Contact person: Jasmin Grosinger (jasmin.grosinger@oru.se)

Internal Partners:

1. Örebro University, ORU, Jasmin Grosinger

External Partners:

1. Denmark Technical Unisersity, Thomas Bolander

Previously we have investigated how an AI system can be proactive, that is, acting anticipatory and on its own initiative, by reasoning on current and future states, mental simulation of actions and their effects, and what is desirable. In this micro-project we extend our earlier work doing epistemic reasoning. That is, we want to do reasoning on knowledge and belief of the human and by that inform the AI system what kind of proactive announcement to make to the human. As in our previous work, we will consider which states are desirable and which are not, and we too will take into account how the state will evolve into the future, if the AI system does not act. Now we also want to consider the human’s false beliefs. It is not necessary and, in fact, not desirable to make announcements to correct each and any false belief that the human may have. For example, if the human is watching the TV, she need not be informed that the salt is in the red container and the sugar is in the blue container, while the human’s belief is that it is the other way around. On the other hand, when the human starts cooking and is about to use the content of the blue container believing it is salt, then it is a relevant announcement of the AI system to inform the human what is actually the case to avoid undesirable outcomes. The example shows that we need to research not only what to announce but also when to make the announcement. The methods we will use in this micro-project are knowledge-based, to be precise, we will employ Dynamic Epistemic Logic (DEL). DEL is a modal logic. It is an extension of Epistemic Logic which allows to model change in knowledge and belief of an agent herself and of other agents.1 week of visit is planned.

Results Summary

[On going project] The project is still going on. It turned out to be much bigger and is way beyond the scope of a micro-project. Also there were interruptions. We are working on our DEL-based framework for proactive agents and expect a journal article submission in January next year. The project will keep going on at least until then, but is expected to continue and extend the current status of the work.

Contact person: Loris Bozzato 

Internal Partners:

1. Fondazione Bruno Kessler (FBK), Loris Bozzato
2. TU Wien, Thomas EIter

This project continues the collaboration between FBK and TUW about defeasible knowledge in description logics in the Contextualized Knowledge Repository (CKR) framework.In applications, knowledge can hold by default and be overridden in more specific contexts. For example, in a tourism event recommendation system, events can appear as suggested to a class of tourists in a general context: in the more specific context of a particular tourist, preferences can be refined to more precise interests, which may override those at higher contexts.Goal of this project is to enhance the answer set programming (ASP) based realization of CKR to deal with complex context hierarchies: we use an ASP extension recently proposed by TUW, ASP with algebraic measures, which allows for reasoning on orderings induced by the organization of defeasible knowledge. This collaboration provides a prototype for reasoning over CKR hierarchies, but also an application for ASP with algebraic measures.

Results Summary

The goal of this project is to reason on complex contextualized knowledge bases using an answer set programming extension with algebraic measures and show the capabilities of this formalism.

The main formal contributions of this project are:

• an extension of the CKR contextual framework to reason about defeasible information over multi-relational contextual hierarchies.
• an ASP based modelling of multi-relational CKRs, where combination of model preferences is realized via algebraic measure expressions.
• an aspirin based implementation of query answering in a fragment of multi-relational CKRs, extending the existing CKR datalog translation.
• a study of further capabilities of algebraic measures, showing the possibilities for reasoning on model aggregation.

Tangible Outcomes

1. Program/code: Prototype – Loris Bozzato https://github.com/dkmfbk/ckrew/releases/tag/v.1.6 
2. Technical report
   https://tinyurl.com/FBK-TUW-MP-Report
3. Video presentation summarizing the project

Contact person: Holger Hoos (hh@cs.rwth-aachen.de)

Internal Partners:

1. Leiden University, Holger Hoos
2. INESC TEC, João Gama, jgama@fep.up.pt

Real world data streams are rarely stationary, but subjective to concept drift, i.e., the change of distribution of the observations. Concept drift needs to be constantly monitored, so that when the trained model is no longer adequate, a new model can be trained that fits the most recent concept. Current methods of detecting concept drift typically include monitoring the performance, and triggering a signal once this drops by a certain margin. The disadvantage of this is that this method acts retroactively, i.e., when the performance has already dropped.

