Abstract
Goal Recognition is the task of discerning the intended goal agent aims to achieve given a sequence of observations, whereas Plan Recognition consists of identifying the plan to achieve such intended goal. Regardless of the underlying
techniques, most recognition approaches are directly affected by the quality of the available observations. In this paper, we develop neuro-symbolic recognition approaches that can combine learning and planning techniques, compensating for noise and missing observations using prior data. We evaluate our approaches in standard human-designed planning domains as well as domain models automatically learned from real-world data. Empirical experimentation shows that our approaches reliably infer goals and compute correct plans in the experimental datasets. An ablation study shows that we outperform existing approaches that rely exclusively on the domain model, or exclusively on machine learning, in problems with both noisy observations and low observability.
techniques, most recognition approaches are directly affected by the quality of the available observations. In this paper, we develop neuro-symbolic recognition approaches that can combine learning and planning techniques, compensating for noise and missing observations using prior data. We evaluate our approaches in standard human-designed planning domains as well as domain models automatically learned from real-world data. Empirical experimentation shows that our approaches reliably infer goals and compute correct plans in the experimental datasets. An ablation study shows that we outperform existing approaches that rely exclusively on the domain model, or exclusively on machine learning, in problems with both noisy observations and low observability.
Original language | English |
---|---|
Publication status | Accepted/In press - 2 Dec 2022 |
Event | AAAI-23: The 37th AAAI Conference on Artificial Intelligence - Walter E. Washington Convention Center, Washington, United States Duration: 7 Feb 2023 → 14 Feb 2023 Conference number: 37th https://aaai.org/Conferences/AAAI-23/ |
Conference
Conference | AAAI-23 |
---|---|
Country/Territory | United States |
City | Washington |
Period | 7/02/23 → 14/02/23 |
Internet address |
Bibliographical note
AcknowledgementsFelipe Meneguzzi acknowledges support from the CNPq with project 302773/2019-3 (PQ Fellowship). Ramon Fraga Pereira acknowledges support from the ERC Advanced Grant WhiteMech (No. 834228) and the EU ICT-48 2020
project TAILOR (No. 952215).