Open-World Active Learning with Stacking Ensemble for Self-Driving Cars
This addresses the challenge of handling unknown objects in high-risk autonomous driving scenarios, but it appears incremental as it builds on existing algorithms like DOC and Query-by-Committee.
The paper tackles the problem of classifying objects in dynamic, uncertain environments for self-driving cars by proposing an open-world active learning algorithm that identifies known entities and detects/learns unknown objects, achieving unspecified performance improvements.
The environments, in which autonomous cars act, are high-risky, dynamic, and full of uncertainty, demanding a continuous update of their sensory information and knowledge bases. The frequency of facing an unknown object is too high making hard the usage of Artificial Intelligence (AI) classical classification models that usually rely on the close-world assumption. This problem of classifying objects in this domain is better faced with and open-world AI approach. We propose an algorithm to identify not only all the known entities that may appear in front of the car, but also to detect and learn the classes of those unknown objects that may be rare to stand on an highway (e.g., a lost box from a truck). Our approach relies on the DOC algorithm from Lei Shu et. al. as well as on the Query-by-Committee algorithm.