The field of neural network verification detects whether a neural network is susceptible to an adversarial attack, i.e., whether a given input image can be perturbed by a given epsilon, such that the output of the network changes. This indicates that this input is close to the decision boundary. When the distribution of images that are close to the decision boundary significantly changes, this indicates that concept drift is occurring, and we can proactively (before the performance drops) retrain the model. The short-term goal of this micro-project is to define ways to a) monitor the distribution of images close to the decision boundary, and b) define control systems that can act upon this notion.

Disadvantages of this are that verifying neural networks requires significant computation time, and it will take many speed-ups before this can be utilized in high-throughput streams.

Contact person: Haris Papageorgiuo (haris@athenarc.gr)

Internal Partners:

1. ATHENA RC, Haris Papageorgiou
2. German Research Centre for Artificial Intelligence (DFKI), Julián Moreno Schneider
3. OpenAIRE, Natalia Manola

SciNoBo is a microproject focused on enhancing science communication, particularly in health and climate change topics, by integrating AI systems with science journalism. The project aims to assist science communicators—such as journalists and policymakers—by utilizing AI to identify, verify, and simplify complex scientific statements found in mass media. By grounding these statements in scientific evidence, the AI will help ensure accurate dissemination of information to non-expert audiences. This approach builds on prior work involving neuro-symbolic question-answering systems and aims to leverage advanced language models, argumentation mining, and text simplification technologies. Technologically, we build on our previous MP work on neuro-symbolic Q&A (*) and further exploit and advance recent developments in instruction fine-tuning of large language models, retrieval augmentation and natural language understanding – specifically the NLP areas of argumentation mining, claim verification and text (ie, lexical and syntactic) simplification. The proposed MP addresses the topic of “Collaborative AI” by developing an AI system equipped with innovative NLP tools that can collaborate with humans (ie, science communicators -SCs) communicating statements on Health & Climate Change topics, grounding them on scientific evidence (Interactive grounding) and providing explanations in simplified language, thus, facilitating SCs in science communication. The innovative AI solution will be tested on a real-world scenario in collaboration with OpenAIRE by employing OpenAIRE research graph (ORG) services in Open Science publications.

Results Summary

The project is divided into two phases that ran in parallel. The main focus in phase I is the construction of the data collections and the adaptations and improvements needed in PDF processing tools. Phase II deals with the development of the two subsystems: claim analysis and text simplification as well as their evaluation.

• Phase I: Two collections with News and scientific publications will be compiled in the areas of Health and Climate. The News collection will be built based on an existing dataset with News stories and ARC automated classification system in the areas of interest. The second collection with publications will be provided by OpenAIRE ORG service and further processed, managed and properly indexed by ARC SciNoBo toolkit. A small-scale annotation is foreseen by DFKI in support of the simplification subsystem.
• Phase II: We developed, fine tuned and evaluated the two subsystems. Concretely, the “claim analysis” subsystem encompasses (i) ARC previous work on “claim identification”, (ii) a retrieval engine fetching relevant scientific publications (based on our previous miniProject), and (iii) an evidence-synthesis module indicating whether the publications fetched and the scientists’ claims therein, support or refute the News claim under examination.

Tangible Outcomes

1. Kotitsas, S., Kounoudis, P., Koutli, E., & Papageorgiou, H. (2024, March). Leveraging fine-tuned Large Language Models with LoRA for Effective Claim, Claimer, and Claim Object Detection. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 2540-2554).  https://aclanthology.org/2024.eacl-long.156/ 
2. HCN dataset: news articles in the domain of Health and Climate Change. The dataset contains news articles, annotated with the major claim, claimer(s) and claim object(s). https://github.com/iNoBo/news_claim_analysis 
3. Website demo: http://scinobo.ilsp.gr:1997/services 
4. Services for claim identification and the retrieval engine http://scinobo.ilsp.gr:1997/live-demo?HFSpace=inobo-scinobo-claim-verification.hf.space 
5. Service for the text simplification http://scinobo.ilsp.gr:1997/text-simplification 

Contact person: Szymon Talaga (stalaga@uw.edu.pl) 

Internal Partners:

1. Univ. Warsaw, Szymon Talaga, stalaga@uw.edu.pl

This project builds upon another finished microproject. In this project, we continue the development of the Segram package for Python. The purpose of the package is to provide tools for automated narrative analysis of text data focused on extracting information on basic building blocks of narratives – agents (both active and passive), actions, events, or relations between agents and actions (e.g. determining subjects and objects of actions), as well as descriptions of actors, actions and events. The development process is also naturally paired with conceptual work on representations of narratives.

