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

• URL: http://arxiv.org/abs/2604.13853v1
• Date: Wed, 15 Apr 2026 13:23:47 GMT
• Title: Mosaic: An Extensible Framework for Composing Rule-Based and Learned Motion Planners
• Abstract summary: Rule-based planners offer predictable and explainable behavior; learned planners exhibit strong adaptability but suffer from reduced transparency and occasional safety violations.<n>We introduce Mosaic, a framework for structured decision-making that integrates both paradigms through arbitration graphs.<n>In experimental evaluation, 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.
• Score: 5.399177691034965
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• LePlanner: An Iterative Amortized Controller For World Models [0.0]
  We propose LePlanner, an amortized iterative controller that learns to construct and refine latent action sequences through a frozen world-model predictor.<n>LePlanner is trained with an arrival-and-hold objective that encourages the controller to reach the goal at the earliest feasible horizon and remain there.<n>It achieves success rates of 98% on PushT, 100% on Reacher, 100% on TwoRooms, and 92% on the OGBench Cube task.
  arXiv  Detail & Related papers  (2026-09-12T10:01:21Z)
• World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning [60.88859946006306]
  Adversa World Modeling is a theoretically grounded multi-agent self-play fine-tuning framework.<n>In inner minimization, the planner's predictive world model is converted into a role-conditioned adversary that learns sparse, scene-adaptive attack coalitions.<n> Experiments on the nuPlan and InterPlan benchmarks demonstrate that our method generates transferable adversarial interactions.
  arXiv  Detail & Related papers  (2026-07-12T07:44:16Z)
• Large Language Model Enhanced Differentiable Trajectory Planning for IoT-Enabled Autonomous Driving [26.33691640001489]
  This paper proposes a large language model (LLM) enhanced differentiable trajectory planning framework for IoT-enabled autonomous driving.<n>We introduce a surrounding agent centric data augmentation strategy to reorganize sur rounding agent trajectories as additional planning supervision.<n>We also design a complexity-aware asyn chronous LLM-based semantic enhancement module to extract scene-related high-level semantic features.
  arXiv  Detail & Related papers  (2026-07-11T18:43:14Z)
• Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning [60.888463449435484]
  We present Shift & Drift, a novel dual-track benchmark designed to rigorously stress-test motion planners across two critical axes of distribution shift.<n>We show that imitation learning methods achieve high scores in ID benchmarks, but suffer from persistent drift when subjected to temporally correlated actuation noise.<n>Our findings reveal an empirical trade-off between imitation fidelity and closed-loop resilience, providing the community with a rigorous benchmark to evaluate progress toward reliable deployment.
  arXiv  Detail & Related papers  (2026-07-08T18:23:48Z)
• ReactiveBFM: Reactive Closed-Loop Motion Planning Towards Universal Humanoid Whole-Body Control [54.267632784131415]
  ReactiveBFM is a real-time-loop planning-control framework for humanoids.<n>It mitigates fatal cumulative exposure bias via a scheduled prefix sampling curriculum.<n>It demonstrates unprecedented physical agility across a vast repertoire of text-conditioned closed-loop motions.
  arXiv  Detail & Related papers  (2026-06-29T14:27:27Z)
• Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling [19.766968596602457]
  Plan-RewardBench is a trajectory-level preference benchmark designed to evaluate how well judges distinguish preferred versus distractor agent trajectories.<n>Plan-RewardBench covers four representative task families -- (i) Safety Refusal, (ii) Tool-Irrelevance / Unavailability, (iii) Complex Planning, and (iv) Robust Error Recovery.
  arXiv  Detail & Related papers  (2026-04-09T12:35:06Z)
• Connectivity-Aware Representations for Constrained Motion Planning via Multi-Scale Contrastive Learning [6.0393663164774125]
  The objective of constrained motion planning is to connect start and goal configurations while satisfying task-specific constraints.<n>This paper addresses these challenges by learning a connectivity-aware representation for selecting start and goal configurations prior to planning.
  arXiv  Detail & Related papers  (2026-03-26T10:44:21Z)
• When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarks [39.146761527401424]
  Rule-based traffic agents hide planner deficiencies and bias rankings.<n>We integrate the state-of-the-art learned traffic agent model SMART into nuPlan.<n>Our analysis shows that IDM-based simulation overestimates planning performance.
