Modelling Observation Correlations for Active Exploration and Robust Object Detection
This work addresses the challenge of robust object detection for mobile robots in real-world environments, which is crucial for tasks like understanding human instructions, but it is incremental as it builds on existing planning and detection methods.
The paper tackles the problem of improving object detection for mobile robots by modeling spatial correlations between sensor measurements and planning motions to maximize detection performance. It demonstrates significant improvements in door and text detection tasks in both simulated and real robot experiments.
Today, mobile robots are expected to carry out increasingly complex tasks in multifarious, real-world environments. Often, the tasks require a certain semantic understanding of the workspace. Consider, for example, spoken instructions from a human collaborator referring to objects of interest; the robot must be able to accurately detect these objects to correctly understand the instructions. However, existing object detection, while competent, is not perfect. In particular, the performance of detection algorithms is commonly sensitive to the position of the sensor relative to the objects in the scene. This paper presents an online planning algorithm which learns an explicit model of the spatial dependence of object detection and generates plans which maximize the expected performance of the detection, and by extension the overall plan performance. Crucially, the learned sensor model incorporates spatial correlations between measurements, capturing the fact that successive measurements taken at the same or nearby locations are not independent. We show how this sensor model can be incorporated into an efficient forward search algorithm in the information space of detected objects, allowing the robot to generate motion plans efficiently. We investigate the performance of our approach by addressing the tasks of door and text detection in indoor environments and demonstrate significant improvement in detection performance during task execution over alternative methods in simulated and real robot experiments.