The package is designed as a graybox model. It is based on an opaque statistical language model providing linguistic annotations, which are subsequently used by transparent deterministic algorithms for discovering narrative elements. Thus, the final output should be easy to interpret and validate by human users, whenever necessary. Moreover, by lifting the analysis from the purely linguistic level to the arguably more intuitive level of narratives, it is hoped that the provided tools will be significantly easier to use and understand for end users, including those without training in linguistics and/or computer science.

The proposed framework is aimed at language understanding and information extraction, as opposed to language generation. Namely, the role of the package is to organize narrative information in convenient data structures allowing effective querying and deriving of various statistical descriptions. Crucially, thanks to its semi-transparent nature, the produced output should be easy to validate for human users. This should facilitate development of shared representations (corresponding the WP1 and WP2 motivated goal: „Establishing Common Ground for Collaboration with AI Systems”) of narratives, understandable for both humans and machines, that are the same time trustworthy (by being easy to validate for humans), which is arguably a desirable feature, for instance in comparison to increasingly powerful but hard-to-trust large language models. In particular, the package should be useful for facilitating and informing human-driven analyses of text data.

Alpha version of the package implementing core functionalities related to grammatical and narrative analysis is ready. The goal of the present microproject was to improve the package and release a beta version. This includes implementing an easy-to-use interface (operating at the level of narrative concepts) for end users allowing effective querying and analysis of the data produced by Segram as well as developing a comprehensive documentation. Thus, the planned release should be ready for broader adoption to a wide array of use cases and users with different levels of linguistic/computational expertise.

Results Summary

The project delivered a software Python package for narrative analysis as per the project description. The package is distributed through Python Package Index (PyPI) under a permissive open-source license (MIT) and therefore is easily accessible and free-to-use. Moreover, it comes with a detailed documentation page facilitating adoption by third-parties. It is worth noting that the advent of latest-generation large language models (LLMs) has partially limited the relevance of the project results.

Tangible Outcomes

1. Package page at Python Package Index: https://pypi.org/project/segram/ 
2. tutorial page documenting how to use the package https://segram.readthedocs.io/en/latest/ 

Contact person: Szymon Talaga, (stalaga@uw.edu.pl) 

Internal Partners:

1. Univ. Warsaw, Szymon Talaga, stalaga@uw.edu.pl
2. Institut Polytechnique de Grenoble, James Crowley, james.crowley@univ-grenoblealpes.fr

This Micro-Project has laid the groundwork for developing a new approach to narrative

analysis providing a gray-box (at least partially explainable) NLP model tailored for facilitating work of qualitative text/narrative analysts. The above goal fits into a broader HumanE-AI objective of developing common ground concepts providing better representations shared by humans and machines alike. In particular, the contribution of the project to work on aligning machine analyses with human perspective through the notion of narratives is twofold. Firstly, narrative-oriented tools for automated text analyses can empower human analysts as, arguably, the narrative framework provides a more natural and meaningful context for people without formal training in linguistics and/or computer science for reasoning about textual data. Secondly, the development of the software for narrative analysis is naturally intertwined with conceptual work on the core terms and building blocks of narratives, which can inform subsequent work on more advanced approaches. We conducted a proof-of-concept study combining existing standard NLP methods (e.g. topic modeling, entity recognition) with qualitative analysis of narratives about smart cities and related technologies and use this experience to conceptualize our approach to narrative analysis, in particular with respect to problems which are not easily solved with the existing tools.

Results Summary

The aim of the project was to develop a software package (for Python) providing easy to use and understand (also for researchers not trained in computer science or linguistics) tools for extracting narrative information (active and passive actors, the actions they perform as well as descriptions of both actors and actions, which together define events) and organizing them in rich hierarchical data structures (data model is implicitly graphical) from which subsequently different sorts of descriptive statistics can be generated depending on particular research questions. Crucially, for this to be practically possible, a legible and efficient framework for querying the produced data is needed.

Importantly, the software is developed as a graybox model, in which core low-level NLP tasks, such as POS and dependency tagging, are performed by a blackbox statistical model, and then they are transformed to higher order grammar and narrative data based on a set of transparent deterministic rules. This is to ensure high explainability of the approach, which is crucial for systems in which the machine part is supposed to be a helper of a human analyst instead of an implicit leader.

