deployed in a real-world navigation app, demonstrating its effectiveness and benefits.

Problem

• multi-route planning
• real-time navigation
• personalized routing
• industrial-scale navigation
• route diversity

Innovation

• generative route planning
• multi-route generation
• skeleton-to-capillary
• correctional boosting
• real-time navigation