Artificial Intelligence and Robotics Commons^™

Rrsds: Towards A Robot-Ready Spoken Dialogue System, Casey Kennington, Daniele Moro, Lucas Marchand, Jake Carns, David Mcneill

Computer Science Faculty Publications and Presentations

Spoken interaction with a physical robot requires a dialogue system that is modular, multimodal, distributive, incremental and temporally aligned. In this demo paper, we make significant contributions towards fulfilling these requirements by expanding upon the ReTiCo incremental framework. We outline the incremental and multimodal modules and how their computation can be distributed. We demonstrate the power and flexibility of our robot-ready spoken dialogue system to be integrated with almost any robot.

How To Make Sure That Robot's Behavior Is Human-Like, Vladik Kreinovich, Olga Kosheleva, Laxman Bokati

Departmental Technical Reports (CS)

In many applications -- e.g., in health care -- it is desirable to make robots behave human-like. This means, in particular, that robotic control should not be optimal, it should be similar to human (suboptimal) behavior. People's decisions are based on bounded rationality: since we cannot compute an optimal solution for all possible situations, we divide situations into groups and come up with a solution appropriate for each group. What is optimal here is the division into groups. It is therefore desirable to implement a similar algorithm for robots. To help with such algorithms, we provide techniques that help optimally …

Adaptive Large Neighborhood Search For Vehicle Routing Problem With Cross-Docking, Aldy Gunawan, Audrey Tedja Widjaja, Pieter Vansteenwegen, Vincent F. Yu

Research Collection School Of Computing and Information Systems

Cross-docking is considered as a method to manage and control the inventory flow, which is essential in the context of supply chain management. This paper studies the integration of the vehicle routing problem with cross-docking, namely VRPCD which has been extensively studied due to its ability to reducethe overall costs occurring in a supply chain network. Given a fleet of homogeneous vehicles for delivering a single type of product from suppliers to customers through a cross-dock facility, the objective of VRPCD is to determine the number of vehicles used and the corresponding vehicle routes, such that the vehicleoperational and transportation …

Learning Word Groundings From Humans Facilitated By Robot Emotional Displays, David Mcneill, Casey Kennington

Computer Science Faculty Publications and Presentations

In working towards accomplishing a human-level acquisition and understanding of language, a robot must meet two requirements: the ability to learn words from interactions with its physical environment, and the ability to learn language from people in settings for language use, such as spoken dialogue. In a live interactive study, we test the hypothesis that emotional displays are a viable solution to the cold-start problem of how to communicate without relying on language the robot does not–indeed, cannot–yet know. We explain our modular system that can autonomously learn word groundings through interaction and show through a user study with 21 …

Nonlinear Dimensionality Reduction For The Thermodynamics Of Small Clusters Of Particles, Aditya Dendukuri

Graduate Theses and Dissertations

This work employs tools and methods from computer science to study clusters comprising a small number N of interacting particles, which are of interest in science, engineering, and nanotechnology. Specifically, the thermodynamics of such clusters is studied using techniques from spectral graph theory (SGT) and machine learning (ML). SGT is used to define the structure of the clusters and ML is used on ensembles of cluster configurations to detect state variables that can be used to model the thermodynamic properties of the system. While the most fundamental description of a cluster is in 3N dimensions, i.e., the Cartesian coordinates of …

Identification Of Microscopy Cell Images By Using Convolutional Neural Network Application, Ajis Norfatin Farisya

Student Works (2020-2029)

Breast cancer has been the major factor of cancer death and the second main cause of women’s deaths in the world. The false positive results of this cancer cell detection during the screening test leads to false treatment and emotional disturbance of the patients. Thus, breast cancer cell lines (MCF7) is used as the microscopy image samples together with the Human Bone Osteosarcoma Epithelial Cells (U2OS), and Human Hepatocyte as control to study the effectiveness of convolutional neural network (CNN) as a method of image recognition. The objectives of this study are to determine the ability of convolutional neural network …

Video-Grounded Dialogues With Pretrained Generation Language Models, Hung Le, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Pre-trained language models have shown remarkable success in improving various downstream NLP tasks due to their ability to capture dependencies in textual data and generate natural responses. In this paper, we leverage the power of pre-trained language models for improving video-grounded dialogue, which is very challenging and involves complex features of different dynamics: (1) Video features which can extend across both spatial and temporal dimensions; and (2) Dialogue features which involve semantic dependencies over multiple dialogue turns. We propose a framework by extending GPT-2 models to tackle these challenges by formulating video-grounded dialogue tasks as a sequence-to-sequence task, combining both …

