返回首页

自动驾驶

共 56 篇论文

cs.CV自动驾驶CV

RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios

RoadBench is a comprehensive benchmark designed to evaluate Multimodal Large Language Models (MLLMs) on fine-grained spatial understanding and reasoning tasks specifically in urban road scenarios. The benchmark covers diverse driving conditions including intersections, parking lots, and complex road layouts to assess models' capabilities in spatial perception, object localization, and scene comprehension. It provides standardized evaluation metrics and extensive testing scenarios to advance the development of AI systems for autonomous driving applications. The benchmark includes both perception-level and reasoning-level tasks to comprehensively measure the performance of multimodal models in understanding complex road environments.

RoadBench Team
20 days ago
本地论文
cs.CV自动驾驶CV

RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios

This paper presents RoadBench, a comprehensive benchmark designed to evaluate Multi-Modal Large Language Models (MLLMs) on fine-grained spatial understanding and reasoning tasks in urban road scenarios. The benchmark includes diverse urban road images, detailed annotations, and challenging questions that require precise spatial perception and reasoning. RoadBench aims to address the gap in existing benchmarks that lack focus on fine-grained spatial understanding and reasoning under complex urban road conditions. Experimental results demonstrate that current MLLMs still face significant challenges in handling fine-grained spatial understanding and reasoning in urban road scenarios.

Unknown
20 days ago
本地论文
cs.CV自动驾驶端到端

Rectify, Don't Regret: Avoiding Pitfalls of Differentiable Simulation in Trajectory Prediction

This paper addresses critical challenges in autonomous driving trajectory prediction where minor initial deviations in open-loop models cascade into compounding errors, leading to out-of-distribution states. The authors identify a shortcut learning problem in differentiable closed-loop simulators where gradients inadvertently leak future ground truth information into previous predictions, causing non-causal regret instead of genuine recovery. To solve this, they propose a detached receding horizon rollout that severs computation graphs between simulation steps, forcing the model to learn authentic reactive recovery behaviors from drifted states. Comprehensive evaluations on the nuScenes and DeepScenario autonomous driving datasets demonstrate the effectiveness of their approach in achieving genuine trajectory rectification without temporal information leakage.

Anonymous Authors
26 days ago
arXiv 2603.23393v1
cs.CV自动驾驶CV

YOLOv10 with Kolmogorov-Arnold networks and vision-language foundation models for interpretable object detection and trustworthy multimodal AI in computer vision perception

This paper presents an interpretable object detection framework using Kolmogorov-Arnold networks to enhance trustworthiness in autonomous vehicle perception systems. The approach addresses the critical limitation of limited transparency in confidence scores during visually degraded or ambiguous driving scenarios. A Kolmogorov-Arnold network serves as an interpretable post-hoc surrogate model for YOLOv10 detections, utilizing seven geometric and semantic features to assess detection reliability. The additive spline-based architecture enables direct visualization of feature contributions, revealing when confidence scores are well-supported versus unreliable. Experimental validation on COCO dataset and University of Bath campus images demonstrates accurate trustworthiness estimation for autonomous driving perception.

Unknown
26 days ago
arXiv 2603.23037v1
cs.CV自动驾驶CV

Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Prediction

This paper presents Gau-Occ, a multi-modal framework for 3D semantic occupancy prediction in autonomous driving that models scenes as compact collections of semantic 3D Gaussians, bypassing traditional dense volumetric processing. The proposed LiDAR Completion Diffuser recovers missing structures from sparse LiDAR point clouds to initialize robust Gaussian anchors, while Gaussian Anchor Fusion efficiently integrates multi-view image semantics through geometry-aligned 2D sampling and cross-modal alignment. By refining these compact Gaussian descriptors, the method achieves both spatial consistency and semantic discriminability for comprehensive 3D scene understanding in autonomous vehicles.

