Amortizing Trajectory Diffusion with Keyed Drift Fields

• URL: http://arxiv.org/abs/2603.14056v1
• Date: Sat, 14 Mar 2026 17:56:15 GMT
• Title: Amortizing Trajectory Diffusion with Keyed Drift Fields
• Abstract summary: Keyed Drifting Policies is a one-step trajectory generator trained with a drift-field objective.<n>It repels generated trajectories toward condition-matched dataset windows.<n>It achieves strong performance with one-step inference and substantially lower planning latency than diffusion sampling.
• Score: 2.5352713493505785
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion-based trajectory planners can synthesize rich, multimodal action sequences for offline reinforcement learning, but their iterative denoising incurs substantial inference-time cost, making closed-loop planning slow under tight compute budgets. We study the problem of achieving diffusion-like trajectory planning behavior with one-step inference, while retaining the ability to sample diverse candidate plans and condition on the current state in a receding-horizon control loop. Our key observation is that conditional trajectory generation fails under naïve distribution-matching objectives when the similarity measure used to align generated trajectories with the dataset is dominated by unconstrained future dimensions. In practice, this causes attraction toward average trajectories, collapses action diversity, and yields near-static behavior. Our key insight is that conditional generative planning requires a conditioning-aware notion of neighborhood: trajectory updates should be computed using distances in a compact key space that reflects the condition, while still applying updates in the full trajectory space. Building on this, we introduce Keyed Drifting Policies (KDP), a one-step trajectory generator trained with a drift-field objective that attracts generated trajectories toward condition-matched dataset windows and repels them from nearby generated samples, using a stop-gradient drifted target to amortize iterative refinement into training. At inference, the resulting policy produces a full trajectory window in a single forward pass. Across standard RL benchmarks and real-time hardware deployments, KDP achieves strong performance with one-step inference and substantially lower planning latency than diffusion sampling. Project website, code and videos: https://keyed-drifting.github.io/

