Ming Hou

Defence Research & Development Canada · Human Systems Integration

Artificial Intelligence (AI) is becoming more ubiquitous throughout our lives. As our reliance on this technology increases, ensuring human operators maintain an adequate level of trust is integral to their safe and effective operations. To facilitate the appropriate level of operator trust in AI, a mechanism to continuously evaluate and calibrate...

Object detection is important in many applications, such as autonomous driving. While 2D images lack depth information and are sensitive to environmental conditions, 3D point clouds can provide accurate depth information and a more descriptive environment. However, sparsity is always a challenge in single-frame point cloud object detection. This pa...

Object detection is important in many applications, such as autonomous driving. While 2D images are lack of depth information and are sensitive to environmental conditions, 3D point cloud can provide accurate depth information and a more descriptive environment. However, sparsity is always a challenge in single-frame point cloud object detection. T...

Sample efficiency, which refers to the number of samples required for a learning agent to attain a specific level of performance, is central to developing practical reinforcement learning (RL) for complex and large-scale decision-making problems. The ability to transfer and generalize knowledge gained from previous experiences to downstream tasks c...

The problem of exploration is one of the major challenges in practical reinforcement learning (RL). Uncertainty-aware exploration, which leverages the quantification of epistemic and aleatory uncertainty, has been known as an appealing exploration method. However, capturing the combined effect of aleatory and epistemic uncertainty for decision-maki...

Sample efficiency, which refers to the number of samples required for a learning agent to attain a specific level of performance, is central to developing practical reinforcement learning (RL) for complex and large-scale decision-making problems. The ability to transfer and generalize knowledge gained from previous experiences to downstream tasks c...

This article proposes a resilient strategy for leaderless and leader–following consensus in general linear multiagent systems under simultaneous presence of false data injection and denial-of-service (DoS) attacks. To save energy, local control updates and communication between the neighboring agents are based on a distributed periodic event-trigge...

Introduction This paper proposes a Bayesian surprise learning algorithm that internally motivates the cognitive radar to estimate a target's state (i.e., velocity, distance) from noisy measurements and make decisions to reduce the estimation error gradually. The work exhibits how the sensor learns from experiences, anticipates future responses, and...

Mobile Edge Caching (MEC) is a revolutionary technology for the Sixth Generation (6G) of wireless networks with the promise to significantly reduce users' latency via offering storage capacities at the edge of the network. The efficiency of the MEC network, however, critically depends on its ability to dynamically predict/update the storage of cach...

In support of the modernization of the North American Aerospace Defense Command (NORAD), several new initiatives have been proposed for future NORAD multi-domain Command and Control (C2) operations. The research works at Defence Research and Development (DRDC) Toronto Research Centre (TRC) aims to identify key Human Factors (HF) challenges and prov...

Coded/uncoded content placement in Mobile Edge Caching (MEC) has evolved as an efficient solution to meet the significant growth of global mobile data traffic by boosting the content diversity in the storage of caching nodes. To meet the dynamic nature of the historical request pattern of multimedia contents, the main focus of recent researches has...

Ultra-Wideband (UWB) is one of the key technologies empowering the Internet of Thing (IoT) concept to perform reliable, energy-efficient, and highly accurate monitoring, screening, and localization in indoor environments. Performance of UWB-based localization systems, however, can significantly degrade because of Non Line of Sight (NLoS) connection...

A brain-inspired intelligent adaptive system (IAS) framework is developed toward fundamental breakthroughs in the cognitive bottleneck of humans and the incompetence of artificial intelligence (AI) under indeterministic conditions or with insufficient data. IASs have led to defense science and technology innovations for interaction-centered design...

Recent studies in neuroscience suggest that Successor Representation (SR)-based models provide adaptation to changes in the goal locations or reward function faster than model-free algorithms, together with lower computational cost compared to that of model-based algorithms. However, it is not known how such representation might help animals to man...

Guidance for integrating socio-technical systems (e.g., autonomous systems) into broad applications

Ultra Wide Band (UWB) has been emerged as a technology to provide reliable, accurate, and energy-efficient indoor navigation/localization systems. There are, however, several key challenges ahead for its efficient implementation including complexity of the identification/mitigation of Non Line of Sight (NLoS) links, and the limited battery life of...

Recently, as a consequence of the COVID-19 pandemic, dependence on telecommunication for remote learning/working and telemedicine has significantly increased. In this context, preserving high Quality of Service (QoS) and maintaining low latency communication are of paramount importance. In cellular networks, incorporation of Unmanned Aerial Vehicle...

Neurorehabilitation is an emerging and transdisciplinary field that is not only highly demanded in medical science and healthcare, but also a challenging problem in cognitive neurology, neurosignaling theory, neuroinformatics, and brain science. This paper presents findings in basic research on neuroinformatics towards neurorehabilitation by explor...

To understand animals’ behavior in finding relations between similar tasks and adapting themselves to changes in the tasks, it is necessary to know how the brain generalizes the learned knowledge from a previous task to unseen tasks. Recent studies in neuroscience suggest that Successor Representation (SR)-based models provide adaptation to changes...

Cognitive Informatics (CI) and Cognitive Computing (CC) are fundamental intelligence theories and general AI technologies triggered by the transdisciplinary advances in intelligence, computer, brain, knowledge, cognitive, robotic, and cybernetic sciences for engineering implementations. This paper presents a summary of the plenary panel (Part I) on...

