An Adversarial Explainable Artificial Intelligence (XAI) Based Approach for Action Forecasting
Vibekananda Dutta, Teresa T. Zielinska · Journal of Automation Mobile Robotics & Intelligent Systems · 2021
Despite the growing popularity of machine learning technology, vision-based action recognition/forecasting systems are seen as black-boxes by the user.The effectiveness of such systems depends on the machine learning algorithms, it is difficult (or impossible) to explain the decisions making processes to the users.In this context, an approach that offers the user understanding of these reasoning models is significant.To do this, we present an Explainable Artificial Intelligence (XAI) based approach to action forecasting using structured database and object affordances definition.The structured database is supporting the prediction process.The method allows to visualize the components of the structured database.Later, the components of the base are used for forecasting the nominally possible motion goals.The object affordance explicated by the probability functions supports the selection of possible motion goals.The presented methodology allows satisfactory explanations of the reasoning behind the inference mechanism.Experimental evaluation was conducted using the WUT-18 dataset, the efficiency of the presented solution was compared to the other baseline algorithms.