Currently, the core modules of the package responsible for the grammatical analysis are mostly ready (but several improvements are still planned). This includes also a coreference resolution module. Moreover, the core part of the semantic module, which translates grammatical information to more semantic constructs focused on actors, actions and descriptions, is also ready. What is still missing are an interface exposing methods for end users allowing easy access and analysis of rich data produced by the package as well as a principled and convenient query framework on which the interface should be based.

This is the main focus of the ongoing and future work. The second missing part is the documentation, but this part is best finished after the interface is ready. Thus, even though the package in the current state can seem a little rough from the perspective of an end user, its quality and usefulness will increase steadily as new updates are delivered.

Tangible Outcomes

1. python package providing grey box NLP model to assist qualitative analysts https://github.com/sztal/segram

Contact person: Rui Prada (rui.prada@tecnico.ulisboa.pt) 

Internal Partners:

1. Instituto Superior Técnico, Department of Computer Science,
2. Eötvös Loránd University, Department of Artificial Intelligence

External Partners:

1. DFKI Lower Saxony, Interactive Machine Learning Lab
2. Carnegie Mellon University, Robotics Institute  

The project addresses research on interactive grounding. It consists of the development of an Augmented Reality (AR) game, using HoloLens, that supports the interaction of a human player with an AI character in a mixed reality setting using gestures as the main communicative act. The game will integrate technology to perceive human gestures and poses. The game will bring about collaborative tasks that need coordination at the level of mutual understanding of the several elements of the required task. Players (human and AI) will have different information about the tasks to advance in the game and need to communicate that information to their partners through gestures. The main grounding challenge will be based on learning the mapping between gestures to the meaning of actions to perform in the game. There will be two levels of gestures toground, some are task-independent while others are task-dependent. In other words, besides the gestures that communicate explicit information about the game task, the players need to agree on the gestures used to coordinate the communication itself; for example, to signal agreement or doubt, to ask for more information, or close the communication. These latter gesture types can be transferred from task to task within the game, and probably to other contexts as well. It will be possible to play the game with two humans and study their gesture communication in order to gather the gestures that emerge: a human-inspired gesture set will be collected and serve the creation of a gesture dictionary in the AI repertoire. The game will provide different tasks of increasing difficulty. The first ones will ask the players to perform gestures or poses as mechanisms to open a door to progress to the next level. But later, in a more advanced version of the game, specific and constrained body poses, interaction with objects, and the need to communicate more abstract concepts (e.g., next to, under, to the right, the biggest one, …) will be introduced. The game will be built as a platform to perform studies. It will support studying diverse questions about the interactive grounding of gestures. For example, we can study the way people adapt to and ascribe meaning to the gestures performed by the AI agent, we can study how different gesture profiles influence the people’s interpretation, facilitate grounding, and have an impact on the performance of the tasks, or we can study different mechanisms on the AI to learn its gesture repertoire from humans (e.g., by imitation grounded on the context).

Results Summary

An AR game, where players face a sequence of codebreaking challenges that require them to press some buttons in a specific sequence, however, only one of the partners has access to the buttons while the other has access to the solution code. The core gameplay is centred on the communication between the two partners (AI and virtual agent), which must be performed only by using gestures. In addition, to the development of the AR game, we developed some sample AI agents that are able to play with a human player. A version using an LLM was also developed to provide some reasoning for gesture recognition and performance by the AI virtual agent.

Players face a sequence of codebreaking challenges that require them to press some buttons in a specific sequence, however, only one of the partners has access to the buttons while the other has access to the solution code. Furthermore, only gesture communication if possible. Therefore, the core gameplay is centred on the communication between the two partners (AI and virtual agent). Gestures supported in the game are split into two distinct subtypes:

1. Taskwork gestures: Used for conveying information about the game’s tasks and environment (e.g., an object’s colour).
2. Teamwork gestures: Used for giving feedback regarding communication (e.g., affirming that a gesture was understood).

The gameplay loop implies shared performance coordination and communication.

In the current version, the virtual agent is able to play reactively in response to the player’s gestures based on a gesture knowledge base that assigns meaning and action to each gesture. A version using an LLM was also developed to provide some reasoning for gesture recognition and performance by the AI virtual agent.