  arXiv  Detail & Related papers  (2025-10-16T13:34:12Z)
• Align2Act: Instruction-Tuned Models for Human-Aligned Autonomous Driving [0.0]
  We propose Align2Act, a motion planning framework that transforms instruction-tuned language models into interpretable planners aligned with human behavior.<n>By fine-tuning LLaMA-2-7B with LoRA on one million scenarios from the nuPlan dataset, our method achieves an open-loop score of 85.17 and closed-loop scores of 70.31 and 66.96 on Test14-random.<n>Unlike prior work focused on synthetic or open-loop settings, we demonstrate improved planning quality and human-likeness on the real-world nuPlan closed-loop benchmark.
  arXiv  Detail & Related papers  (2025-10-12T08:50:34Z)
• Building a Foundational Guardrail for General Agentic Systems via Synthetic Data [76.18834864749606]
  LLM agents can plan multi-step tasks, intervening at the planning stage-before any action is executed-is often the safest way to prevent harm.<n>Existing guardrails mostly operate post-execution, which is difficult to scale and leaves little room for controllable supervision at the plan level.<n>We introduce AuraGen, a controllable engine that synthesizes benign trajectories, injects category-labeled risks with difficulty, and filters outputs via an automated reward model.
  arXiv  Detail & Related papers  (2025-10-10T18:42:32Z)
• Piano: A Multi-Constraint Pin Assignment-Aware Floorplanner [32.58046584473385]
  Piano is a floorplanning framework that simultaneously optimize module placement and pin assignment under multiple constraints.<n>Results show Piano achieves an average 6.81% reduction in HPWL, a 13.39% decrease in feedthrough wirelength, and a 16.36% reduction in the number of feedthrough modules.
  arXiv  Detail & Related papers  (2025-07-20T10:44:54Z)
• Foundation Models for Logistics: Toward Certifiable, Conversational Planning Interfaces [59.80143393787701]
  Large language models (LLMs) can handle uncertainty and promise to accelerate replanning while lowering the barrier to entry.<n>We introduce a neurosymbolic framework that pairs the accessibility of natural-language dialogue with verifiable guarantees on goal interpretation.<n>A lightweight model, fine-tuned on just 100 uncertainty-filtered examples, surpasses the zero-shot performance of GPT-4.1 while cutting inference latency by nearly 50%.
  arXiv  Detail & Related papers  (2025-07-15T14:24:01Z)
• Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling [74.41886258801209]
  We propose a two-stage trajectory planning framework that decouples principle alignment from behavior learning.<n>Plan-R1 significantly improves planning safety and feasibility, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-05-23T09:22:19Z)
• Distilling Multi-modal Large Language Models for Autonomous Driving [64.63127269187814]
  Recent end-to-end autonomous driving systems leverage large language models (LLMs) as planners to improve generalizability to rare events.<n>We propose DiMA, an end-to-end autonomous driving system that maintains the efficiency of an LLM-free (or vision-based) planner while leveraging the world knowledge of an LLM.<n>Training with DiMA results in a 37% reduction in the L2 trajectory error and an 80% reduction in the collision rate of the vision-based planner, as well as a 44% trajectory error reduction in longtail scenarios.
  arXiv  Detail & Related papers  (2025-01-16T18:59:53Z)
• DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving [55.53171248839489]
  We propose an ego-centric fully sparse paradigm, named DiFSD, for end-to-end self-driving.<n>Specifically, DiFSD mainly consists of sparse perception, hierarchical interaction and iterative motion planner.<n>Experiments conducted on nuScenes and Bench2Drive datasets demonstrate the superior planning performance and great efficiency of DiFSD.
  arXiv  Detail & Related papers  (2024-09-15T15:55:24Z)
• LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning [65.86754998249224]
  We develop a novel hybrid planner that leverages a conventional rule-based planner in conjunction with an LLM-based planner. Our approach navigates complex scenarios which existing planners struggle with, produces well-reasoned outputs while also remaining grounded through working alongside the rule-based approach.
  arXiv  Detail & Related papers  (2023-12-30T02:53:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.