Evaluating Human Versus Machine Learning Performance In Classifying Research Abstracts, Yeow Chong Goh, Xin Qing Cai, Walter Theseira, Giovanni Ko, Khiam Aik Khor

Research Collection School Of Economics

We study whether humans or machine learning (ML) classification models are better at classifying scientific research abstracts according to a fixed set of discipline groups. We recruit both undergraduate and postgraduate assistants for this task in separate stages, and compare their performance against the support vectors machine ML algorithm at classifying European Research Council Starting Grant project abstracts to their actual evaluation panels, which are organised by discipline groups. On average, ML is more accurate than human classifiers, across a variety of training and test datasets, and across evaluation panels. ML classifiers trained on different training sets are also more …

Unsupervised Monocular Depth Estimation With Multi-Scale Structural Similarity Powered Loss Function, Kohan Ali

Student Works (2020-2029)

Depth Estimation refers to a set of techniques and algorithms that aim to obtain a representation of spatial information of a scene. Nowadays specific hardware such as sensors, radars and multiple-view-recording cameras are being used in order to acquire depth data of a scene. Modern approaches use deep learning to address this task by trying to learn depth information in a supervised manner. However, this approach requires a large amount ground-truth data for a particular scene so that a model can be trained successfully. Also preparing ground-truth data for a range of environments is a challenging and expensive task to …

Efficient Vehicle Routing Optimization For Autistic Users, Mohammed Shabalah Abdulrahman Hasan

Student Works (2020-2029)

In recent years, daily life without a vehicle would be impossible. As an inevitable result, the number of vehicles on the road increases day by day in various large cities around the world. The increased number of vehicles is a big concern because it causes a lot of traffic congestions, especially during peak hours. Besides, there has been a rapid rise of on-demand Ride-Hailing Services (RHSs), such as Grab, Uber, EzCab, and MyCar, etc. This allows passengers with smartphones to place trip requests and assign them to drivers according to requester’s location and drivers' availability. In consequence, efficient routing algorithms …

Query Graph Generation For Answering Multi-Hop Complex Questions From Knowledge Bases, Yunshi Lan, Jing Jiang

Research Collection School Of Computing and Information Systems

Previous work on answering complex questions from knowledge bases usually separately addresses two types of complexity: questions with constraints and questions with multiple hops of relations. In this paper, we handle both types of complexity at the same time. Motivated by the observation that early incorporation of constraints into query graphs can more effectively prune the search space, we propose a modified staged query graph generation method with more flexible ways to generate query graphs. Our experiments clearly show that our method achieves the state of the art on three benchmark KBQA datasets.

Trajectory Similarity Learning With Auxiliary Supervision And Optimal Matching, Hanyuan Zhang, Xingyu Zhang, Qize Jiang, Baihua Zheng, Zhenbang Sun, Weiwei Sun, Changhu Wang

Research Collection School Of Computing and Information Systems

Trajectory similarity computation is a core problem in the field of trajectory data queries. However, the high time complexity of calculating the trajectory similarity has always been a bottleneck in real-world applications. Learning-based methods can map trajectories into a uniform embedding space to calculate the similarity of two trajectories with embeddings in constant time. In this paper, we propose a novel trajectory representation learning framework Traj2SimVec that performs scalable and robust trajectory similarity computation. We use a simple and fast trajectory simplification and indexing approach to obtain triplet training samples efficiently. We make the framework more robust via taking full …

Skin-Mimo: Vibration-Based Mimo Communication Over Human Skin, Dong Ma, Yuezhong Wu, Ming Ding, Mahbub Hassan, Wen Hu

Research Collection School Of Computing and Information Systems

We explore the feasibility of Multiple-Input-Multiple-Output (MIMO) communication through vibrations over human skin. Using off-the-shelf motors and piezo transducers as vibration transmitters and receivers, respectively, we build a 2x2 MIMO testbed to collect and analyze vibration signals from real subjects. Our analysis reveals that there exist multiple independent vibration channels between a pair of transmitter and receiver, confirming the feasibility of MIMO. Unfortunately, the slow ramping of mechanical motors and rapidly changing skin channels make it impractical for conventional channel sounding based channel state information (CSI) acquisition, which is critical for achieving MIMO capacity gains. To solve this problem, we …

Next-Generation Self-Organizing Communications Networks: Synergistic Application Of Machine Learning And User-Centric Technologies, Chetana V. Murudkar

USF Tampa Graduate Theses and Dissertations

The telecommunications industry is going through a metamorphic journey where the 5G and 6G technologies will be deeply rooted in the society forever altering how people access and use information. In support of this transformation, this dissertation proposes a fundamental paradigm shift in the design, performance assessment, and optimization of wireless communications networks developing the next-generation self-organizing communications networks with the synergistic application of machine learning and user-centric technologies.

