TY - GEN
T1 - Combining LSTMs and symbolic approaches for robust plan recognition
AU - Amado, Leonardo Rosa
AU - Pereira, Ramon Fraga
AU - Meneguzzi, Felipe
N1 - Acknowledgements: Felipe acknowledges support from CNPq with projects 407058/2018-4 (Universal) and 302773/2019-3 (PQ). Ramon acknowledges support from ERC Advanced Grant White-Mech (No. 834228) and EU ICT-48 2020 TAILOR (No. 952215).
PY - 2021/5/3
Y1 - 2021/5/3
N2 - Plan recognition is the task of inferring the actual plan an observed agent is performing to achieve a goal, given domain theory and a partial, possibly noisy, sequence of observations [3, 14, 22]. Applications include natural language processing [6], elder-care [5], multi-agent systems [4, 19], collaborative problem-solving[10, 11], epistemic problems [17] and more [7, 18]. Real world plan recognition problems impose limitations on the quality and quantity of the observations, which may be missing or faulty from silent errors in the sensors [22]. While recent approaches to goal and plan recognition have substantially improved performance under partial observability and noisy conditions [12, 13, 20, 21, 23], dealing with these problems remains a challenge.
AB - Plan recognition is the task of inferring the actual plan an observed agent is performing to achieve a goal, given domain theory and a partial, possibly noisy, sequence of observations [3, 14, 22]. Applications include natural language processing [6], elder-care [5], multi-agent systems [4, 19], collaborative problem-solving[10, 11], epistemic problems [17] and more [7, 18]. Real world plan recognition problems impose limitations on the quality and quantity of the observations, which may be missing or faulty from silent errors in the sensors [22]. While recent approaches to goal and plan recognition have substantially improved performance under partial observability and noisy conditions [12, 13, 20, 21, 23], dealing with these problems remains a challenge.
UR - http://www.scopus.com/inward/record.url?scp=85112286224&partnerID=8YFLogxK
UR - https://aamas2021.soton.ac.uk/
M3 - Published conference contribution
AN - SCOPUS:85112286224
T3 - Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
SP - 1634
EP - 1636
BT - 20th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2021
PB - International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
T2 - 20th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2021
Y2 - 3 May 2021 through 7 May 2021
ER -