PulseAugur
中
实时 13:13:06

AI research advances autonomous driving perception and safety

作者 PulseAugur 编辑部 · [5 个来源] ·

Researchers are developing advanced AI techniques to improve autonomous driving systems. One approach, CaAD, focuses on causality-aware end-to-end modeling to better predict vehicle and agent interactions, showing strong performance on benchmarks. Another method, Enhanced HOPE, uses adaptive perception that adjusts computation based on scene complexity and incorporates temporal memory to track occluded objects. Additionally, generative AI is being used to create diverse synthetic pedestrian data for training more robust perception models, highlighting the benefits and limitations of cross-domain training. Finally, a novel attack paradigm leverages view-induced trajectory manipulation, using static camouflage to trick autonomous vehicles into inferring incorrect paths and triggering unnecessary braking. AI

影响 New AI methodologies promise to enhance the safety, robustness, and efficiency of autonomous driving systems.

排序理由 Cluster contains multiple academic papers detailing new AI methodologies for autonomous driving.

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →

AI research advances autonomous driving perception and safety

报道来源 [5]

  1. arXiv cs.AI TIER_1 English(EN) · Jungbeom Lee ·

    Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling

    End-to-end autonomous driving, which bypasses traditional modular pipelines by directly predicting future trajectories from sensor inputs, has recently achieved substantial progress. However, existing methods often overlook the causal inter-dependencies in ego-vehicle planning, i…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling

    End-to-end autonomous driving, which bypasses traditional modular pipelines by directly predicting future trajectories from sensor inputs, has recently achieved substantial progress. However, existing methods often overlook the causal inter-dependencies in ego-vehicle planning, i…

  3. arXiv cs.AI TIER_1 English(EN) · Jaehyoung Park ·

    Think as Needed: Geometry-Driven Adaptive Perception for Autonomous Driving

    Autonomous driving scenes range from empty highways to dense intersections with dozens of interacting road users, yet current 3D detection models apply a fixed computation budget to every frame, wasting resources on simple scenes while lacking capacity for complex ones. Existing …

  4. arXiv cs.CV TIER_1 English(EN) · Oliver Wasenmuller ·

    Generative Texture Diversification of 3D Pedestrians for Robust Autonomous Driving Perception

    In recent years, autonomous driving has significantly in creased the demand for high-quality data to train 2D and 3D perception models for safety-critical scenarios. Real world datasets struggle to meet this demand as require ments continuously evolve and large-scale annotated da…

  5. arXiv cs.CV TIER_1 English(EN) · Sen He ·

    Still Camouflage, Moving Illusion: View-Induced Trajectory Manipulation in Autonomous Driving

    Existing physical adversarial attacks on vision-based autonomous driving induce time-evolving perception errors, including biased object tracking or trajectory prediction, through (i) sophisticated physical patch inducing detection box drift when entering the view distance, or (i…

相关实体

相关话题