用摄像头和已知物体形状，实现3D姿态的可信定位
Perception with Guarantees: Certified Pose Estimation via Reachability Analysis
- 基于可达性分析与神经网络验证，对摄像头图像中的物体姿态进行形式化边界计算
- 在真实与合成场景中均实现高效准确的3D姿态估计，误差可严格证明
- 适合对安全性要求极高的自动驾驶、机器人导航等场景
网络物理系统中的智能体日益承担安全关键任务。确保其安全通常需要精确定位姿态以执行后续操作。姿态估计可通过激光雷达、摄像头及外部服务（如GPS）等多种方式获取。然而，在安全关键领域，粗略估计不足以保证安全——即在最坏情况下仍能形式化保证安全，且外部服务可能不可信。本文提出一种仅依赖单张相机图像与已知目标几何结构的3D姿态认证估计方法。通过利用最新的可达性分析与形式化神经网络验证技术，对姿态进行形式化上界约束。实验表明，该方法在合成与真实世界场景中均能高效、准确地完成智能体定位。
原文摘要 · Abstract (English)
Agents in cyber-physical systems are increasingly entrusted with safety-critical tasks. Ensuring safety of these agents often requires localizing the pose for subsequent actions. Pose estimates can, e.g., be obtained from various combinations of lidar sensors, cameras, and external services such as GPS. Crucially, in safety-critical domains, a rough estimate is insufficient to formally determine safety, i.e., guaranteeing safety even in the worst-case scenario, and external services might additionally not be trustworthy. We address this problem by presenting a certified pose estimation in 3D solely from a camera image and a well-known target geometry. This is realized by formally bounding the pose, which is computed by leveraging recent results from reachability analysis and formal neural network verification. Our experiments demonstrate that our approach efficiently and accurately localizes agents in both synthetic and real-world experiments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。