Not All History Helps: Velocity-Aware Selective Memory for Long-Horizon End-to-End Autonomous Driving

• URL: http://arxiv.org/abs/2608.15573v1
• Date: Sun, 16 Aug 2026 06:41:56 GMT
• Title: Not All History Helps: Velocity-Aware Selective Memory for Long-Horizon End-to-End Autonomous Driving
• Abstract summary: We propose StableDrive to address cross-cycle historical reliability and within-horizon motion-stage evolution.<n>On nuScenes under the MomAD evaluation protocol, StableDrive achieves SOTA across all reported planning metrics from 1 to 6 s.<n>On the Longitudinal-Transition nuScenes (LT-nuScenes), StableDrive reduces 6-s collision rate by 23.81%, TPC by 10.90%, and L2 by 6.37%.
• Score: 20.970999540713326
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reliable long-horizon planning remains a key challenge in end-to-end autonomous driving. By accounting for future motion evolution and potential consequences, it provides forward-looking guidance for safe and consistent driving in evolving traffic environments. Existing methods use historical planning states as temporal context. Self-generated history may become stale or conflict with the current motion stage, introducing unreliable priors. We propose StableDrive to address cross-cycle historical reliability and within-horizon motion-stage evolution. Selective Momentum Memory (SMM), implemented with a Mamba selective state-space operator, controls the influence of the preceding self-predicted planning state on the current cycle. Motion-Stage Training Scaffold (MSTS) uses motion-stage, long-horizon trajectory, and longitudinal-motion supervision to guide stage-aware future motion learning and is removed before inference. A fixed parameter midpoint between two architecture-aligned endpoints yields a single deployable SMM planner without model ensembling or extra inference-time computation. On nuScenes under the MomAD evaluation protocol, StableDrive achieves SOTA performance across all reported planning metrics from 1 to 6 s, reducing average collision rate by 23.3%, TPC by 30.9%, and L2 by 11.8% over the best previously reported value for each metric. On the curated Longitudinal-Transition nuScenes (LT-nuScenes), StableDrive reduces 6-s collision rate by 23.81%, TPC by 10.90%, and L2 by 6.37%. On NAVSIM v1 and v2, StableDrive achieves the highest PDMS/EPDMS in all three reported settings, including a 5.7-point EPDMS gain on v2 navhard over the previous best.