Chengxin Lv +3
26 days ago
arXiv 2603.22852v1
cs.CV自动驾驶CV

Feasibility of Augmented Reality-Guided Robotic Ultrasound with Cone-Beam CT Integration for Spine Procedures

This paper presents an optical see-through augmented reality (OST-AR)-guided robotic system for spine procedures, integrating cone-beam CT (CBCT)-derived 3D spine models with live ultrasound for enhanced needle trajectory planning. The system enables in situ visualization of spinal structures, combining global anatomical context from CBCT with local real-time ultrasound feedback. A phantom user study with 16 participants evaluated facet joint injection and lumbar puncture procedures under AR vs. conventional screen visualization conditions, demonstrating the feasibility of AR-guided medical robotics for precise needle placement.

Research Team
27 days ago
arXiv 2603.22174v1
cs.CV自动驾驶端到端

Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning

This paper presents a Verbal Reinforcement Learning framework for interpretable task-level planning in mobile robots operating under execution uncertainty. The approach employs a closed-loop architecture where Behavior Trees are iteratively refined by a Large Language Model, guided by structured feedback from a Vision-Language Model critic that observes robot execution. Unlike traditional reinforcement learning, policy updates occur at the symbolic planning level without gradient-based optimization, enabling transparent reasoning and human-interpretable policy evolution. The framework is validated on a real mobile robot performing multi-stage manipulation and navigation tasks, demonstrating effective handling of execution uncertainty through iterative refinement.

Anonymous Authors
27 days ago
arXiv 2603.22169v1
cs.CV自动驾驶CV

OpenEarth-Agent: From Tool Calling to Tool Creation for Open-Environment Earth Observation

This paper presents OpenEarth-Agent, the first tool-creation agent framework designed for open-environment Earth Observation. Unlike traditional tool-calling agents confined to closed environments with pre-defined tools, OpenEarth-Agent employs adaptive workflow planning and dynamic tool creation to generalize across diverse multi-source satellite data and heterogeneous remote sensing tasks. The framework integrates multi-stage tools with cross-domain knowledge bases, enabling robust execution throughout the entire Earth Observation pipeline. This approach represents a significant advancement in autonomous EO systems by moving beyond narrow, predefined toolkits to an open-ended, adaptive framework capable of handling unseen data modalities and novel tasks in land surface monitoring applications.

OpenEarth-Agent Team
27 days ago
arXiv 2603.22148v1
cs.RO自动驾驶

Do World Action Models Generalize Better than VLAs? A Robustness Study

Robot action planning in the real world is challenging as it requires not only understanding the current state of the environment but also predicting how it will evolve in response to actions. Vision-language-action (VLA), which repurpose large-scale vision-language models for robot action generation using action experts, have achieved notable success across a variety of robotic tasks. Nevertheless, their performance remains constrained by the scope of their training data, exhibiting limited generalization to unseen scenarios and vulnerability to diverse contextual perturbations. More recently, world models have been revisited as an alternative to VLAs. These models, referred to as world action models (WAMs), are built upon world models that are trained on large corpora of video data to predict future states. With minor adaptations, their latent representation can be decoded into robot actions. It has been suggested that their explicit dynamic prediction capacity, combined with spatiotemporal priors acquired from web-scale video pretraining, enables WAMs to generalize more effectively than VLAs. In this paper, we conduct a comparative study of prominent state-of-the-art VLA policies and recently released WAMs. We evaluate their performance on the LIBERO-Plus and RoboTwin 2.0-Plus benchmarks under various visual and language perturbations. Our results show that WAMs achieve strong robustness, with LingBot-VA reaching 74.2% success rate on RoboTwin 2.0-Plus and Cosmos-Policy achieving 82.2% on LIBERO-Plus. While VLAs such as $π_{0.5}$ can achieve comparable robustness on certain tasks, they typically require extensive training with diverse robotic datasets and varied learning objectives. Hybrid approaches that partially incorporate video-based dynamic learning exhibit intermediate robustness, highlighting the importance of how video priors are integrated.