Tangible Outcomes

1. The base game – https://github.com/badomate/EscapeHololens 
2. The extended game – https://github.com/badomate/EscapeMain 
3. A presentation summarizing the project: https://www.youtube.com/watch?v=WmuWaNdIpcQ
4. A short demo for the system https://youtu.be/j_bAw8e0lNU?si=STi6sbLzbpknckGG

Contact person: Fernando Martin Maroto, (Algebraic AI) (martin.maroto@algebraic.ai) 

Internal Partners:

1. Algebraic, Fernando Martin
2. Christian Weis (Technische Universität Kaiserslautern)  

Algebraic Machine Learning (AML) offers new opportunities in terms of transparency and control. However, that comes along with many challenges regarding software and hardware implementations. To understand the hardware needs of this new method it is essential to analyze the algorithm and its computational complexity. With this understanding, the final goal of this microproject is to investigate the feasibility of various hardware options particularly in-memory processing hardware acceleration for AML.

Results Summary

Sparse Crossing is a machine learning algorithm based on algebraic semantic embeddings. The goal of the collaboration is to first understand the needs and computational complexity of Sparse Crossing and then perform a feasibility analysis of various hardware options for an efficient implementation of the algorithm. Particularly, in-memory processing hardware acceleration and FPGA-based implementations have been considered. A report, and a FPGA based prototype has been developed (currently under patent).

Contact person: John Shawe-Taylor, UCL (j.shawe-taylor@ucl.ac.uk) 

Internal Partners:

1. University College London í(UCL), John Shawe-Taylor
2. Institut “Jožef Stefan” (JSI), John Shawe-Taylor
3. INESC TEC, Alipio Jorge  

Through this work, we explore novel and advanced learner representation models aimed at exploiting learning trajectories to build a transparent, personalised and efficient automatic learning tutor through resource recommendations. We elaborate on the different types of publicly available data sources that can be used to build an accurate trajectory graph of how knowledge should be taught to learners to fulfil their learning goals effectively. Our aim is to capture and utilise the inferred learner state and the understanding the model has about sensible learning trajectories to generate personalised narratives that will allow the system to rationalise the educational recommendations provided to individual learners. Since an educational path consists heavily of building/following a narrative, a properly constructed narrative structure and representation is paramount to the problem of building successful and transparent educational recommenders.

Results Summary

Adding humanly-intuitive model assumptions to the TrueLearn Bayesian learner model such as 1) interest, 2) knowledge of learner 3) semantic relatedness between content topics has been achieved successfully leading to improved predictive performance. A dataset of personalised learning pathways of over 20000 learners has been composed. Analysis on Optimal Transport for generating interpretable narratives using Earth Mover’s Distance (EMD) of Wikipedia concepts also showed promise in scenarios where there is a limited number of topic annotations per document. A novel method for cross-lingual information retrieval using EMD has been invented pursuing this idea. Incorporating semantic networks (WordNet, WikiData) in building higher-level reasoning for recommendation also shows promise albeit with limited results at this point. Successful expansion of WordNet network using WikiData network is achieved. The resultant semantic network indicates that the quality of reasoning over Wiki Annotated video lectures can be improved in this way.

Tangible Outcomes

1. X5Learn: A Personalised Learning Companion at the Intersection of AI and HCI – Maria Perez-Ortiz. https://dl.acm.org/doi/10.1145/3397482.3450721  
2. “Why is a document relevant? Understanding the relevance scores in cross-lingual document retrieval.” Novak, Erik, Luka Bizjak, Dunja Mladenić, and Marko Grobelnik. Knowledge-Based Systems 244 (2022): 108545. https://dl.acm.org/doi/10.1016/j.knosys.2022.108545
3. Towards an Integrative Educational Recommender for Lifelong Learners (Student Abstract). Sahan Bulathwela,  María Pérez-Ortiz, Emine Yilmaz, and John Shawe-Taylor. (2020, April). In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 34, No. 10, pp. 13759-13760). https://ojs.aaai.org/index.php/AAAI/article/view/7151/7005
4. “TrueLearn: A Python Library for Personalised Informational Recommendations with (Implicit) Feedback.” Yuxiang Qiu,  Karim Djemili, Denis Elezi, Aaneel Shalman, María Pérez-Ortiz, and Sahan Bulathwela.  arXiv preprint arXiv:2309.11527 (2023). Published through ORSUM workshop, RecSys’23 https://arxiv.org/pdf/2309.11527
5. “Peek: A large dataset of learner engagement with educational videos.” Bulathwela, Sahan, Maria Perez-Ortiz, Erik Novak, Emine Yilmaz, and John Shawe-Taylor.  arXiv preprint arXiv:2109.03154 (2021). Submitted to ORSUM workshop, RecSys’21 https://arxiv.org/abs/2109.03154
6. Dataset: PEEK Dataset – Sahan Bulathwela https://github.com/sahanbull/PEEK-Dataset
7. Program/code: TrueLearn Model – Sahan Bulathwela https://github.com/sahanbull/TrueLearn
8. Program/code: Semantic Networks for Narratives – Daniel Loureiro https://github.com/danlou/mp_narrative

