@inproceedings{soton478647,
title = {Multi-agent signal-less intersection management with dynamic platoon formation},
author = {Phuriwat Worrawichaipat and Enrico Gerding and Ioannis Kaparias and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/478647/},
year = {2023},
date = {2023-05-01},
booktitle = {22nd International Conference on Autonomous Agents and Multiagent Systems (29/05/23 - 02/06/23)},
pages = {1542--1550},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
@misc{soton477553,
title = {AI Foundation Models: initial review, CMA Consultation, TAS Hub Response},
author = {Joshua Krook and Derek McAuley and Stuart Anderson and John Downer and Peter Winter and Sarvapali D Ramchurn},
url = {https://eprints.soton.ac.uk/477553/},
year = {2023},
date = {2023-06-01},
publisher = {University of Southampton},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
@inproceedings{soton479970,
title = {The effect of data visualisation quality and task density on human-swarm interaction},
author = {Ayodeji Abioye and Mohammad Naiseh and William Hunt and Jediah R Clark and Sarvapali D Ramchurn and Mohammad Soorati},
url = {https://eprints.soton.ac.uk/479970/},
year = {2023},
date = {2023-06-01},
booktitle = {Proceedings of the 2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)},
publisher = {IEEE},
abstract = {Despite the advantages of having robot swarms, human supervision is required for real-world applications. The performance of the human-swarm system depends on several factors including the data availability for the human operators. In this paper, we study the human factors aspect of the human-swarm interaction and investigate how having access to high-quality data can affect the performance of the human-swarm system - the number of tasks completed and the human trust level in operation. We designed an experiment where a human operator is tasked to operate a swarm to identify casualties in an area within a given time period. One group of operators had the option to request high-quality pictures while the other group had to base their decision on the available low-quality images. We performed a user study with 120 participants and recorded their success rate (directly logged via the simulation platform) as well as their workload and trust level (measured through a questionnaire after completing a human-swarm scenario). The findings from our study indicated that the group granted access to high-quality data exhibited an increased workload and placed greater trust in the swarm, thus confirming our initial hypothesis. However, we also found that the number of accurately identified casualties did not significantly vary between the two groups, suggesting that data quality had no impact on the successful completion of tasks.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Autonomous swarms of robots can bring robustness, scalability and adaptability to safety-critical tasks such as search and rescue but their application is still very limited. Using semi-autonomous swarms with human control can bring robot swarms to real-world applications. Human operators can define goals for the swarm, monitor their performance and interfere with, or overrule, the decisions and behaviour. We present the "Human And Robot Interactive Swarm'' simulator (HARIS) that allows multi-user interaction with a robot swarm and facilitates qualitative and quantitative user studies through simulation of robot swarms completing tasks, from package delivery to search and rescue, with varying levels of human control. In this demonstration, we showcase the simulator by using it to study the performance gain offered by maintaining a "human-in-the-loop'' over a fully autonomous system as an example. This is illustrated in the context of search and rescue, with an autonomous allocation of resources to those in need.
https://eprints.soton.ac.uk/479903/
@inproceedings{soton479903,
title = {Demonstrating performance benefits of human-swarm teaming},
author = {William Hunt and Jack Ryan and Ayodeji O Abioye and Sarvapali D Ramchurn and Mohammad D Soorati},
url = {https://eprints.soton.ac.uk/479903/},
year = {2023},
date = {2023-05-01},
booktitle = {Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems},
pages = {3062--3064},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)},
abstract = {Autonomous swarms of robots can bring robustness, scalability and adaptability to safety-critical tasks such as search and rescue but their application is still very limited. Using semi-autonomous swarms with human control can bring robot swarms to real-world applications. Human operators can define goals for the swarm, monitor their performance and interfere with, or overrule, the decisions and behaviour. We present the "Human And Robot Interactive Swarm'' simulator (HARIS) that allows multi-user interaction with a robot swarm and facilitates qualitative and quantitative user studies through simulation of robot swarms completing tasks, from package delivery to search and rescue, with varying levels of human control. In this demonstration, we showcase the simulator by using it to study the performance gain offered by maintaining a "human-in-the-loop'' over a fully autonomous system as an example. This is illustrated in the context of search and rescue, with an autonomous allocation of resources to those in need.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The proliferation of ?Things? over a network creates the Internet of Things (IoT), where sensors integrate to collect data from the environment over long periods of time. The growth of IoT applications will inevitably involve co-locating multiple wireless sensor networks, each serving different applications with, possibly, different needs and constraints. Since energy is scarce in sensor nodes equipped with non-rechargeable batteries, energy harvesting technologies have been the focus of research in recent years. However, new problems arise as a result of their wide spatio-temporal variation. Such a shortcoming can be avoided if co-located networks cooperate with each other and share their available energy. Due to their unique characteristics and different owners, recently, we proposed a negotiation approach to deal with conflict of preferences. Unfortunately, negotiation can be impractical with a large number of participants, especially in an open environment. Given this, we introduce a new partner selection technique based on multi-armed bandits (MAB), that enables each node to learn the strategy that optimises its energy resources in the long term. Our results show that the proposed solution allows networks to repeatedly learn the current best energy partner in a dynamic environment. The performance of such a technique is evaluated through simulation and shows that a network can achieve an efficiency of 72% against the optimal strategy in the most challenging scenario studied in this work.