Zhanguang Zhang +12
27 days ago
arXiv 2603.22078v1
cs.GR自动驾驶

MineRobot: A Unified Framework for Kinematics Modeling and Solving of Underground Mining Robots in Virtual Environments

Underground mining robots are increasingly operated in virtual environments (VEs) for training, planning, and digital-twin applications, where reliable kinematics is essential for avoiding hazardous in-situ trials. Unlike typical open-chain industrial manipulators, mining robots are often closed-chain mechanisms driven by linear actuators and involving planar four-bar linkages, which makes both kinematics modeling and real-time solving challenging. We present \emph{MineRobot}, a unified framework for modeling and solving the kinematics of underground mining robots in VEs. First, we introduce the Mining Robot Description Format (MRDF), a domain-specific representation that parameterizes kinematics for mining robots with native semantics for actuators and loop closures. Second, we develop a topology-processing pipeline that contracts four-bar substructures into generalized joints and, for each actuator, extracts an Independent Topologically Equivalent Path (ITEP), which is classified into one of four canonical types. Third, leveraging ITEP independence, we compose per-type solvers into an actuator-centered sequential forward-kinematics (FK) pipeline. Building on the same decomposition, we formulate inverse kinematics (IK) as a bound-constrained optimization problem and solve it with a Gauss--Seidel-style procedure that alternates actuator-length updates. By converting coupled closed-loop kinematics into a sequence of small topology-aware solves, the framework avoids robot-specific hand derivations and supports efficient computation. Experiments demonstrate that MineRobot provides the real-time performance and robustness required by VE applications.

Shengzhe Hou +4
27 days ago
arXiv 2603.22055v1
cs.CV自动驾驶CV

Future-Interactions-Aware Trajectory Prediction via Braid Theory

This paper presents a novel approach to multi-agent trajectory prediction for autonomous vehicles using braid theory as a fundamental mathematical framework. The method projects future trajectories of interacting agents into braids that precisely describe how trajectories cross over time, enabling exact representation of coordination modes between agents. By fully leveraging the expressivity of the braid representation, the approach conditions predicted trajectories on specific interaction patterns, moving beyond traditional heuristic-based behavior labeling methods. This results in improved joint prediction accuracy while maintaining computational efficiency compared to existing approaches that rely on extensive computational resources.

Anonymous Authors
27 days ago
arXiv 2603.22035v1
cs.CV自动驾驶CV

LRC-WeatherNet: LiDAR, RADAR, and Camera Fusion Network for Real-time Weather-type Classification in Autonomous Driving

Autonomous vehicles encounter significant perception and navigation challenges during adverse weather conditions including rain, fog, and snow, which degrade the performance of LiDAR, RADAR, and RGB camera sensors. This study introduces LRC-WeatherNet, a novel multi-sensor fusion framework that integrates LiDAR, RADAR, and camera data for real-time weather-type classification in autonomous driving. The proposed approach employs both early fusion utilizing a unified Bird's Eye View representation and mid-level gated fusion of modality-specific feature maps, enabling adaptive sensor reliability assessment under varying weather conditions. Evaluated on the extensive MSU-4S dataset covering nine distinct weather types, LRC-WeatherNet demonstrates superior classification performance and computational efficiency, significantly outperforming unimodal baseline approaches.

LRC-WeatherNet Authors
27 days ago
arXiv 2603.21987v1
cs.CV自动驾驶

The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation

Continual Test-Time Adaptation (CTTA) aims to enable models to adapt online to unlabeled data streams under distribution shift without accessing source data. Existing CTTA methods face an efficiency-generalization trade-off: updating more parameters improves adaptation but severely reduces online inference efficiency. An ideal solution is to achieve comparable adaptation with minimal feature updates; we call this minimal subspace the golden subspace. We prove its existence in a single-step adaptation setting and show that it coincides with the row space of the pretrained classifier. To enable online maintenance of this subspace, we introduce the sample-wise Average Gradient Outer Product (AGOP) as an efficient proxy for estimating the classifier weights without retraining. Building on these insights, we propose Guided Online Low-rank Directional adaptation (GOLD), which uses a lightweight adapter to project features onto the golden subspace and learns a compact scaling vector while the subspace is dynamically updated via AGOP. Extensive experiments on classification and segmentation benchmarks, including autonomous-driving scenarios, demonstrate that GOLD attains superior efficiency, stability, and overall performance. Our code is available at https://github.com/AIGNLAI/GOLD.