Related papers

• MomADv2: Reliable Temporal Memory for End-to-End Autonomous Driving [37.331403884871136]
  MomADv2 is a reliable state-space memory framework for end-to-end autonomous driving.<n>It filters historical planning queries based on temporal continuity and command consistency.<n>It learns a continuous residual correction field from the refined planning output to the expert trajectory.
  arXiv  Detail & Related papers  (2026-08-24T15:51:07Z)
• DREAM Technical Report [53.37525197047151]
  We present DREAM, an autonomous optimization control architecture that adds a perception-aware, orchestrable, and auditable policy layer atop existing pipelines without replacing them.<n> DREAM has two core components. First, a three-tier Intent Engine fuses on-device signals into structured L0/L1/L2 intent representations; its edge-cloud trigger chain reduces reporting volume to approximately 8.7%.<n>Second, a Meta Engine uses a MetaModel for layered M1-to-M2-to-M3 reasoning: intent summarization, strategy planning informed by Strategy Memory, and parameter translation. It dispatches the resulting parameters through a unified outlet with
  arXiv  Detail & Related papers  (2026-08-10T10:35:32Z)
• Steins;Gate Drive: Semantic Safety Arbitration over Structured Futures for Latency-Decoupled LLM Planning [4.025443168660699]
  SteinsGateDrive is a latency-decoupled planner-runtime architecture.<n>We present SteinsGateDrive, a latency-decoupled planner-runtime architecture.
  arXiv  Detail & Related papers  (2026-05-21T13:20:51Z)
• LLaViDA: A Large Language Vision Driving Assistant for Explicit Reasoning and Enhanced Trajectory Planning [28.59507336524504]
  Trajectory planning is a fundamental yet challenging component of autonomous driving.<n>We propose LLaViDA, a Large Language Vision Driving Assistant that leverages a Vision-Language Model (VLM) for object motion prediction.<n>On the NuScenes benchmark, LLaViDA surpasses state-of-the-art end-to-end and other recent VLM/LLM-based baselines in open-loop trajectory planning task.
  arXiv  Detail & Related papers  (2025-12-20T04:38:35Z)
• Mimir: Hierarchical Goal-Driven Diffusion with Uncertainty Propagation for End-to-End Autonomous Driving [17.533465904228844]
  We propose Mimir, a novel hierarchical dual-system framework capable of generating robust trajectories relying on goal points with uncertainty estimation.<n>Mimir surpasses previous state-of-the-art methods with a 20% improvement in the driving scoreS, while achieving 1.6 times improvement in high-level module inference speed.
  arXiv  Detail & Related papers  (2025-12-08T03:31:25Z)
• KEPT: Knowledge-Enhanced Prediction of Trajectories from Consecutive Driving Frames with Vision-Language Models [19.625631486595505]
  This paper introduces KEPT, a knowledge-enhanced vision-language framework.<n>It predicts ego trajectories directly from consecutive front-view driving frames.<n>It achieves state-of-the-art performance across open-loop protocols.
  arXiv  Detail & Related papers  (2025-09-03T03:10:42Z)
• SpaRC-AD: A Baseline for Radar-Camera Fusion in End-to-End Autonomous Driving [5.343552118560704]
  SpaRC-AD is a query-based end-to-end camera-radar fusion framework for planning-oriented autonomous driving.<n>Our method achieves strong improvements over the state-of-the-art vision-only baselines across multiple autonomous driving tasks.
  arXiv  Detail & Related papers  (2025-08-14T12:02:41Z)
• DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving [62.62464518137153]
  DriveTransformer is a simplified E2E-AD framework for the ease of scaling up.<n>It is composed of three unified operations: task self-attention, sensor cross-attention, temporal cross-attention.<n>It achieves state-of-the-art performance in both simulated closed-loop benchmark Bench2Drive and real world open-loop benchmark nuScenes with high FPS.
  arXiv  Detail & Related papers  (2025-03-07T11:41:18Z)
• Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving [59.705635382104454]
  We present Bench2Drive, the first benchmark for evaluating E2E-AD systems' multiple abilities in a closed-loop manner.<n>We implement state-of-the-art E2E-AD models and evaluate them in Bench2Drive, providing insights regarding current status and future directions.
  arXiv  Detail & Related papers  (2024-06-06T09:12:30Z)
• STT: Stateful Tracking with Transformers for Autonomous Driving [48.621552393062686]
  Tracking objects in three-dimensional space is critical for autonomous driving. To ensure safety while driving, the tracker must be able to reliably track objects across frames and accurately estimate their states such as velocity and acceleration in the present. We propose STT, a Stateful Tracking model built with Transformers, that can consistently track objects in the scenes while also predicting their states accurately.
  arXiv  Detail & Related papers  (2024-04-30T23:04:36Z)
• Motion Planning and Control for Multi Vehicle Autonomous Racing at High Speeds [100.61456258283245]
  This paper presents a multi-layer motion planning and control architecture for autonomous racing. The proposed solution has been applied on a Dallara AV-21 racecar and tested at oval race tracks achieving lateral accelerations up to 25 $m/s2$.
  arXiv  Detail & Related papers  (2022-07-22T15:16:54Z)
• IntentNet: Learning to Predict Intention from Raw Sensor Data [86.74403297781039]
  In this paper, we develop a one-stage detector and forecaster that exploits both 3D point clouds produced by a LiDAR sensor as well as dynamic maps of the environment. Our multi-task model achieves better accuracy than the respective separate modules while saving computation, which is critical to reducing reaction time in self-driving applications.
  arXiv  Detail & Related papers  (2021-01-20T00:31:52Z)

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.