https://eprints.soton.ac.uk/445733/
@article{soton445733,
title = {Partner selection in self-organised wireless sensor networks for opportunistic energy negotiation: A multi-armed bandit based approach},
author = {Andre P Ortega and Sarvapali Ramchurn and Long Tran-Thanh and Geoff Merrett},
url = {https://eprints.soton.ac.uk/445733/},
year = {2021},
date = {2021-03-01},
journal = {Ad Hoc Networks},
volume = {112},
abstract = {The proliferation of ?Things? over a network creates the Internet of Things (IoT), where sensors integrate to collect data from the environment over long periods of time. The growth of IoT applications will inevitably involve co-locating multiple wireless sensor networks, each serving different applications with, possibly, different needs and constraints. Since energy is scarce in sensor nodes equipped with non-rechargeable batteries, energy harvesting technologies have been the focus of research in recent years. However, new problems arise as a result of their wide spatio-temporal variation. Such a shortcoming can be avoided if co-located networks cooperate with each other and share their available energy. Due to their unique characteristics and different owners, recently, we proposed a negotiation approach to deal with conflict of preferences. Unfortunately, negotiation can be impractical with a large number of participants, especially in an open environment. Given this, we introduce a new partner selection technique based on multi-armed bandits (MAB), that enables each node to learn the strategy that optimises its energy resources in the long term. Our results show that the proposed solution allows networks to repeatedly learn the current best energy partner in a dynamic environment. The performance of such a technique is evaluated through simulation and shows that a network can achieve an efficiency of 72% against the optimal strategy in the most challenging scenario studied in this work.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
To develop and effectively deploy Trustworthy Autonomous Systems (TAS), we face various social, technological, legal, and ethical challenges in which different notions of responsibility can play a key role. In this work, we elaborate on these challenges, discuss research gaps, and show how the multidimensional notion of responsibility can play a key role to bridge them. We argue that TAS requires operational tools to represent and reason about the responsibilities of humans as well as AI agents.
https://eprints.soton.ac.uk/446459/
@inproceedings{soton446459,
title = {Responsibility ascription in trustworthy autonomous systems},
author = {Vahid Yazdanpanah and Enrico H Gerding and Sebastian Stein and Mehdi Dastani and Catholijn M Jonker and Timothy J Norman and Sarvapali D Ramchurn},
url = {https://eprints.soton.ac.uk/446459/},
year = {2021},
date = {2021-02-01},
booktitle = {Embedding AI in Society (18/02/21 - 19/02/21)},
abstract = {To develop and effectively deploy Trustworthy Autonomous Systems (TAS), we face various social, technological, legal, and ethical challenges in which different notions of responsibility can play a key role. In this work, we elaborate on these challenges, discuss research gaps, and show how the multidimensional notion of responsibility can play a key role to bridge them. We argue that TAS requires operational tools to represent and reason about the responsibilities of humans as well as AI agents.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we present a new application-focused benchmark dataset and results from a set of baseline Natural Language Processing and Machine Learning models for prediction of match outcomes for games of football (soccer). By doing so we give a baseline for the prediction accuracy that can be achieved exploiting both statistical match data and contextual articles from human sports journalists. Our dataset is focuses on a representative time-period over 6 seasons of the English Premier League, and includes newspaper match previews from The Guardian. The models presented in this paper achieve an accuracy of 63.18% showing a 6.9% boost on the traditional statistical methods.