Guannan Lai +3
27 days ago
arXiv 2603.21928v1
cs.CV自动驾驶CV

Disengagement Analysis and Field Tests of a Prototypical Open-Source Level 4 Autonomous Driving System

This study presents a comprehensive evaluation of an open-source Level 4 autonomous driving system through extensive field testing across 236 km of mixed traffic scenarios. The research utilizes an Autoware-based software stack and classifies 30 disengagement events using a novel five-level criticality framework, revealing a spatial disengagement rate of 0.127 per kilometer. Analysis demonstrates that perception and planning failures account for 40% and 26.7% of disengagements respectively, with object-tracking losses and operational deadlocks from parked vehicles being primary failure modes. The findings highlight critical challenges in computer vision-based perception and tracking systems for autonomous vehicles operating in complex urban environments.

Anonymous Authors
27 days ago
arXiv 2603.21926v1
cs.RO自动驾驶

IGV-RRT: Prior-Real-Time Observation Fusion for Active Object Search in Changing Environments

Object Goal Navigation (ObjectNav) in temporally changing indoor environments is challenging because object relocation can invalidate historical scene knowledge. To address this issue, we propose a probabilistic planning framework that combines uncertainty-aware scene priors with online target relevance estimates derived from a Vision Language Model (VLM). The framework contains a dual-layer semantic mapping module and a real-time planner. The mapping module includes an Information Gain Map (IGM) built from a 3D scene graph (3DSG) during prior exploration to model object co-occurrence relations and provide global guidance on likely target regions. It also maintains a VLM score map (VLM-SM) that fuses confidence-weighted semantic observations into the map for local validation of the current scene. Based on these two cues, we develop a planner that jointly exploits information gain and semantic evidence for online decision making. The planner biases tree expansion toward semantically salient regions with high prior likelihood and strong online relevance (IGV-RRT), while preserving kinematic feasibility through gradient-based analysis. Simulation and real-world experiments demonstrate that the proposed method effectively mitigates the impact of object rearrangement, achieving higher search efficiency and success rates than representative baselines in complex indoor environments.

Wei Zhang +10
27 days ago
arXiv 2603.21887v1
cs.RO自动驾驶

Optimal Solutions for the Moving Target Vehicle Routing Problem with Obstacles via Lazy Branch and Price

The Moving Target Vehicle Routing Problem with Obstacles (MT-VRP-O) seeks trajectories for several agents that collectively intercept a set of moving targets. Each target has one or more time windows where it must be visited, and the agents must avoid static obstacles and satisfy speed and capacity constraints. We introduce Lazy Branch-and-Price with Relaxed Continuity (Lazy BPRC), which finds optimal solutions for the MT-VRP-O. Lazy BPRC applies the branch-and-price framework for VRPs, which alternates between a restricted master problem (RMP) and a pricing problem. The RMP aims to select a sequence of target-time window pairings (called a tour) for each agent to follow, from a limited subset of tours. The pricing problem adds tours to the limited subset. Conventionally, solving the RMP requires computing the cost for an agent to follow each tour in the limited subset. Computing these costs in the MT-VRP-O is computationally intensive, since it requires collision-free motion planning between moving targets. Lazy BPRC defers cost computations by solving the RMP using lower bounds on the costs of each tour, computed via motion planning with relaxed continuity constraints. We lazily evaluate the true costs of tours as-needed. We compute a tour's cost by searching for a shortest path on a Graph of Convex Sets (GCS), and we accelerate this search using our continuity relaxation method. We demonstrate that Lazy BPRC runs up to an order of magnitude faster than two ablations.

