Driving on Memory

• URL: http://arxiv.org/abs/2608.31029v1
• Date: Mon, 31 Aug 2026 16:10:04 GMT
• Title: Driving on Memory
• Abstract summary: A high benchmark score should reflect that a model can understand the scene in front of it and act accordingly.<n>We replace a model's camera input with memories from prior drives at the same location.<n>Memory is nearly sufficient on NAVSIM, reaching or even exceeding the performance of leading end-to-end methods.
• Score: 44.83333974000826
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: End-to-end autonomous driving models plan future trajectories from raw sensor input. While earlier driving benchmarks often measured deviation from the human trajectory, current benchmarks such as NAVSIM and Bench2Drive evaluate models with richer simulation-based metrics intended to capture safe and compliant driving. A high benchmark score should reflect that a model can understand the scene in front of it and act accordingly. But how much of that score specifically comes from reacting to the dynamic part of that scene? To probe this, we remove a model's camera input and replace it with memories from prior drives at the same location. The retrieved memories can provide persistent scene information, including road layout and location-conditioned regularities, but not the current traffic state. Surprisingly, memory is nearly sufficient on NAVSIM, reaching or even exceeding the performance of leading end-to-end methods without actually observing the evaluated scene. Our results suggest that a high NAVSIM score does not require a planner to react to the current traffic scene and should be treated with caution. This effect is benchmark-dependent: driving from memory causes substantially larger performance drops on Bench2Drive and RealEngine. We provide our code at https://github.com/boschresearch/MemoryDrivoR .

Related papers

• PriorEye: Geospatial Visual Priors for End-to-End Autonomous Driving [8.847248042144681]
  We propose a memory augmentation module featuring a dual-memory architecture and an adaptive memory gate.<n>Our approach consistently improves performance across diverse end-to-end baselines.<n>Our method inherently improves robustness against sensor corruption, while the dual-memory design ensures safe fallback when the retrieved priors themselves become unreliable.
  arXiv  Detail & Related papers  (2026-06-30T15:36:48Z)
• EvoMemNav: Efficient Self-Evolving Fine-Grained Memory for Zero-Shot Embodied Navigation [81.54723508469617]
  EvoMemNav is an efficient, self-evolving, fine-grained memory framework for zero-shot embodied navigation.<n>VSMGraph organizes views with semantic cues and topological relations into a room-view-object hierarchy.<n>Experiments on GOAT-Bench and HM3D across object, text-description, and image-goal modalities show consistent gains in SR/SPL.
  arXiv  Detail & Related papers  (2026-06-02T11:27:44Z)
• A Survey of Spatial Memory Representations for Efficient Robot Navigation [4.560386676154887]
  Survey examines the spatial memory efficiency problem across 88 references spanning 52 systems.<n>We introduce the $= M_textpeak / M_textmap$, the ratio of peak runtime memory (the total RAM or GPU memory consumed during operation) to saved map size.
  arXiv  Detail & Related papers  (2026-04-13T02:12:17Z)
• CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning [27.23760411917563]
  We present textbfCrashSight, a vision-language benchmark for roadway crash understanding using real-world roadside camera data.<n>The dataset comprises 250 crash videos, annotated with 13K multiple-choice question-answer pairs organized under a two-tier taxonomy.<n>We benchmark 8 state-of-the-art VLMs and show that, despite strong scene description capabilities, current models struggle with temporal and causal reasoning in safety-critical scenarios.
  arXiv  Detail & Related papers  (2026-04-09T16:52:04Z)
• TARS: Traffic-Aware Radar Scene Flow Estimation [7.031882453765095]
  Scene flow provides crucial motion information for autonomous driving.<n>Recent LiDAR scene flow models utilize the rigid-motion assumption at the instance level.<n>We present a novel Traffic-Aware Radar Scene-Flow estimation method.
  arXiv  Detail & Related papers  (2025-03-13T09:54:08Z)
• NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking [65.24988062003096]
  We present NAVSIM, a framework for benchmarking vision-based driving policies. Our simulation is non-reactive, i.e., the evaluated policy and environment do not influence each other. NAVSIM enabled a new competition held at CVPR 2024, where 143 teams submitted 463 entries, resulting in several new insights.
  arXiv  Detail & Related papers  (2024-06-21T17:59:02Z)
• Enhancing End-to-End Autonomous Driving with Latent World Model [78.22157677787239]
  We propose a novel self-supervised learning approach using the LAtent World model (LAW) for end-to-end driving.<n> LAW predicts future scene features based on current features and ego trajectories.<n>This self-supervised task can be seamlessly integrated into perception-free and perception-based frameworks.
  arXiv  Detail & Related papers  (2024-06-12T17:59:21Z)
• Leveraging Driver Field-of-View for Multimodal Ego-Trajectory Prediction [69.29802752614677]
  RouteFormer is a novel ego-trajectory prediction network combining GPS data, environmental context, and the driver's field-of-view.<n>To tackle data scarcity and enhance diversity, we introduce GEM, a dataset of urban driving scenarios enriched with synchronized driver field-of-view and gaze data.
  arXiv  Detail & Related papers  (2023-12-13T23:06:30Z)
• DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving [76.29141888408265]
  We propose a large-scale dataset containing diverse accident scenarios that frequently occur in real-world driving. The proposed DeepAccident dataset includes 57K annotated frames and 285K annotated samples, approximately 7 times more than the large-scale nuScenes dataset.
  arXiv  Detail & Related papers  (2023-04-03T17:37:00Z)
• Driving Safety Prediction and Safe Route Mapping Using In-vehicle and Roadside Data [3.8103848718367597]
  The Safe Route Mapping (SRM) model is extended to consider driver behaviors when making predictions. An Android App is designed to gather drivers' information and upload it to a server. dynamic traffic information is captured by a roadside camera and uploaded to the same server. A LightGBM model is introduced to predict conflict indices for drivers in the next one or two seconds.
  arXiv  Detail & Related papers  (2022-09-12T20:39:33Z)
• Real Time Monocular Vehicle Velocity Estimation using Synthetic Data [78.85123603488664]
  We look at the problem of estimating the velocity of road vehicles from a camera mounted on a moving car. We propose a two-step approach where first an off-the-shelf tracker is used to extract vehicle bounding boxes and then a small neural network is used to regress the vehicle velocity.
  arXiv  Detail & Related papers  (2021-09-16T13:10:27Z)

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.