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

• URL: http://arxiv.org/abs/2604.21489v1
• Date: Thu, 23 Apr 2026 09:50:34 GMT
• Title: MISTY: High-Throughput Motion Planning via Mixer-based Single-step Drifting
• Abstract summary: MISTY is a generative motion planner that achieves state-of-the-art closed-loopational with pure single-step inference.<n>We introduce a latent-space drifting loss that shifts the complex evolution to the training phase.<n> MISTY operates at over 99 FPS with an end-to-end latency of 10.1 ms.
• Score: 19.16655963423315
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Accelerating Human-Aware Robot Trajectory Generation via Diffusion and Consistency Distillation [3.8411993084160283]
  This research proposes a constrained motion planning framework for robot manipulators in human-robot interaction (HRI)<n>Additional requirements such as collision avoidance and self-collision avoidance are difficult to handle as simple null-space secondary tasks.<n>To address this limitation, collision- and self-collision-aware trajectories are generated using Rapidly-exploring Random Tree (RRT) and RRT* algorithms.
  arXiv  Detail & Related papers  (2026-08-04T05:47:25Z)
• PedestrianDiffusion: Multimodal Generative Denoising and Dense State Estimation for Inertial Navigation [1.8620637029128544]
  PedestrianDiffusion is a generative framework that reformulates dense 6D state estimation as a continuous conditional denoising process.<n>It achieves state-of-the-art performance, exhibiting unprecedented robustness to impulse perturbations and coupled 6D kinematic drift.<n>This work provides a rigorous algorithmic blueprint for next-generation Neural Inertial Measurement Units (N-IMUs)
  arXiv  Detail & Related papers  (2026-07-03T14:04:30Z)
• SATB-VR: Training Few-Step Video Restoration Diffusion Model using SNR-Aware Trajectory Blending [55.764018145256216]
  We present SATB-VR, a few-step paradigm that jump-starts the denoising process via an auxiliary predictor.<n>We show that SATB-VR performs favorably against existing approaches on synthetic, real-world, and AIGC benchmarks.
  arXiv  Detail & Related papers  (2026-06-27T01:32:16Z)
• Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models [65.89572755202245]
  Diffusion Language Models (DLMs) offer stronger global awareness and highly parallel generation.<n>Post-training DLMs with standard Negative Evidence Lower Bound (NELBO)-based supervised fine-tuning remains inefficient.<n>We propose a self-distilled trajectory-based post-training framework that aligns training with the easy-to-hard structure of inference.
  arXiv  Detail & Related papers  (2026-05-12T09:39:06Z)
• Bridging Restoration and Generation Manifolds in One-Step Diffusion for Real-World Super-Resolution [22.963799508399365]
  Recent single-step distillation accelerates inference but faces a stark perception-distortion trade-off.<n>We present Adaptive Inversion and Degradation-aware Sampling for Real-ISR (IDaS-SR)<n>IDaS-SR is a one-step framework bridging the deterministic restoration and generation bottlenecks.
  arXiv  Detail & Related papers  (2026-04-27T07:43:00Z)
• Allo{SR}$^2$: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows [32.29950358173077]
  Real-world image super-resolution (Real-SR) has been revolutionized by leveraging the powerful generative priors of large-scale diffusion and flow-based models.<n>AlloSR$2$ is a novel framework that rectifies one-step SR trajectories via allomorphic generative flows to maintain high-fidelity generative realism.
  arXiv  Detail & Related papers  (2026-04-21T08:44:40Z)
• LiquidTAD: Efficient Temporal Action Detection via Parallel Liquid-Inspired Temporal Relaxation [2.3837169660687123]
  LiquidTAD is a framework that distills the exponential relaxation prior to liquid neural dynamics into a parallel temporal operator.<n>LiquidTAD achieves accuracy competitive with strong baselines while substantially lowering the model footprint.
