Kheng Hui Yeo

Designing IDA - An Intelligent Driver Assistant for Smart City Parking in Singapore

A current problem modern cities are facing is the increased traffic flow and heavily congested parking places. To reduce the time and traffic caused by finding available parking we propose IDA, an Intelligent Driver Assistant. The main objective of IDA is to help drivers to find suitable park places, to online monitor car park availability and to redirect drivers when the number of free available spots drops to a critical level. Unlike other parking applications, IDA uses speech to interact with the driver and becomes an active helper during the navigation process by adjusting dynamically the parking decisions based on the traffic situation. The paper presents the current work in progress, interaction design aspects, uses cases, as well as a first user feedback received during a public event where IDA was showcased.

SARA: Singapore’s Automated Responsive Assistant, A Multimodal Dialogue System for Touristic Information

In this paper we describe SARA, a multimodal dialogue system offering touristic assistance for visitors coming to Singapore. The system is implemented as an Android mobile phone application and provides information about local attractions, restaurants, sightseeing, direction and transportation services. SARA is able to detect the user’s location on a map by using a GPS integrated module and accordingly can provide real-time orientation and direction help. To communicate with SARA users can use speech, text or scanned QR code. Input/output modalities for SARA include natural language in form of speech or text. A short video about the main features of our Android application can be seen at: http://vimeo.com/91620644. Currently, the system supports only English, but we are working towards a multi-lingual input/output support. For test purposes we also created a web version of SARA that can be tested for Chinese and English text input/output at: http://iris.i2r.a-star.edu.sg/StatTour/.

CLARA: A Multifunctional Virtual Agent for Conference Support and Touristic Information

In this paper we present a multifunctional conversational agent which combines natural language search capabilities for two different domain applications: a conference information system and local tourist guide. The paper describes the corpora, architecture, algorithm, and the mobile application created to interact with the users. Finally, some results obtained when using the proposed system in the context of an international scientific conference held in Singapore in September 2014 with more than 1200 assistants are provided.

Design and evaluation of a conversational agent for the touristic domain

This paper focuses on the design and evaluation of SARA, a conversational agent for the touristic domain featuring a high number of different, unique characteristics: spoken dialogue interaction, dialogue orchestration, context dependent information, an animated avatar and support for different kind of dialogue types, i.e. chat, specific and general question-answering, task oriented dialogues. The agent has currently two implementations: as web client and as mobile phone application. The paper describes the modules and resources required for running the agent on both interfaces, as well as the evaluation results obtained from two assessment studies concerning the interaction design of these two agent interfaces. The feedback gathered from the studies will enable us to improve the applications in terms of service, performance and usability.

Designing MUSE: A Multimodal User Experience for a Shopping Mall Kiosk

Multimodal interactions provide more engaging experiences allowing users to perform complex tasks while searching for information. In this paper, we present a multimodal interactive kiosk for displaying information in shopping malls. The kiosk uses visual information and natural language to communicate with visitors. Users can connect to the kiosk using their own mobile phone as speech or type input device. The connection is established by scanning a QR code displayed on the kiosk screen. Field work, observations, design, system architecture and implementation are reported.

Configuration of dialogue agent with multiple knowledge sources

Knowledge base is a key component of a dialogue agent which determines its usability, performance as well as intelligence. Usually one type of knowledge source is tailored towards specific application or task. One challenge for developing multiple-domain dialogue agents is how to represent the domain knowledge in their respective ways for the best efficiency and easy construction of queries from natural language. There are a variety of knowledge sources available for building up dialogue agents such as relational database, ontology, knowledge base (KB), search index, artificial intelligence markup language (AIML) and the World Wide Web, etc. In this paper, we present a systematic way of configuring dialogue agents supported by multiple knowledge sources. With the proposed dialogue framework, we provide a complete solution for the development of various dialogue systems with the support of different dialogue management techniques, multiple protocols for cloud-enabled dialogue services, pluggable infrastructure for component reuse and service enhancement, strong scripting functions in both XML and Python. We have constructed various dialogue agents with this framework. Results show that these agents are robust and the development cycle can be considerably reduced.

Understanding welding practices on shipyards: An ethnographic study for designing any interactive robot welder

The aim of this ethnographic study is to understand welding practices in shipyard environments with the purpose of designing an interactive robot welder. The robot is meant to help workers with their daily job while being deployed on a jack-up rig. The design of the robot, including its user interface turns out to be a challenging task due to several problematic conditions encountered on the shipyard: dust, irregular floor ground, high temperatures, wind variations, elevated working platforms, narrow spaces, and circular welding paths requiring robotic arms with more than 6 degrees of freedom. Additionally, the environment is noisy and workers - mostly foreigners - have a relatively low level of English commands. The paper presents the results of our field observations and interviews conducted with several welders, as well as our robot design recommendations for the next project stage.