Contact person: Mohamed Chetouani (mohamed.chetouani@sorbonne-universite.fr) 

Internal Partners:

1. ISIR, Sorbonne University, Mohamed Chetouani, Silvia Tulli
2. Vrije Universiteit Amsterdam, Kim Baraka  

Human-Interactive Robot Learning (HIRL) is an area of robotics that focuses on developing robots that can learn from and interact with humans. This educational module aims to cover the basic principles and techniques of Human-Interactive Robot Learning. This interdisciplinary module will encourage graduate students (Master/PhD level) to connect different bodies of knowledge within the broad field of Artificial Intelligence, with insights from Robotics, Machine Learning, Human Modelling, and Design and Ethics. The module is meant for Master’s and PhD students in STEM, such as Computer Science, Artificial Intelligence, and Cognitive Science. This work will extend the tutorial presented in the context of the International Conference on Algorithms, Computing, and Artificial Intelligence (ACAI 2021) and will be shared with the Artificial Intelligence Doctoral Academy (AIDA). Moreover, the proposed lectures and assignments will be used as teaching material at Sorbonne University, and Vrije Universiteit Amsterdam. We plan to design a collection of approximately 12 1.5-hour lectures, 5 assignments, and a list of recommended readings, organized along relevant topics surrounding HIRL. Each lecture will include an algorithmic part and a practical example of how to integrate such an algorithm into an interactive system. The assignments will encompass the replication of existing algorithms with the possibility for the student to develop their own alternative solutions. Proposed module contents (each lecture approx. 1.5 hour): (1) Interactive Machine Learning vs Machine Learning – 1 lecture, (2) Interactive Machine Learning vs Interactive Robot Learning (Embodied vs non-embodied agents) – 1 lecture, (3) Fundamentals of Reinforcement Learning – 2 lectures, (4) Learning strategies: observation, demonstration, instruction, or feedback- Imitation Learning, Learning from Demonstration – 2 lectures- Learning from Human Feedback: evaluative, descriptive, imperative, contrastive examples – 3 lectures, (5) Evaluation metrics and benchmarks – 1 lecture, (6) Application scenarios: hands-on session – 1 lecture, and (7) Design and ethical considerations – 1 lecture.

Contact person: Chiara Ghidini (ghidini@fbk.eu) 

Internal Partners:

1. University of Bologna, Federico Chesani, fchesani@gmail.com

External Partners:

1. Free University of Bozen-Bolzano, Sergio Tessaris, tessaris@inf.unibz.it

Making sense of data is a main challenge in creating human understandable descriptions of complex situations. When data refer to process executions, techniques exist that discover explicit descriptions in terms of formal models. Many research works envisage the discovery task as a one-class supervised learning job. Work on deviance mining highlighted nonetheless the need to characterise behaviours that exhibit certain characteristics and forbid others (e.g., the slower, less frequent), leading to the quest for a binary supervised learning task.In this microproject we focus on the discovery of declarative process models, expressed through Linear Time Temporal Logic, as a binary supervised learning task, where the input log reports both positive and negative behaviours. We therefore investigate how valuable information can be extracted and formalised into an “optimal” model, according to user- preferences (e.g., model generality or simplicity). By iteratively including further examples, the user can also refine the discovered models

Results Summary

The micro-project has produced three main results:

1. A two-step approach for the discovery of temporal-logic patterns as a binary supervised learning problem, that is starting from a set of “positive traces” (execution traces whose behaviour we want to observe in the discovered patterns), and a set of “negative traces” (execution traces whose behaviour we do not want to observe in the discovered patterns). In detail, in the first step, sets of patterns (possible models) that accept all positive traces and discard as much as possible of the negative ones are discovered. In the second step, the model(s) optimizing one criterion, as for instance the generality or the simplicity, are selected among the possible discovered models.
2. Two synthetic labelled (“positive” and “negative”) event log datasets used for the synthetic evaluation of the proposed approach.
3. A paper describing the approach, as well as the approach evaluation.