https://eprints.soton.ac.uk/445607/
@inproceedings{soton445607,
title = {Combining machine learning and human experts to predict match outcomes in football: A baseline model},
author = {Ryan James Beal and Stuart Middleton and Timothy Norman and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/445607/},
year = {2021},
date = {2021-02-01},
booktitle = {The Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (02/02/21 - 09/02/21)},
abstract = {In this paper, we present a new application-focused benchmark dataset and results from a set of baseline Natural Language Processing and Machine Learning models for prediction of match outcomes for games of football (soccer). By doing so we give a baseline for the prediction accuracy that can be achieved exploiting both statistical match data and contextual articles from human sports journalists. Our dataset is focuses on a representative time-period over 6 seasons of the English Premier League, and includes newspaper match previews from The Guardian. The models presented in this paper achieve an accuracy of 63.18% showing a 6.9% boost on the traditional statistical methods.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
ensuremathWe present a novel approach to the management of notifications from devices in a healthcare setting. We employ a distributed constraint optimisation (DCOP) approach to the delivery of notification for healthcare assistants that aims to preserve the privacy of patients while reducing the intrusiveness of such notifications. Our approach reduces the workload of the assistants and improves patient safety by automating task allocation while ensuring high priority needs are addressed in a timely manner. We propose and evaluate several DCOP models both in simulation and in real-world deployments. Our models are shown to be efficient both in terms of computation and communication costs.ensuremath
https://eprints.soton.ac.uk/447983/
@inproceedings{soton447983,
title = {Decentralised control of intelligent devices: a healthcare facility study},
author = {Sacha Lhopital and Samir Aknine and Sarvapali Ramchurn and Vincent Thavonekham and Huan Vu},
editor = {Nick Bassiliades and Georgios Chalkiadakis and Dave de Jonge},
url = {https://eprints.soton.ac.uk/447983/},
year = {2021},
date = {2021-01-01},
booktitle = {Multi-Agent Systems and Agreement Technologies - 17th European Conference, EUMAS 2020, and 7th International Conference, AT 2020, Revised Selected Papers},
volume = {12520 LNAI},
pages = {20--36},
publisher = {Springer},
abstract = {ensuremathWe present a novel approach to the management of notifications from devices in a healthcare setting. We employ a distributed constraint optimisation (DCOP) approach to the delivery of notification for healthcare assistants that aims to preserve the privacy of patients while reducing the intrusiveness of such notifications. Our approach reduces the workload of the assistants and improves patient safety by automating task allocation while ensuring high priority needs are addressed in a timely manner. We propose and evaluate several DCOP models both in simulation and in real-world deployments. Our models are shown to be efficient both in terms of computation and communication costs.ensuremath},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we present a novel approach for optimising long-term tactical and strategic decision-making in football (soccer) by encapsulating events in a league environment across a given time frame. ensuremath We model the teams' objectives for a season and track how these evolve as games unfold to give a fluent objective that can aid in decision-making games. We develop Markov chain Monte Carlo and deep learning-based algorithms that make use of the fluent objectives in order to learn from prior games and other games in the environment and increase the teams? long-term performance. Simulations of our approach using real-world datasets from 760 matches shows that by using optimised tactics with our fluent objective and prior games, we can on average increase teams mean expected finishing distribution in the league by up to 35.6%.
https://eprints.soton.ac.uk/449655/
@inproceedings{soton449655,
title = {Optimising long-term outcomes using real-world fluent objectives: an application to football},
author = {James Beal Ryan and Georgios Chalkiadakis and Timothy Norman and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/449655/},
year = {2021},
date = {2021-01-01},
booktitle = {20th International Conference on Autonomous Agents and Multiagent Systems (03/05/21 - 07/05/21)},
pages = {196--204},
abstract = {In this paper, we present a novel approach for optimising long-term tactical and strategic decision-making in football (soccer) by encapsulating events in a league environment across a given time frame. ensuremath
We model the teams' objectives for a season and track how these evolve as games unfold to give a fluent objective that can aid in decision-making games. We develop Markov chain Monte Carlo and deep learning-based algorithms that make use of the fluent objectives in order to learn from prior games and other games in the environment and increase the teams? long-term performance. Simulations of our approach using real-world datasets from 760 matches shows that by using optimised tactics with our fluent objective and prior games, we can on average increase teams mean expected finishing distribution in the league by up to 35.6%.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Objectively quantifying the value of player actions in football (soccer) is a challenging problem. To date, studies in football analytics have mainly focused on the attacking side of the game, while there has been less work on event-driven metrics for valuing defensive actions (e.g., tackles and interceptions). Therefore in this paper, we use deep learning techniques to define a novel metric that values such defensive actions by studying the threat of passages of play that preceded them. By doing so, we are able to value defensive actions based on what they prevented from happening in the game. Our Defensive Action Expected Threat (DAxT) model has been validated using real-world event-data from the 2017/2018 and 2018/2019 English Premier League seasons, and we combine our model outputs with additional features to derive an overall rating of defensive ability for players. Overall, we find that our model is able to predict the impact of defensive actions allowing us to better value defenders using event-data.