This dissertation gives an overview of the concept of self-organizing networks (SONs), provides insight into the “hot” technology of machine learning (ML), and offers an intuitive understanding of the user-centric (UC) …

Simulation-Based An Exploratory Analysis Of Drone Air Strike On Saudi Oilfields, Jiajun Zhang, Xiaochao Qian, Jinpeng Zhou, Xuanling Wang, Zhifeng Lu

Journal of System Simulation

Abstract: The incident of air strike in Sandi Arabia in September 2019 is taken as an example，A rapid analysis method for crisis events based on simulation is proposed. Combining the simulation with the exploratory analysis, the uncertainty of crisis events is comprehensively analyzed and dealt with. According to the public information of the incidents details from Sandi Arabia, Yemen, the combat situation of the air strike is replayed based on the wargaming. The rationality and authenticity of the details in the event statement is verified and can also provide reference to the development and combat research of the “Low, Small …

Multi-Tank Adaptive Scheduling Algorithm And Simulation For Ship Stability Realization, Xiong Yong, Xuanzhuo Liang, Zhang Jia

Journal of System Simulation

Abstract: Aiming at the influence of the oil tank on the floating state and stability of the ship, the multi-tank adaptive dispatching control algorithm to maintain the stability of the ship is studied. The automatic floating state adjustment simulation system of the ship is realized by the WinCC (Windows Control Center) configuration software. For the system architecture, the Boolean logic table is used to construct the connection relationships of the oil tanks, pumps and pipelines, and the amount of oil exchange between the cabins is calculated according to the floating equation, and the balance of the floating state in the …

Simulation-Based Effectiveness Evaluation For System-Of-System Under Multi-Equipment Collaboration, Ma Ning, Shenglin Lin

Journal of System Simulation

Abstract: Complex coordination exists among the various equipment in the system-of-system (SoS) operational process. The influence relationship among the various indexes is ignored in the traditional effectiveness evaluation methods. Aiming at this, a new effectiveness evaluation approach for the SoS is proposed. Numerous evaluation data is analyzed, based on the association rules mining, to obtain the influence among the effectiveness indexes. The networked evaluation index system is constructed, and the effectiveness integration evaluation is realized based on the analytic network process. The feasibility and validity of the proposed method are verified by evaluating the effectiveness of an air defense SoS.

Identification Method For Fractional-Order Systems Based On Haar Wavelet Operational Matrix, Yuanlu Li, Li Teng, Baoying Liu

Journal of System Simulation

Abstract: Studies have shown that the dynamical systems can be more accurately described by the fractional-order systems because its order can be any number. That’s why the fractional-order systems are being paid more and more attention. However, how to create a fractional-order system is still in the exploratory stage. Considering the nonlocal features of the fractional differentiation, a method for the fractional-order system identification is proposed by taking the Haar wavelet operational matrix. The proposed method can reduce the dimension of the operational matrix by abandoning the high frequency coefficients of the input and output signals so that the buffer …

Virtual-Point-Light Sampling Algorithm Based On Indirect Illumination Clustering Of Visible Scene Region, Chen Sheng, Chunyi Chen, Qiwei Xing, Chaozhi Yang

Journal of System Simulation

Abstract: Focusing on the accuracy of indirect illumination calculation, an improved view-sensitive virtual point light (VPL) sampling method is proposed. The visible shading points are clustered according to the positions and normal vectors. The product of the contribution of VPLs on the representative visible shading points and the number of VPLs belonging to the same class is calculated, and the sum of the products is treated as the estimation of the indirect illumination which constructs the cumulative distribution function (CDF). On the basis of the CDF, the VPLs of calculating the indirect illumination on every visible shading point are selected. …

Augmented Reality Interactive Media System For Ancient Buildings Based On Servomotor, Xingquan Cai, Zhe Yang, He Xin, Chen Chao

Journal of System Simulation

Abstract: Augmented reality is usually limited to the screen devices, and is difficult to realize the stereoscopic dynamic interaction of multiplayer. A large screen interactive display method based on the servo motor is prsented. The serial communication program to control the scanning reciprocating mode of the servo is designed. By using the edge detection methods and deep normal texture processing, the line draft of the ancient buildings is rendered. By combining the hardware and presentation application modules, the user interaction capabilities and seasonal effects is added to the showcase application modules. The experimental results show that the interactive media system …