{"total":14,"items":[{"citing_arxiv_id":"2605.19490","ref_index":9,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Closed-Loop Hybrid Digital Twin Platform for Connected and Automated Vehicle Validation","primary_cat":"cs.RO","submitted_at":"2026-05-19T07:44:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A real-time hybrid digital twin platform couples high-fidelity CARLA-SUMO co-simulation with a physical CAV test site via V2X for closed-loop control and multi-scenario verification.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18074","ref_index":23,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"4DLidarOpen: An Open 4D FMCW Lidar Dataset for Motion-Aware Autonomous Driving","primary_cat":"cs.RO","submitted_at":"2026-05-18T08:55:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"4DLidarOpen is a new open dataset providing synchronized 4D FMCW Lidar velocity measurements, multi-Lidar and camera data, and 3D bounding-box annotations with track IDs to support benchmarks on 3D detection, BEV segmentation, flow prediction, and motion forecasting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16805","ref_index":10,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"NeuroLiDAR: Adaptive Frame Rate Depth Sensing via Neuromorphic Event-LiDAR Fusion","primary_cat":"cs.CV","submitted_at":"2026-05-16T04:21:59+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"NeuroLiDAR adaptively boosts LiDAR frame rates to 27.8-66 Hz via event-camera fusion and cuts depth RMSE by 29% on a new ELiDAR dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13591","ref_index":23,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Real2Sim: A Physics-driven and Editable Gaussian Splatting Framework for Autonomous Driving Scenes","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:26:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Real2Sim reconstructs editable dynamic driving scenes as temporally continuous Gaussians integrated with a differentiable MPM physics solver for high-fidelity simulation of interactions and collisions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08713","ref_index":15,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"REAP: Reinforcement-Learning End-to-End Autonomous Parking with Gaussian Splatting Simulator for Real2Sim2Real Transfer","primary_cat":"cs.RO","submitted_at":"2026-05-09T05:50:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"REAP trains an end-to-end SAC policy with behavior cloning and collision penalties inside a 3DGS Real2Sim simulator and transfers it to physical vehicles, succeeding in narrow mechanical parking slots.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"This often leads to planning failures in complex scenarios when there is no prior map or when real- time perception is inaccurate. Deep reinforcement learning (DRL) [14], as an interactive learning method, has achieved remarkable success in scenar- ios such as games and gambling. In the field of robotics, reinforcement learning is often trained in simulators [15]- [18]. However, a Sim2Real gap remains, leading to significant degradation in model performance when models trained in simulators are transferred to real-world environments. Re- cently, some methods [19], [20] have adopted 3D Gaussian Splatting (3DGS) combined with physics engines [16], [17] to achieve visual fidelity. However, these simulators mainly"},{"citing_arxiv_id":"2605.05897","ref_index":15,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Generating Roadside LiDAR Datasets from Vehicle-Side Datasets via Novel View Synthesis","primary_cat":"cs.RO","submitted_at":"2026-05-07T09:10:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"VRS generates annotated roadside LiDAR data from vehicle observations via novel view synthesis with geometry completion and occupancy constraints, improving 3D object detection generalization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01121","ref_index":22,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"From Sensing to Decision: A Generic Architecture for Freight Signal Priority Systems","primary_cat":"eess.SY","submitted_at":"2026-05-01T21:46:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A systematic review proposes a generic two-layer architecture for Freight Signal Priority systems that links sensing modalities to reliable priority decisions while accounting for detection and communication uncertainties.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23105","ref_index":59,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Driving","primary_cat":"cs.CV","submitted_at":"2026-04-25T02:00:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AdvAD produces physical-world adversarial patches with improved transferability to unseen object detectors by multi-model optimization, adaptive balancing, and physical variation robustness.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22835","ref_index":9,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"ParkingScenes: A Structured Dataset for End-to-End Autonomous Parking in Simulation Scenes","primary_cat":"cs.CV","submitted_at":"2026-04-20T06:37:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ParkingScenes is a new multimodal dataset of 704 structured reverse and parallel parking episodes generated in CARLA with Hybrid A* and MPC trajectories, showing better model performance than unstructured simulation data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12208","ref_index":18,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Unveiling the Surprising Efficacy of Navigation Understanding in End-to-End Autonomous Driving","primary_cat":"cs.RO","submitted_at":"2026-04-14T02:34:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"The SNG framework and SNG-VLA model enable end-to-end driving systems to better incorporate global navigation for state-of-the-art route following without auxiliary perception losses.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.02573","ref_index":11,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Dynamic Risk Generation for Autonomous Driving: Naturalistic Reconstruction of Vehicle-E-Scooter Interactions","primary_cat":"eess.SY","submitted_at":"2026-04-02T23:05:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A simulation pipeline reconstructs real vehicle-e-scooter interactions and extends them to higher-risk scenarios using a Social Force Model to validate autonomous vehicle collision avoidance.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"* Corresponding author: Yaobin Chen. Fig. 1. General pipeline for VEI scenario generation from naturalistic driving data. Building on the collected traffic data that focuses on e- scooter motion behavior by [10], this paper proposes a pipeline (Fig. 1) that can reproduce real-time vehicle and e-scooter interaction (VEI) in a simulated traffic environment based on the CARLA platform [11]. Variants of motion behavior for the e-scooter rider are created in the simulation by applying a social force model. The extended synthetic scenarios can be used to test the safety functions, such as emergency braking. An extensive traffic scenario for the VEI can be developed using this pipeline for future AD development. The key contributions of this paper include:"},{"citing_arxiv_id":"2512.16055","ref_index":11,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Driving in Corner Case: A Real-World Adversarial Closed-Loop Evaluation Platform for End-to-End Autonomous Driving","primary_cat":"cs.CV","submitted_at":"2025-12-18T00:41:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A platform using flow matching for real-world image generation and an adversarial policy creates challenging corner cases to evaluate end-to-end autonomous driving models like UniAD and VAD, showing performance degradation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.08439","ref_index":53,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Dataset Safety in Autonomous Driving: Requirements, Risks, and Assurance","primary_cat":"cs.AI","submitted_at":"2025-11-11T16:42:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"The paper introduces a safety framework for datasets in autonomous driving that uses the AI Data Flywheel and lifecycle processes to identify hazards and ensure compliance with ISO/PAS 8800.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2505.14184","ref_index":20,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"VaN3Twin: the Multi-Technology V2X Digital Twin with Ray-Tracing in the Loop","primary_cat":"cs.NI","submitted_at":"2025-05-20T10:41:11+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}