Related papers

• G2DP: Diffusion Planning with Spatio-Temporal Grid Guidance [44.0166619948181]
  In autonomous driving, diffusion-based planners have emerged as a promising paradigm for robust motion planning in dense and interactive traffic.<n>Existing guidance typically relies on sparse, entity-centric geometric queries or post-hoc refinement, yielding limited awareness and fragile performance in interactive scenes.<n>G2DP (GuidedGrid-Guided Planning) constructs a differentiable-temporal cost volume by fusing probabilistic future occupancy guidance with a route-time map.<n>It achieves state-of-the-art performance on nuPlan, outperforming the strongest imitation-learning baseline by +7.2 points in reactive transfers.
  arXiv  Detail & Related papers  (2026-06-24T16:38:55Z)
• Ergodic Trajectory Design by Learned Pushforward Maps: Provable Coverage via Conditional Flow Matching [3.1807155456602274]
  The emphergodic coverage problem is central to UAV-assisted data collection and sensing, robotic exploration, and mobile monitoring.<n>For flying agents, trajectories must balance coverage fidelity against tight energy budgets, no-fly zones, and acceleration limits.<n>We propose a emphepushforward framework that decouples ergodicity from density matching.
  arXiv  Detail & Related papers  (2026-05-13T06:34:08Z)
• RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework [49.531001563853984]
  RAD-2 is a unified generator-discriminator framework for closed-loop planning.<n>It produces diverse trajectory candidates, while an RL-optimized discriminator reranks these candidates according to their long-term driving quality.<n>It reduces the collision rate by 56% compared with strong diffusion-based planners.
  arXiv  Detail & Related papers  (2026-04-16T17:59:44Z)
• HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving [51.268878540511054]
  We propose HAD, an end-to-end planning framework with a Hierarchical Diffusion Policy.<n>We show that HAD achieves new state-of-the-art performance on both NAVSIM and HUGSIM.
  arXiv  Detail & Related papers  (2026-04-04T04:12:47Z)
• PC-Diffuser: Path-Consistent Capsule CBF Safety Filtering for Diffusion-Based Trajectory Planner [15.914164951048614]
  PC-Diffuser is a safety augmentation framework that embeds a path-consistent barrier-function structure directly into the denoising loop of diffusion planning.<n>It evaluates collision risk using a capsule-distance barrier function that better reflects vehicle geometry.<n>It converts denoised waypoints into dynamically feasible motion under a kinematic bicycle model.
  arXiv  Detail & Related papers  (2026-03-11T01:52:56Z)
• Streaming Real-Time Trajectory Prediction Using Endpoint-Aware Modeling [54.94692733670454]
  Future trajectories of neighboring traffic agents have a significant influence on the path planning and decision-making of autonomous vehicles.<n>We propose a lightweight yet highly accurate streaming-based trajectory forecasting approach.<n>Our approach significantly reduces inference latency, making it well-suited for real-world deployment.
  arXiv  Detail & Related papers  (2026-03-02T13:44:23Z)
• ASTRO: Adaptive Stitching via Dynamics-Guided Trajectory Rollouts [22.46606397400043]
  We propose ASTRO, a data augmentation framework that generates distributionally novel and dynamics-consistent trajectories for offline RL.<n>ASTRO first learns a temporal-distance representation to identify distinct and reachable stitch targets.<n>We then employ a dynamics-guided stitch planner that adaptively generates connecting action sequences via Rollout Deviation Feedback.
  arXiv  Detail & Related papers  (2025-11-28T18:35:37Z)
• CAPE: Context-Aware Diffusion Policy Via Proximal Mode Expansion for Collision Avoidance [15.311155448797386]
  contexts-aware diffusion policy via Proximal mode Expansion (CAPE)<n>CAPE expands trajectory distribution modes with context-aware prior and guidance at inference.<n>We evaluate CAPE on diverse manipulation tasks in cluttered unseen simulated and real-world settings.
  arXiv  Detail & Related papers  (2025-11-27T21:53:09Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• FlowDrive: moderated flow matching with data balancing for trajectory planning [5.553127690929986]
  FlowDrive is a flow-matching trajectory planner that learns a conditional rectified flow to map noise directly to trajectory distributions.<n>FlowDrive achieves state-of-the-art results among learning-based planners and approaches methods with rule-based refinements.
  arXiv  Detail & Related papers  (2025-09-26T06:49:22Z)
• Real-Time Sampling-based Online Planning for Drone Interception [18.340019191662957]
  We propose a sampling-based online planning algorithm that leverages neural network inference to replace time-consuming nonlinear trajectory optimization.<n>The proposed method is applied to the drone interception problem, where a defense drone must intercept a target while avoiding collisions and handling imperfect target predictions.
  arXiv  Detail & Related papers  (2025-02-20T03:48:38Z)
• OPUS: Occupancy Prediction Using a Sparse Set [64.60854562502523]
  We present a framework to simultaneously predict occupied locations and classes using a set of learnable queries. OPUS incorporates a suite of non-trivial strategies to enhance model performance. Our lightest model achieves superior RayIoU on the Occ3D-nuScenes dataset at near 2x FPS, while our heaviest model surpasses previous best results by 6.1 RayIoU.
  arXiv  Detail & Related papers  (2024-09-14T07:44:22Z)
• Layout Sequence Prediction From Noisy Mobile Modality [53.49649231056857]
  Trajectory prediction plays a vital role in understanding pedestrian movement for applications such as autonomous driving and robotics. Current trajectory prediction models depend on long, complete, and accurately observed sequences from visual modalities. We propose LTrajDiff, a novel approach that treats objects obstructed or out of sight as equally important as those with fully visible trajectories.
  arXiv  Detail & Related papers  (2023-10-09T20:32:49Z)
• Manifold Interpolating Optimal-Transport Flows for Trajectory Inference [64.94020639760026]
  We present a method called Manifold Interpolating Optimal-Transport Flow (MIOFlow) MIOFlow learns, continuous population dynamics from static snapshot samples taken at sporadic timepoints. We evaluate our method on simulated data with bifurcations and merges, as well as scRNA-seq data from embryoid body differentiation, and acute myeloid leukemia treatment.
  arXiv  Detail & Related papers  (2022-06-29T22:19:03Z)

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.