Publications

@article{dechant_learning_2023,

title = {Learning to summarize and answer questions about a virtual robot’s past actions},

author = {C. DeChant and I. Akinola and D. Bauer},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85176588341&doi=10.1007%2fs10514-023-10134-4&partnerID=40&md5=162b3343d5f000f2b79f59c339f99022},

doi = {10.1007/s10514-023-10134-4},

issn = {09295593 (ISSN)},

year  = {2023},

date = {2023-01-01},

journal = {Autonomous Robots},

volume = {47},

number = {8},

pages = {1103–1118},

abstract = {When robots perform long action sequences, users will want to easily and reliably find out what they have done. We therefore demonstrate the task of learning to summarize and answer questions about a robot agent’s past actions using natural language alone. A single system with a large language model at its core is trained to both summarize and answer questions about action sequences given ego-centric video frames of a virtual robot and a question prompt. To enable training of question answering, we develop a method to automatically generate English-language questions and answers about objects, actions, and the temporal order in which actions occurred during episodes of robot action in the virtual environment. Training one model to both summarize and answer questions enables zero-shot transfer of representations of objects learned through question answering to improved action summarization. © 2023, The Author(s).},

keywords = {Action sequences, E-Learning, Interpretability, Language Model, Long horizon task, Long horizon tasks, Natural language processing systems, Natural languages, Question Answering, Representation learning, Robots, Summarization, Video frame, Virtual Reality, Virtual robots, Zero-shot learning},

pubstate = {published},

tppubtype = {article}

}