Saved in:
Bibliographic Details
Main Authors: Xing, Yining, Ke, Zehong, Tu, Yiqian, Liu, Zhiyuan, Yu, Wenhao, Wang, Jianqiang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.21489
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917431102930944
author Xing, Yining
Ke, Zehong
Tu, Yiqian
Liu, Zhiyuan
Yu, Wenhao
Wang, Jianqiang
author_facet Xing, Yining
Ke, Zehong
Tu, Yiqian
Liu, Zhiyuan
Yu, Wenhao
Wang, Jianqiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_21489
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MISTY: High-Throughput Motion Planning via Mixer-based Single-step Drifting
Xing, Yining
Ke, Zehong
Tu, Yiqian
Liu, Zhiyuan
Yu, Wenhao
Wang, Jianqiang
Robotics
Artificial Intelligence
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.
title MISTY: High-Throughput Motion Planning via Mixer-based Single-step Drifting
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2604.21489