Mosaic: An Extensible Framework for Composing Rule-Based and Learned Motion Planners

2026-04-15

AI Summary

This work addresses the challenges in autonomous driving motion planning, where rule-based methods suffer from poor adaptability and learning-based approaches lack interpretability and safety guarantees. The authors propose Mosaic, a novel, scalable framework that seamlessly integrates heterogeneous planners without requiring retraining. By decoupling trajectory generation, validation, and scoring through an arbitration graph, Mosaic enables transparent and traceable decision-making that synergistically combines rule-based reasoning with end-to-end learning. Evaluated on the nuPlan Val14 closed-loop benchmark, the method achieves state-of-the-art performance with 95.48 CLS-NR and 93.98 CLS-R, reduces accident rates by 30%, and attains a CLS-R of 54.30 in highly interactive interPlan scenarios—outperforming the best single planner by 23.3%.

Technology Category

• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Intelligent Robots: Motion and Path Planning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Safe and explainable motion planning remains a central challenge in autonomous driving. While rule-based planners offer predictable and explainable behavior, they often fail to grasp the complexity and uncertainty of real-world traffic. Conversely, learned planners exhibit strong adaptability but suffer from reduced transparency and occasional safety violations. We introduce Mosaic, an extensible framework for structured decision-making that integrates both paradigms through arbitration graphs. By decoupling trajectory verification and scoring from the generation of trajectories by individual planners, every decision becomes transparent and traceable. Trajectory verification at a higher level introduces redundancy between the planners, limiting emergency braking to the rare case where all planners fail to produce a valid trajectory. Through unified scoring and optimal trajectory selection, rule-based and learned planners with complementary strengths and weaknesses can be combined to yield the best of both worlds. In experimental evaluation on nuPlan, Mosaic achieves 95.48 CLS-NR and 93.98 CLS-R on the Val14 closed-loop benchmark, setting a new state of the art, while reducing at-fault collisions by 30% compared to either planner in isolation. On the interPlan benchmark, focused on highly interactive and difficult scenarios, Mosaic scores 54.30 CLS-R, outperforming its best constituent planner by 23.3% - all without retraining or requiring additional data. The code is available at github.com/KIT-MRT/mosaic.

Problem

• motion planning
• autonomous driving
• safety
• explainability
• rule-based and learned planners

Innovation

• motion planning
• rule-based planner
• learned planner
• arbitration graph
• trajectory verification