The failure of intelligent systems, such as robots, can be inevitable, requiring recoveryassistance from users . In this work, we develop automated, natural languageexplanations for failures encountered during an AI agents’ plan execution . These explanations are developed with a focus of helping non-expert usersunderstand different point of failures to better provide recovery assistance . By doing so, we are able develop a model that can generalize context-based explanations over both different failure types andfailure scenarios . We are able to generalize these explanations over . different failure scenarios. By doing . so we are . able to . develop an existing sequence-to-sequence methodology to automatically generate ourcontext-based explanation .

Author(s) : Devleena Das, Siddhartha Banerjee, Sonia Chernova

Links : PDF - Abstract

Code :


Keywords : explanations - failures - failure - develop - sequence -

Leave a Reply

Your email address will not be published. Required fields are marked *