Research Analyzer
← Back ICRA 2026

Mimir: Hierarchical Goal-Driven Diffusion with Uncertainty Propagation for End-To-End Autonomous Driving

Zebin Xing, Yupeng Zheng, Qichao Zhang, Zhixing Ding, Pengxuan Yang, Songen Gu, zhongpu xia, Dongbin Zhao

PDF

AI summary

Key figure (auto-extracted from paper)
Mimir significantly boosts autonomous driving robustness and real-time performance by modeling goal-point uncertainty and decoupling guidance from planning via a multi-rate architecture.
autonomous driving end-to-end planning uncertainty estimation diffusion models hierarchical control multi-rate guidance

Problem

Existing hierarchical end-to-end driving methods suffer from error propagation due to deterministic goal-point predictions and suffer from slow inference speeds caused by heavy high-level guidance modules.

Approach

Mimir employs a fast-slow dual-system framework that predicts goal points with Laplace-modeled uncertainty and extrapolates extended goals, which are then injected into a diffusion-based trajectory planner to guide robust motion generation.

Key results

  • Laplace-distribution uncertainty modeling for goal points
  • Multi-rate guidance mechanism with extended goal extrapolation
  • 20% improvement in driving score on Navhard and Navtest benchmarks
  • 1.6× faster high-level module inference without accuracy loss

Why it matters

Enables safer and more deployable real-time autonomous driving systems by mitigating error propagation and computational bottlenecks in hierarchical planning architectures.

Abstract

End-to-end autonomous driving has emerged as a pivotal direction in the field of autonomous systems. Recent works have demonstrated impressive performance by incorporating high- level guidance signals to steer low-level trajectory planners. How- ever, their potential is often constrained by inaccurate high-level guidance and the computational overhead of complex guidance modules. To address these limitations, we propose Mimir, a novel hierarchical dual-system framework capable of generating robust trajectories relying on goal points with uncertainty estimation: (1) Unlike previous approaches that deterministically model, we estimate goal point uncertainty with a Laplace distribution to enhance robustness; (2) To overcome the slow inference speed of the guidance system, we introduce a multi-rate guidance mecha- nism that predicts extended goal points in advance. Validated on challenging Navhard and Navtest benchmarks, Mimir surpasses previous state-of-the-art methods with a 20% improvement in the driving score EPDMS, while achieving 1.6× improvement in high- level module inference speed without compromising accuracy. The code and models will be released soon to promote reproducibility and further development.

Index terms

Learning from Demonstration Imitation Learning Autonomous Vehicle Navigation

Related papers