MISTY: High-Throughput Motion Planning via Mixer-based Single-step Drifting

2026-04-23

AI Summary

This work addresses the high latency of existing diffusion-based trajectory planning methods in autonomous driving, which stems from iterative inference and impedes real-time deployment. To overcome this limitation, the authors propose a single-step, high-throughput generative motion planner that encodes the environment via vectorized Sub-Graphs, constructs a low-dimensional trajectory manifold using a variational autoencoder, and employs a lightweight MLP-Mixer decoder for efficient inference. A novel latent-space drift loss is introduced to shift complex distribution evolution into the training phase, while explicit attraction and repulsion mechanisms enable proactive behaviors such as overtaking. Evaluated on nuPlan Test14-hard, the method achieves state-of-the-art performance with non-reactive and reactive scores of 80.32 and 82.21, respectively, delivering a remarkable inference speed of 99 FPS and an end-to-end latency of only 10.1 milliseconds.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Computer Vision: Diffusion Models for Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Multi-modal trajectory generation is essential for safe autonomous driving, yet existing diffusion-based planners suffer from high inference latency due to iterative neural function evaluations. This paper presents MISTY (Mixer-based Inference for Single-step Trajectory-drifting Yield), a high-throughput generative motion planner that achieves state-of-the-art closed-loop performance with pure single-step inference. MISTY integrates a vectorized Sub-Graph encoder to capture environment context, a Variational Autoencoder to structure expert trajectories into a compact 32-dimensional latent manifold, and an ultra-lightweight MLP-Mixer decoder to eliminate quadratic attention complexity. Importantly, we introduce a latent-space drifting loss that shifts the complex distribution evolution entirely to the training phase. By formulating explicit attractive and repulsive forces, this mechanism empowers the model to synthesize novel, proactive maneuvers, such as active overtaking, that are virtually absent from the raw expert demonstrations. Extensive evaluations on the nuPlan benchmark demonstrate that MISTY achieves state-of-the-art results on the challenging Test14-hard split, with comprehensive scores of 80.32 and 82.21 in non-reactive and reactive settings, respectively. Operating at over 99 FPS with an end-to-end latency of 10.1 ms, MISTY offers an order-of-magnitude speedup over iterative diffusion planners while while achieving significantly robust generation.

Problem

• motion planning
• autonomous driving
• diffusion models
• inference latency
• trajectory generation

Innovation

• single-step inference
• MLP-Mixer
• latent-space drifting
• generative motion planning
• proactive trajectory generation