https://eprints.soton.ac.uk/449656/
@inproceedings{soton449656,
title = {What happened next? Using deep learning to value defensive actions in football event-data},
author = {Charbel Merhej and James Beal Ryan and Tim Matthews and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/449656/},
year = {2021},
date = {2021-01-01},
booktitle = {KDD 2021 (14/08/21 - 18/08/21)},
pages = {3394--3403},
abstract = {Objectively quantifying the value of player actions in football (soccer) is a challenging problem. To date, studies in football analytics have mainly focused on the attacking side of the game, while there has been less work on event-driven metrics for valuing defensive actions (e.g., tackles and interceptions). Therefore in this paper, we use deep learning techniques to define a novel metric that values such defensive actions by studying the threat of passages of play that preceded them. By doing so, we are able to value defensive actions based on what they prevented from happening in the game. Our Defensive Action Expected Threat (DAxT) model has been validated using real-world event-data from the 2017/2018 and 2018/2019 English Premier League seasons, and we combine our model outputs with additional features to derive an overall rating of defensive ability for players. Overall, we find that our model is able to predict the impact of defensive actions allowing us to better value defenders using event-data.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper outlines a novel approach to optimising teams for Daily Fantasy Sports (DFS) contests. To this end, we propose a number of new models and algorithms to solve the team formation problems posed by DFS. Specifically, we focus on the National Football League (NFL) and predict the performance of real-world players to form the optimal fantasy team using mixed-integer programming. We test our solutions using real-world data-sets from across four seasons (2014-2017). We highlight the advantage that can be gained from using our machine-based methods and show that our solutions outperform existing benchmarks, turning a profit in up to 81.3% of DFS game-weeks over a season
https://eprints.soton.ac.uk/445995/
@article{soton445995,
title = {Optimising daily fantasy sports teams with artificial intelligence},
author = {Ryan James Beal and Timothy Norman and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/445995/},
year = {2020},
date = {2020-12-01},
journal = {International Journal of Computer Science in Sport},
volume = {19},
number = {2},
abstract = {This paper outlines a novel approach to optimising teams for Daily Fantasy Sports (DFS) contests. To this end, we propose a number of new models and algorithms to solve the team formation problems posed by DFS. Specifically, we focus on the National Football League (NFL) and predict the performance of real-world players to form the optimal fantasy team using mixed-integer programming. We test our solutions using real-world data-sets from across four seasons (2014-2017). We highlight the advantage that can be gained from using our machine-based methods and show that our solutions outperform existing benchmarks, turning a profit in up to 81.3% of DFS game-weeks over a season},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this paper, we critically evaluate the performance of nine machine learning classification techniques when applied to the match outcome prediction problem presented by American Football. Specifically, we implement and test nine techniques using real-world datasets of 1280 games over 5 seasons from the National Football League (NFL). We test the nine different classifier techniques using a total of 42 features for each team and we find that the best performing algorithms are able to improve one previous published works. The algoriothms achieve an accuracy of between 44.64% for a Guassian Process classifier to 67.53% with a Na"ive Bayes classifer. We also test each classifier on a year by year basis and compare our results to those of the bookmakers and other leading academic papers.
https://eprints.soton.ac.uk/446078/
@article{soton446078,
title = {A critical comparison of machine learning classifiers to predict match outcomes in the NFL},
author = {Ryan James Beal and Timothy Norman and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/446078/},
year = {2020},
date = {2020-12-01},
journal = {International Journal of Computer Science in Sport},
volume = {19},
number = {2},
abstract = {In this paper, we critically evaluate the performance of nine machine learning classification techniques when applied to the match outcome prediction problem presented by American Football. Specifically, we implement and test nine techniques using real-world datasets of 1280 games over 5 seasons from the National Football League (NFL). We test the nine different classifier techniques using a total of 42 features for each team and we find that the best performing algorithms are able to improve one previous published works. The algoriothms achieve an accuracy of between 44.64% for a Guassian Process classifier to 67.53% with a Na"ive Bayes classifer. We also test each classifier on a year by year basis and compare our results to those of the bookmakers and other leading academic papers.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Filter