Tangible Outcomes

1. Chesani, F., Francescomarino, C. D., Ghidini, C., Grundler, G., Loreti, D., Maggi, F. M., Mello, P., Montali, M., and Tessaris, S. (2022). Shape your process: Discovering declarative business processes from positive and negative traces taking into account user preferences. In Almeida, J. P. A., Karastoyanova, D., Guizzardi, G., Montali, M., Maggi, F. M., and Fonseca, C. M., editors, Enterprise Design, Operations, and Computing – 26th International Conference, EDOC 2022, Bozen-Bolzano, Italy, October 3-7, 2022, Proceedings, volume 13585 of Lecture Notes in Computer Science, pages 217–234. Springer. https://dl.acm.org/doi/10.1007/978-3-031-17604-3_13 
2. Chesani, F., Francescomarino, C. D., Ghidini, C., Loreti, D., Maggi, F. M., Mello, P., Montali, M., and Tessaris, S. (2022). Process discovery on deviant traces and other stranger things. IEEE Transactions on Knowledge and Data Engineering, pages 1–17. DOI: https://doi.org/10.1109/TKDE.2022.3232207 https://ieeexplore.ieee.org/document/9999331
3. Loan Approval1: dataset. https://drive.google.com/drive/folders/15BwG4PJq8iIMh9Sr9dpMXAYBYqp7QDE?usp=sharing
4. Loan Approval2: dataset. https://drive.google.com/drive/folders/1fcJ8itzdMbNOjEAeV6nUEeI5B6__aB_c?usp=sharing
5. Discovery Framework (program/code): https://zenodo.org/records/5158528 
6. Experiments: https://github.com/stessaris/negdis-experiments/tree/v1.0 

Contact person:  Mehdi Khamassi (mehdi.khamassi@sorbonne-universite.fr) 

Internal Partners:

1. Sorbonne University, Mehdi Khamassi, mehdi.khamassi@sorbonne-universite.fr
2. ATHINA Research Center, Petros Maragos, maragos@cs.ntua.gr

This project entails robot online behavioral adaptation during interactive learning with humans. Specifically, the robot shall adapt to each human subject’s specific way of giving feedback during the interaction. Feedback here includes reward, instruction and demonstration, and can be regrouped under the term “teaching signals”. For example, some human subjects prefer a proactive robot while others prefer the robot to wait for their instructions; some only tell the robot when it performs a wrong action, while others reward correct actions, etc. The main outcome is a new ensemble method of human-robot interaction which can learn models of various human feedback strategies and use them for online tuning of reinforcement learning so that the robot can quickly learn an appropriate behavioral policy. We first derive an optimal solution to the problem and then compare the empirical performance of ensemble methods to this optimum through a set of numerical simulations.

Results Summary

We designed a new ensemble learning algorithm, combining model-based and model-free reinforcement learning, for on-the-fly robot adaptation during human-robot interaction. The algorithm includes a mechanism for the robot to autonomously detect changes in a human’s reward function from its observed behavior, and a reset of the ensemble learning accordingly. We simulated a series of human-robot interaction scenarios to test the robustness of the algorithm. In scenario 1, the human rewards the robot with various feedback profiles: stochastic reward; non-monotonic reward; or punishing for error without rewarding correct responses. In scenario 2, the humans teach the robot through demonstrations, again with different degrees of stochasticity and levels of expertise from the human. In scenario 3, we simulated a human-robot cooperation task for putting a set of cubes in the right box. The task includes abrupt changes in the target box. Results show the generality of the algorithm. Humans and robots are doomed to cooperate more and more within the society. This micro-project addresses a major AI challenge to enable robots to adapt on-the-fly to different situations and to different more-or-less naive human users. The solution consists of designing a robot learning algorithm which generalizes to a variety of simple human robot interaction scenarios. Following the HumanE AI vision, interactive learning puts the human in the loop, prompting human-aware robot behavioral adaptation.

Tangible Outcomes

1.  Rémi Dromnelle, Erwan Renaudo, Benoît Girard, Petros Maragos, Mohamed Chetouani, Raja Chatila, Mehdi Khamassi (2022). Reducing computational cost during robot navigation and human-robot interaction with a human-inspired reinforcement learning architecture. International Journal of Social Robotics, doi: 10.1007/s12369-022-00942-6 Preprint made open on HAL – https://hal.sorbonne-universite.fr/hal03829879
2. Open source code: https://github.com/DromnHell/meta-control-decision-making-agent