Autonomous Vehicles
PulseAugur coverage of Autonomous Vehicles — every cluster mentioning Autonomous Vehicles across labs, papers, and developer communities, ranked by signal.
4 天有情绪数据
-
MapGCLR通过自监督地理空间学习改进高清地图构建
研究人员开发了MapGCLR，一种新颖的自监督学习方法，用于改进自动驾驶汽车矢量化高清地图的构建。该方法通过使用对比损失函数强制重叠地图片段之间的地理空间一致性来增强鸟瞰图特征的表示。通过在具有多遍历要求的大型无标签数据集上进行训练，MapGCLR在下游感知任务和定性可视化方面优于传统的监督方法。
-
图像处理系统：后端、模型更新和车队管理
本文讨论了图像处理系统的后端、模型更新和车队管理方面。文章强调了这些系统在安全、自动驾驶汽车、医疗保健和工业自动化等各个领域的广泛应用。文章着重介绍了部署和维护这些复杂系统所涉及的技术挑战和解决方案。
-
新AI模型使用4D雷达进行可靠的人员检测
研究人员开发了一种名为TMVA4D的新型人工神经网络架构，用于使用4D雷达数据进行语义分割。该系统旨在提高自动驾驶汽车和机器人检测人员的可靠性，特别是在传统传感器（如摄像头和激光雷达）可能失效的严峻环境条件下。TMVA4D模型利用CNN和ConvLSTM编码器处理包括多普勒速度在内的4D雷达点云，并在区分人员与背景噪声方面显示出有希望的结果，即使在低能见度场景下也是如此。
-
Singapore pilots robots for delivery, cleaning, and patrols
Singapore is positioning itself as a hub for "physical AI" by piloting various robots for tasks like cleaning, patrolling, and delivery. Companies such as Grab are testing autonomous vehicles to address labor shortages …
-
AI research tackles temporal grounding for AVs and video analysis
Two new research papers explore methods to improve temporal grounding in AI systems, particularly for autonomous vehicles and video analysis. The first paper, "From Prompts to Pavement Through Time," investigates tempor…
-
AI automation enables 24/7 robot skeleton production in factories
An AI-focused social media account shared a meme depicting autonomous vehicles and AI-powered machinery operating 24/7 in a factory. This automation allows for the production of robot skeletons, a task previously requir…
-
Auddia launches edge AI datacenters for AVs; America First Defense partners with Anduril
Auddia has introduced the LT350, a system designed to support autonomous vehicles through distributed AI data centers. These data centers, integrated with solar-powered parking canopies, will facilitate real-time comput…
-
AI model generates realistic safety-critical scenarios for autonomous vehicle training
Researchers have developed a new method called Conditional Flow-VAE to generate realistic safety-critical scenarios for autonomous vehicle development. This approach uses distribution matching to transform standard driv…
-
AI system PALCAS improves autonomous vehicle lane changes with federated reinforcement learning
Researchers have developed PALCAS, a new system for autonomous vehicles that uses federated reinforcement learning to advise on lane changes. Unlike previous systems, PALCAS prioritizes lane changes based on a vehicle's…
-
New framework offers calibration checks for safety-critical AI systems
Researchers have developed a new framework for calibration checks designed to validate the distributional properties of probabilistic forecasts in safety-critical applications. This framework produces a single accept/re…
-
Researchers compare RL methods for testing autonomous vehicle requirements
A new study empirically evaluates reinforcement learning techniques for testing autonomous vehicles, specifically comparing single-objective RL (SORL) and multi-objective RL (MORL) in generating critical scenarios. The …