Perception with Guarantees: Certified Pose Estimation via Reachability Analysis
This addresses safety-critical localization for agents in domains like autonomous systems, though it is incremental as it builds on existing reachability analysis and verification techniques.
The paper tackles the problem of ensuring safety-critical pose estimation in cyber-physical systems by presenting a certified method that bounds pose from camera images and target geometry, achieving efficient and accurate localization in synthetic and real-world experiments.
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.