Anoop Bhat +5
27 days ago
arXiv 2603.21880v1
cs.RO自动驾驶端到端

Directional Mollification for Controlled Smooth Path Generation

This paper addresses path generation for autonomous robots, industrial robots, and CNC machines by producing smooth, executable paths from discrete planning outputs such as waypoint sequences. The authors introduce directional mollification, a novel approach that overcomes the fundamental geometric constraint of standard mollification, where the smoothed path was confined within the convex hull of the original path. This method provides formal smoothness and curvature guarantees while enabling exact waypoint interpolation as required by mission specifications, offering advantages over traditional spline interpolation and optimization-based approaches for trajectory tracking controllers and nonholonomic systems.

Alfredo González-Calvin +2
27 days ago
arXiv 2603.21831v1
cs.CV自动驾驶CV

Multi-View Deformable Convolution Meets Visual Mamba for Coronary Artery Segmentation

This paper presents MDSVM-UNet, a novel two-stage framework for accurate coronary artery segmentation from CTA images. The proposed method integrates multi-view deformable convolution with Visual Mamba state space models to effectively capture long-range dependencies in vascular structures while maintaining linear computational complexity. This approach addresses challenges in segmenting complex multi-branching coronary arteries with severe class imbalance, enabling improved diagnosis and treatment planning for cardiovascular diseases. The synergy between deformable convolutions and Mamba architecture provides an efficient solution suitable for clinical deployment in resource-constrained environments.

X. Zhang +3
27 days ago
arXiv 2603.21829v1
cs.CV自动驾驶

Partial Attention in Deep Reinforcement Learning for Safe Multi-Agent Control

Attention mechanisms excel at learning sequential patterns by discriminating data based on relevance and importance. This provides state-of-the-art performance in advanced generative artificial intelligence models. This paper applies this concept of an attention mechanism for multi-agent safe control. We specifically consider the design of a neural network to control autonomous vehicles in a highway merging scenario. The environment is modeled as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP). Within a QMIX framework, we include partial attention for each autonomous vehicle, thus allowing each ego vehicle to focus on the most relevant neighboring vehicles. Moreover, we propose a comprehensive reward signal that considers the global objectives of the environment (e.g., safety and vehicle flow) and the individual interests of each agent. Simulations are conducted in the Simulation of Urban Mobility (SUMO). The results show better performance compared to other driving algorithms in terms of safety, driving speed, and reward.

Turki Bin Mohaya +1
27 days ago
arXiv 2603.21810v1
cs.RO自动驾驶

Memory-Efficient Boundary Map for Large-Scale Occupancy Grid Mapping

Determining the occupancy status of locations in the environment is a fundamental task for safety-critical robotic applications. Traditional occupancy grid mapping methods subdivide the environment into a grid of voxels, each associated with one of three occupancy states: free, occupied, or unknown. These methods explicitly maintain all voxels within the mapped volume and determine the occupancy state of a location by directly querying the corresponding voxel that the location falls within. However, maintaining all grid voxels in high-resolution and large-scale scenarios requires substantial memory resources. In this paper, we introduce a novel representation that only maintains the boundary of the mapped volume. Specifically, we explicitly represent the boundary voxels, such as the occupied voxels and frontier voxels, while free and unknown voxels are automatically represented by volumes within or outside the boundary, respectively. As our representation maintains only a closed surface in two-dimensional (2D) space, instead of the entire volume in three-dimensional (3D) space, it significantly reduces memory consumption. Then, based on this 2D representation, we propose a method to determine the occupancy state of arbitrary locations in the 3D environment. We term this method as boundary map. Besides, we design a novel data structure for maintaining the boundary map, supporting efficient occupancy state queries. Theoretical analyses of the occupancy state query algorithm are also provided. Furthermore, to enable efficient construction and updates of the boundary map from the real-time sensor measurements, we propose a global-local mapping framework and corresponding update algorithms. Finally, we will make our implementation of the boundary map open-source on GitHub to benefit the community:https://github.com/hku-mars/BDM.

Benxu Tang +8
27 days ago
arXiv 2603.21774v1
第 1 / 3 页下一页