LEO: Graph Attention Network based Hybrid Multi Sensor Extended Object Fusion and Tracking for Autonomous Driving Applications

• URL: http://arxiv.org/abs/2604.02206v1
• Date: Thu, 02 Apr 2026 15:58:18 GMT
• Title: LEO: Graph Attention Network based Hybrid Multi Sensor Extended Object Fusion and Tracking for Autonomous Driving Applications
• Abstract summary: We bridge classical Bayesian extended-object models with deep learning methods.<n>We show that LEO can learn adaptive fusion weights, ensure temporal consistency and represent multi-scale geometries.<n> Evaluations on the Mercedes-Benz DRIVE PILOT L3 dataset demonstrate real-time computational efficiency suitable for production systems.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Accurate shape and trajectory estimation of dynamic objects is essential for reliable automated driving. Classical Bayesian extended-object models offer theoretical robustness and efficiency but depend on completeness of a-priori and update-likelihood functions, while deep learning methods bring adaptability at the cost of dense annotations and high compute. We bridge these strengths with LEO (Learned Extension of Objects), a spatio-temporal Graph Attention Network that fuses multi-modal production-grade sensor tracks to learn adaptive fusion weights, ensure temporal consistency, and represent multi-scale shapes. Using a task-specific parallelogram ground-truth formulation, LEO models complex geometries (e.g. articulated trucks and trailers) and generalizes across sensor types, configurations, object classes, and regions, remaining robust for challenging and long-range targets. Evaluations on the Mercedes-Benz DRIVE PILOT SAE L3 dataset demonstrate real-time computational efficiency suitable for production systems; additional validation on public datasets such as View of Delft (VoD) further confirms cross-dataset generalization.

Related papers

• Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation [63.01022057888141]
  Asset Harvester is an image-to-3D model and end-to-end pipeline that converts sparse, in-thewild object observations from real driving logs into complete, simulation-ready assets.<n>SparseViewDiT is explicitly designed to address limited-angle views and other real-world data challenges.
  arXiv  Detail & Related papers  (2026-04-20T16:20:57Z)
• Physics-Informed Reinforcement Learning of Spatial Density Velocity Potentials for Map-Free Racing [73.88859384645264]
  Out-Of-Distribution (OOD) generalization to various racetracks utilizes Machine Learning (ML) to encode the mathematical relation between sensor data and vehicle actuation for end-to-end control.<n>This paper presents a DRL method that parameterizes nonlinear vehicle dynamics from the spectral distribution of depth measurements with a non-geometric, physics-informed reward, to infer vehicle time-optimal and overtaking racing controls with an Artificial Neural Network (ANN)<n>The policy outperforms human demonstrations by 12% in OOD tracks on proportionally scaled hardware, by maximizing the friction circle with tire dynamics that resemble an empirical Pacejka tire model.
  arXiv  Detail & Related papers  (2026-04-10T17:12:07Z)
• VLMFusionOcc3D: VLM Assisted Multi-Modal 3D Semantic Occupancy Prediction [0.0]
  VLMFusionOcc3D is a robust multimodal framework for dense 3D semantic occupancy prediction in autonomous driving.<n>We introduce Weather-Aware Adaptive Fusion, a dynamic gating mechanism that utilizes vehicle metadata and weather-conditioned prompts to re-weight sensor contributions.<n>Our approach achieves significant improvements in challenging weather scenarios, offering a scalable and robust solution for complex urban navigation.
  arXiv  Detail & Related papers  (2026-03-03T05:22:28Z)
• Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method [54.461213497603154]
  Occupancy-centric methods have recently achieved state-of-the-art results by offering consistent conditioning across frames and modalities.<n>Nuplan-Occ is the largest occupancy dataset to date, constructed from the widely used Nuplan benchmark.<n>We develop a unified framework that jointly synthesizes high-quality occupancy, multi-view videos, and LiDAR point clouds.
  arXiv  Detail & Related papers  (2025-10-27T03:52:45Z)
• MTGS: Multi-Traversal Gaussian Splatting [51.22657444433942]
  Multi-traversal data provides multiple viewpoints for scene reconstruction within a road block.<n>We propose Multi-Traversal Gaussian Splatting (MTGS), a novel approach that reconstructs high-quality driving scenes from arbitrarily collected multi-traversal data.<n>Our results demonstrate that MTGS improves LPIPS by 23.5% and geometry accuracy by 46.3% compared to single-traversal baselines.
  arXiv  Detail & Related papers  (2025-03-16T15:46:12Z)
• Spectral-Enhanced Transformers: Leveraging Large-Scale Pretrained Models for Hyperspectral Object Tracking [35.34526230299484]
  This paper proposes an effective methodology that adapts transformer-based foundation models for hyperspectral object tracking.<n>We propose an adaptive, learnable spatial-spectral token fusion module that can be extended to any transformer-based backbone.
  arXiv  Detail & Related papers  (2025-02-26T01:46:21Z)
• AdaptiveShape: Solving Shape Variability for 3D Object Detection with Geometry Aware Anchor Distributions [1.3807918535446089]
  3D object detection with point clouds and images plays an important role in perception tasks such as autonomous driving. Current methods show great performance on detection and pose estimation of standard-shaped vehicles but lack behind on more complex shapes. This work introduces several new methods to improve and measure the performance for such classes.
  arXiv  Detail & Related papers  (2023-02-28T12:31:31Z)
• CARNet: A Dynamic Autoencoder for Learning Latent Dynamics in Autonomous Driving Tasks [11.489187712465325]
  An autonomous driving system should effectively use the information collected from the various sensors in order to form an abstract description of the world. Deep learning models, such as autoencoders, can be used for that purpose, as they can learn compact latent representations from a stream of incoming data. This work proposes CARNet, a Combined dynAmic autoencodeR NETwork architecture that utilizes an autoencoder combined with a recurrent neural network to learn the current latent representation.
  arXiv  Detail & Related papers  (2022-05-18T04:15:42Z)
• Multi-Modal Fusion Transformer for End-to-End Autonomous Driving [59.60483620730437]
  We propose TransFuser, a novel Multi-Modal Fusion Transformer, to integrate image and LiDAR representations using attention. Our approach achieves state-of-the-art driving performance while reducing collisions by 76% compared to geometry-based fusion.
  arXiv  Detail & Related papers  (2021-04-19T11:48:13Z)
• SoDA: Multi-Object Tracking with Soft Data Association [75.39833486073597]
  Multi-object tracking (MOT) is a prerequisite for a safe deployment of self-driving cars. We propose a novel approach to MOT that uses attention to compute track embeddings that encode dependencies between observed objects.
  arXiv  Detail & Related papers  (2020-08-18T03:40:25Z)
• Deflating Dataset Bias Using Synthetic Data Augmentation [8.509201763744246]
  State-of-the-art methods for most vision tasks for Autonomous Vehicles (AVs) rely on supervised learning. The goal of this paper is to investigate the use of targeted synthetic data augmentation for filling gaps in real datasets for vision tasks. Empirical studies on three different computer vision tasks of practical use to AVs consistently show that having synthetic data in the training mix provides a significant boost in cross-dataset generalization performance.
  arXiv  Detail & Related papers  (2020-04-28T21:56:10Z)

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.