Demo Publications

@inproceedings{eps375287,

title = {Real-time opinion aggregation methods for crowd robotics},

author = {Elliot Salisbury and Sebastian Stein and Sarvapali Ramchurn},

url = {http://eprints.soton.ac.uk/375287/},

year  = {2015},

date = {2015-01-01},

booktitle = {Autonomous Agents and Multiagent Systems (AAMAS 2015)},

abstract = {Unmanned Aerial Vehicles (UAVs) are increasingly becoming instrumental to many commercial applications, such as transportation and maintenance. However, these applications require flexibility, understanding of natural language, and comprehension of video streams that cannot currently be automated and instead require the intelligence of a skilled human pilot. While having one pilot individually supervising a UAV is not scalable, the machine intelligence, especially vision, required to operate a UAV is still inadequate. Hence, in this paper, we consider the use of crowd robotics to harness a real-time crowd to orientate a UAV in an unknown environment. In particular, we present two novel real-time crowd input aggregation methods. To evaluate these methods, we develop a new testbed for crowd robotics, called CrowdDrone, that allows us to evaluate crowd robotic systems in a variety of scenarios. Using this platform, we benchmark our real-time aggregation methods with crowds hired from Amazon Mechanical Turk and show that our techniques outperform the current state-of-the-art aggregation methods, enabling a robotic agent to travel faster across a fixed distance, and with more precision. Furthermore, our aggregation methods are shown to be significantly more effective in dynamic scenarios},

keywords = {crowdsourcing, uav},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{eps374070,

title = {HAC-ER: A disaster response system based on human-agent collectives},

author = {Sarvapali Ramchurn and Edwin Simpson and Joel Fischer and Trung Dong Huynh and Yuki Ikuno and Steven Reece and Wenchao Jiang and Feng Wu and Jack Flann and S. J. Roberts and Luc Moreau and T. Rodden and N. R. Jennings},

url = {http://eprints.soton.ac.uk/374070/},

year  = {2015},

date = {2015-01-01},

booktitle = {14th International Conference on Autonomous Agents and Multi-Agent Systems},

abstract = {This paper proposes a novel disaster management system called HAC-ER that addresses some of the challenges faced by emer- gency responders by enabling humans and agents, using state-of- the-art algorithms, to collaboratively plan and carry out tasks in teams referred to as human-agent collectives. In particular, HAC- ER utilises crowdsourcing combined with machine learning to ex- tract situational awareness information from large streams of re- ports posted by members of the public and trusted organisations. We then show how this information can inform human-agent teams in coordinating multi-UAV deployments as well as task planning for responders on the ground. Finally, HAC-ER incorporates a tool for tracking and analysing the provenance of information shared across the entire system. In summary, this paper describes a pro- totype system, validated by real-world emergency responders, that combines several state-of-the-art techniques for integrating humans and agents, and illustrates, for the first time, how such an approach can enable more effective disaster response operations.},

keywords = {Coordination, crowdsourcing, human-agent collectives, human-agent interaction, multi-agent systems, uav},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{eps375287,

title = {Real-time opinion aggregation methods for crowd robotics},

author = {Elliot Salisbury and Sebastian Stein and Sarvapali Ramchurn},

url = {http://eprints.soton.ac.uk/375287/},

year  = {2015},

date = {2015-01-01},

booktitle = {Autonomous Agents and Multiagent Systems (AAMAS 2015)},

abstract = {Unmanned Aerial Vehicles (UAVs) are increasingly becoming instrumental to many commercial applications, such as transportation and maintenance. However, these applications require flexibility, understanding of natural language, and comprehension of video streams that cannot currently be automated and instead require the intelligence of a skilled human pilot. While having one pilot individually supervising a UAV is not scalable, the machine intelligence, especially vision, required to operate a UAV is still inadequate. Hence, in this paper, we consider the use of crowd robotics to harness a real-time crowd to orientate a UAV in an unknown environment. In particular, we present two novel real-time crowd input aggregation methods. To evaluate these methods, we develop a new testbed for crowd robotics, called CrowdDrone, that allows us to evaluate crowd robotic systems in a variety of scenarios. Using this platform, we benchmark our real-time aggregation methods with crowds hired from Amazon Mechanical Turk and show that our techniques outperform the current state-of-the-art aggregation methods, enabling a robotic agent to travel faster across a fixed distance, and with more precision. Furthermore, our aggregation methods are shown to be significantly more effective in dynamic scenarios},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{eps374070,

title = {HAC-ER: A disaster response system based on human-agent collectives},

author = {Sarvapali Ramchurn and Edwin Simpson and Joel Fischer and Trung Dong Huynh and Yuki Ikuno and Steven Reece and Wenchao Jiang and Feng Wu and Jack Flann and S. J. Roberts and Luc Moreau and T. Rodden and N. R. Jennings},

url = {http://eprints.soton.ac.uk/374070/},

year  = {2015},

date = {2015-01-01},

booktitle = {14th International Conference on Autonomous Agents and Multi-Agent Systems},

abstract = {This paper proposes a novel disaster management system called HAC-ER that addresses some of the challenges faced by emer- gency responders by enabling humans and agents, using state-of- the-art algorithms, to collaboratively plan and carry out tasks in teams referred to as human-agent collectives. In particular, HAC- ER utilises crowdsourcing combined with machine learning to ex- tract situational awareness information from large streams of re- ports posted by members of the public and trusted organisations. We then show how this information can inform human-agent teams in coordinating multi-UAV deployments as well as task planning for responders on the ground. Finally, HAC-ER incorporates a tool for tracking and analysing the provenance of information shared across the entire system. In summary, this paper describes a pro- totype system, validated by real-world emergency responders, that combines several state-of-the-art techniques for integrating humans and agents, and illustrates, for the first time, how such an approach can enable more effective disaster response operations.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}