Human-machine Systems

The semantic level in HMS design (ECCE-2010 Delf)

by Michael May

Michael May: The Semantic Level in HMS Design:Constraints, Scale Types and Representational Forms. Paper presented at the 28th Annual European Conference on Cognitive Ergonomics, August 25 - 27, 2010, Delft University.
Proceedings published by ACM.

Scale transformations and information presentation in supervisory control (IJHCS2006)

by Michael May

Johannes Petersen & Michael May: Scale transformations and information presentation in supervisory control, Int. J. Human-Computer Studies 64 (2006) 405–419. Elsevier.

Extending interface design principles based on scale types - EAM06

by Michael May

Johannes Petersen & Michael May: Extending interface design principles based on scale types, Paper for EAM-06, European Annual Conference on
Human Decision-Making and Manual Control, Valenciennes.

Media, signs & scales (Ergonomcis 2006)

by Michael May

Michael May & Johannes Petersen: Media, Signs, and Scales for the Design Space of Instrument Displays. Contemporary Ergonomics 2006 Conference, page 93-97, Taylor & Francis.

Dimensions of Representation Design (IDSS-2005 Draft, Sienna Workshop)

by Michael May

Johannes Petersen & Michael May: Dimensions of Representation Design.
Draft paper for International Workshop on Intelligent Decision Support Systems: Retrospects and prospects, August 29 - September 2, 2005, Certosa di Pontignano (Siena). Unpublished.

Modeling Human Behaviour in Emergency: A Research Agenda for the Creation of a Rescue Robot

by Nicla Rossini

co-autored with Anna Esposito.
In Apolloni, B., Bassis, S., Esposito, A., Morabito, C.F. (Eds): Neural Nets WIRN11, Vol. 234, Frontiers in Artificial Intelligence and Applications, pp. 235-46, ISBN 978-1-60750-971-4, IOSpress, 2011.
N.B.: THIS IS A PRE-PUBLICATION DRAFT. IT MAY CONTAIN ERROS AND DIFFER SIGNIFICANTLY FROM THE PUBLISHED VERSION. FOR QUOTATION PLEASE ASK US A COPY OF THE PUBLISHED VERSION.

Robust Human-Machine Problem Solving

by David Atkinson

Atkinson, David J. “Robust Human-Machine Problem Solving”, Final Report Contract Number FA2386-09-4005, Air Force Office of Scientific Research. 2009.

This study of the state of robust human-machine problem solving research in the information sciences is motivated by... more This study of the state of robust human-machine problem solving research in the information sciences is motivated by several fundamental needs presented by the USAF mission:
1. Help humans interact and cooperate
2. Facilitate the consensus creation of knowledge
3. Formulate and facilitate prediction, prescription, decisions and planning
4. Perform complex tasks with ever-increasing volumes and sources of data
5. Achieve a network effect from adding resources

The utility of information sciences reaches its pinnacle when humans and computer can become true partners in the sense that machines are enabling humans (as individuals, teams, and large groups) to reach their full potential. We are already dependent on computers, and we live and work in intimate association with them and the capabilities they provide. This is the essence of symbiosis, a common state of species in nature in balanced ecosystems. J. C. R. Licklider coined the term “Man-Computer Symbiosis” in an early seminal paper and the aims he identified continue to guide human factors and
artificial intelligence work to this day. The central thesis of this report is that robust human-machine problem solving arises from this symbiosis.

Semantics for instrument components, EAM-01 (2001)

by Michael May

Michael May: "Semantics for Instrument Components", EAM-01, 20th European Annual Conference on Human Decision Making and Manual Control, 25-27 June, Technical University of Denmark (DTU), Lyngby, Morten Lind (Ed.).

Cognitive aspects of interface design and human-centered automation on the ship bridge: the example of ARPA-ECDIS integration (1999)

by Michael May

Michael May: " Cognitive aspects of interface design and human-centered automation on the ship bridge: the example of ARPA-ECDIS integration", in:
People In Control. Proceedings of An International Conference on Human Interfaces in Control Rooms, Cockpits and Command Centers (PIC’99), Bath June 21-23 1999. IEEE Conference publication Number 463, p. 394-399

Identifying and measuring the value of human factors to an acquisition project

by Rebecca Grier

Flexible Turn-Taking for Spoken Dialog Systems

by Antoine Raux

PhD thesis.