  arXiv  Detail & Related papers  (2026-04-20T13:48:17Z)
• Ada3Drift: Adaptive Training-Time Drifting for One-Step 3D Visuomotor Robotic Manipulation [53.750389076941396]
  Diffusion-based visuomotor policies capture multimodal action distributions through iterative denoising, but their high inference latency limits real-time robotic control.<n>We propose Ada3Drift, which learns a training-time drifting field that attracts predicted actions toward expert demonstration modes.<n>Ada3Drift achieves state-of-the-art performance while requiring $10times$ fewer function evaluations than diffusion-based alternatives.
  arXiv  Detail & Related papers  (2026-03-12T14:36:53Z)
• From Flow to One Step: Real-Time Multi-Modal Trajectory Policies via Implicit Maximum Likelihood Estimation-based Distribution Distillation [18.70033095161235]
  We propose a framework that distills a Conditional Flow Matching expert into a fast single-step student via Implicit Likelihood Estimation (IMLE)<n>A bi-directional Chamfer distance provides a set-level objective that promotes both mode coverage and fidelity.<n>A unified perception encoder further integrates multi-view RGB, depth, point clouds, and proprioception into a geometry-aware representation.
  arXiv  Detail & Related papers  (2026-03-10T09:30:05Z)
• DRIFT: Diffusion-based Rule-Inferred For Trajectories [15.78457153766977]
  Trajectory generation for mobile robots in unstructured environments faces a critical dilemma: balancing smoothness for safe execution with terminal precision for fine-grained tasks.<n>This article proposes DRIFT, a conditional framework designed to generate high-fidelity reference trajectories by integrating two complementary inductive biases.<n>Results demonstrate that DRIFT reconciles these conflicting objectives, achieving centimeter-level imitation fidelity (0.041m FDE) and competitive smoothness (27.19 Jerk)
  arXiv  Detail & Related papers  (2026-03-01T05:54:38Z)
• OMP: One-step Meanflow Policy with Directional Alignment [26.114675928221974]
  One-step MeanFlow Policy (OMP) designed for high-fidelity, real-time manipulation.<n>Experiments on Adroit and Meta-World benchmarks demonstrate that OMP outperforms state-of-the-art methods in success rate and trajectory accuracy.
  arXiv  Detail & Related papers  (2025-12-22T12:45:35Z)
• Drift No More? Context Equilibria in Multi-Turn LLM Interactions [58.69551510148673]
  contexts drift is the gradual divergence of a model's outputs from goal-consistent behavior across turns.<n>Unlike single-turn errors, drift unfolds temporally and is poorly captured by static evaluation metrics.<n>We show that multi-turn drift can be understood as a controllable equilibrium phenomenon rather than as inevitable decay.
  arXiv  Detail & Related papers  (2025-10-09T04:48:49Z)
• Discrete-Guided Diffusion for Scalable and Safe Multi-Robot Motion Planning [56.240199425429445]
  Multi-Robot Motion Planning (MPMP) involves generating trajectories for multiple robots operating in a shared continuous workspace.<n>While discrete multi-agent finding (MAPF) methods are broadly adopted due to their scalability, their coarse discretization trajectory quality.<n>This paper tackles limitations of two approaches by introducing discrete MAPF solvers with constrained generative diffusion models.
  arXiv  Detail & Related papers  (2025-08-27T17:59:36Z)
• Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models [57.45019514036948]
  Simultaneous MRMP Diffusion (SMD) is a novel approach integrating constrained optimization into the diffusion sampling process to produce collision-free, kinematically feasible trajectories.<n>The paper introduces a comprehensive MRMP benchmark to evaluate trajectory planning algorithms across scenarios with varying robot densities, obstacle complexities, and motion constraints.
  arXiv  Detail & Related papers  (2025-02-05T20:51:28Z)
• 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)
• Efficient Text-driven Motion Generation via Latent Consistency Training [21.348658259929053]
  We propose a motion latent consistency training framework (MLCT) to solve nonlinear reverse diffusion trajectories.<n>By combining these enhancements, we achieve stable and consistency training in non-pixel modality and latent representation spaces.
  arXiv  Detail & Related papers  (2024-05-05T02:11:57Z)

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.