Hierarchical Bayesian Noise Inference for Robust Real-time Probabilistic Object Classification
This addresses the need for accurate uncertainty handling in robot perception, particularly for semantic object labels in complex environments, though it is incremental as it builds on existing filtering methods.
The paper tackles the problem of robust object classification for robots by filtering sequences of classification probabilities using online noise modeling, resulting in improved classification accuracy over existing methods and successful real-time hardware experiments on a moving quadrotor.
Robust environment perception is essential for decision-making on robots operating in complex domains. Principled treatment of uncertainty sources in a robot's observation model is necessary for accurate mapping and object detection. This is important not only for low-level observations (e.g., accelerometer data), but for high-level observations such as semantic object labels as well. This paper presents an approach for filtering sequences of object classification probabilities using online modeling of the noise characteristics of the classifier outputs. A hierarchical Bayesian approach is used to model per-class noise distributions, while simultaneously allowing sharing of high-level noise characteristics between classes. The proposed filtering scheme, called Hierarchical Bayesian Noise Inference (HBNI), is shown to outperform classification accuracy of existing methods. The paper also presents real-time filtered classification hardware experiments running fully onboard a moving quadrotor, where the proposed approach is demonstrated to work in a challenging domain where noise-agnostic filtering fails.