Even as progress in speech technologies and task and dialog modeling has allowed the development of advanced spoken... more Even as progress in speech technologies and task and dialog modeling has allowed the development of advanced spoken dialog systems, the low-level interaction behavior of those systems remains often rigid and inefficient.

The goal of this thesis, is to provide a framework and models to endow spoken dialog systems with robust and flexible turn-taking abilities. To this end, we designed a new dialog system architecture that combines a high-level Dialog Manager (DM) with a low-level Interaction Manager (IM). While the DM operates on user and system turns, the IM operates at the sub-turn level, acting as the interface between the real time information of sensors and actuators, and the symbolic information of the DM. In addition, the IM controls reactive behavior, such as interrupting a system prompt when the user barges in. We propose two approaches to control turn-taking in the IM.

First, we designed an optimization method to dynamically set the pause duration threshold used to detect the end of user turns. Using a wide range of dialog features, this algorithm allowed us to reduce average system latency by as much as 22% over a fixed-threshold baseline, while keeping the detection error rate constant.

Second, we proposed a general, flexible model to control the turn-taking behavior of conversational agents. This model, the Finite-State Turn-Taking Machine (FSTTM), builds on previous work on 6-state representations of the conversational floor and extends them in two ways. First, it incorporates the notion of turn-taking action (such as grabbing or releasing the floor) and of state-dependent action cost. Second, it models the uncertainty that comes from imperfect recognition of user's turn-taking intentions. Experimental results show that this approach performs significantly better than the threshold optimization method for end-of-turn detection, with latencies up to 40% shorter than a fixed-threshold baseline. We also applied the FSTTM model to the problem of interruption detection, which reduced detection latency by 11% over a strong heuristic baseline.

The architecture as well as all the models proposed in this thesis were evaluated on the CMU Let's Go bus information system, a publicly available telephone-based dialog system that provides bus schedule information to the Pittsburgh population.

Smartphone based vehicle-to-driver/environment interaction system for motorcycles

by Vincenzo Manzoni

Co-authored with C. Spelta, A. Corti and A. Goggi. IEEE Embedded Systems Letters, Vol. 2, n. 2, pp. 39-42.

This letter concerns the definition and implementation of an add-on interaction system for motorcycles. The system... more This letter concerns the definition and implementation of an add-on interaction system for motorcycles. The system consists of a vehicle-to-driver and a vehicle-to-environment communication mechanism, which is based on a smartphone core and on a wireless Bluetooth medium. The system is focused to increase the safety level of a motorcycle and it is constituted by a vehicle with a CAN bus, a compact embedded electronic unit implementing a CAN-to-Bluetooth gateway, a smartphone and a Bluetooth helmet. The driver-to-vehicle interaction is based on an audio interaction located at helmet level. The driver-to-environment is represented by communication via the HTTP protocol. The vocal synthesis, the speech recognition, and the gateway to the web server are implemented on the smartphone. This letter presents the hardware architecture, the software architecture and some case-study implementation issues. An evaluation of the critical aspects of the system is also provided.

A Driver-to-Infrastructure Interaction System for Motorcycles based on Smartphone

by Vincenzo Manzoni

Co-authored with A. Corti, C. Spelta and S. M. Savaresi. 13th International IEEE Conference on Intelligent Transportation Systems, ITSC 2010. Madeira Island, Portugal, September 2010, pp.1442-1447.

This paper concerns the definition and implementation of an add-on interaction system for motorcycles. The system is a... more This paper concerns the definition and implementation of an add-on interaction system for motorcycles. The system is a vehicle-to-driver communication system and a driver-to-infrastructure communication system, based on a smartphone core and a wireless Bluetooth medium. The system is devoted to increase the safety level of a motorcycle and it is constituted by a vehicle with a CAN bus, a compact embedded electronic implementing a CAN-to-Bluetooth gateway, a smartphone and a Bluetooth helmet. The driver-to-vehicle system is based on an audio interaction located at helmet level. The driver-to-infrastructure is represented by communication via a HTTP protocol. The vocal synthesis, the speech recognition, and the web gateway are resident on the smartphone. This work presents the general hardware and software architecture and some specific web-oriented implementation. An evaluation of the critical aspects of the system is also provided.