Recent advancements in Internet of Things (IoTs) have brought about a surge of interest in indoor positioning for the purpose of providing reliable, accurate, and energy-efficient indoor navigation/localization systems. Ultra Wide Band (UWB) technology has been emerged as a potential candidate to satisfy the aforementioned requirements. Although UW...

Symbiotic autonomous systems (SAS) are advanced intelligent and cognitive systems that exhibit autonomous collective intelligence enabled by coherent symbiosis of human–machine interactions in hybrid societies. Basic research in the emerging field of SAS has triggered advanced general-AI technologies that either function without human intervention...

Autonomous systems are advanced intelligent systems and general AI technologies triggered by the transdisciplinary development in intelligence science, system science, brain science, cognitive science, robotics, computational intelligence, and intelligent mathematics. AS are driven by the increasing demands in the modern industries of cognitive com...

Autonomous Systems (AS) are perceived as the most advanced intelligent systems evolved from those of reflexive, imperative, and adaptive intelligence. A plenary panel on "Future Development of Autonomous Systems" is organized at the inaugural IEEE ICAS'21. This paper reports the panel discussions about the-state-of-the-art and paradigms of AS, the...

This paper presents a panel summary on the framework of Autonomous Systems (AS) and paradigms in development. AS are advanced intelligent systems and general AI technologies triggered by the transdisciplinary development in intelligence science, system science, brain science, cognitive science, robotics, computational intelligence, and intelligent...

A trust model IMPACTS (intention, measurability, performance, adaptivity, communication, transparency, and security) has been conceptualized to build human trust in autonomous systems. A system must exhibit the seven critical characteristics to gain and maintain its human partner’s trust towards an effective and collaborative team in achieving comm...

Human action recognition using various sensors is a mandatory component of autonomous vehicles, humanoid robots, and ambient living environments. A particular interest is the detection and recognition of falls. In this paper, we propose the use of temporal convolution networks guided by knowledge distillation for detecting falls and recognizing typ...

Symbiotic Autonomous Systems (SAS) are advanced intelligent and cognitive systems exhibiting autonomous collective intelligence enabled by coherent symbiosis of human-machine interactions in hybrid societies. Basic research in the emerging field of SAS has triggered advanced general AI technologies functioning without human intervention or hybrid s...

A trust model IMPACT: Intention, Measurability, Predictability, Agility, Communication, and Transparency has been conceptualized to build human trust in autonomous agents. The six critical characteristics must be exhibited by the agents in order to gain and maintain the trust from their human partners towards an effective and collaborative team in...

Recently, as a consequence of the COVID-19 pandemic, dependence on telecommunication for remote learning/working and telemedicine has significantly increased. In this context, preserving high Quality of Service (QoS) and maintaining low latency communication are of paramount importance. Development of an Unmanned Aerial Vehicles (UAV)-aided heterog...

Autonomous systems are an emerging AI technology functioning without human intervention underpinned by the latest advances in intelligence, cognition, computer, and systems sciences. This paper explores the intelligent and mathematical foundations of autonomous systems. It focuses on structural and behavioral properties that constitute the intellig...

Remotely piloted aircraft systems (RPASs) are tools for military organizations to help remove humans from dangerous situations, and permit operations in severe and inhospitable environments. To support the procurement of an RPAS fleet under Canada’s Strong, Secure, Engaged 2017 defence policy, the Royal Canadian Air Force (RCAF) under the RCAF Join...

It is recognized that system trustworthiness is a hyperstructure embodied by the dimensions of the structural, behavioral, and system trustworthiness and associated uncertainty. This paper explores a theoretical framework of trust and trustworthiness of autonomous systems. It presents a formal study on the essences and mathematical models of system...

Analytic epidemiology is a transdisciplinary study on the cognitive, theoretical, and mathematical models of COVID-19 and other contagious diseases. It is recognized that analytic epidemiology may be better studied by big data explorations at the macro level rather than merely biological analyses at the micro level in order to not loss the forest f...

Biometrics and biometric-enabled decision support systems (DSS) have become a mandatory part of complex dynamic systems such as security checkpoints, personal health monitoring systems, autonomous robots, and epidemiological surveillance. Risk, trust, and bias (R-T-B) are emerging measures of performance of such systems. The existing studies on the...

Biometrics and biometric-enabled decision support systems (DSS) have become a mandatory part of complex dynamic systems such as security checkpoints, personal health monitoring systems, autonomous robots, and epidemiological surveillance. Risk, trust, and bias (R-T-B) are emerging measures of performance of such systems. The existing studies on the...

Recognizing, assessing, countering, and mitigating the biases of different nature from heterogeneous sources is a critical problem in designing a cognitive Decision Support System (DSS). An example of such a system is a cognitive biometric-enabled security checkpoint. Biased algorithms affect the decision-making process in an unpredictable way, e.g...

Objective: This study evaluated sonification and tactification for encoding urgency of system health status presented in the ground control station (GCS) visual interface of an unmanned aircraft system (UAS), and the observer’s perception of urgency. Background: The barrage of data in the GCS visual interface has the potential to isolate the operat...

Autonomous systems underpinned by cognitive intelligence represent advanced forms of artificial intelligence studied in intelligence science, systems science, and computational intelligence. Traditional theories and technologies of autonomous systems put emphases on human-system interactions and humans in-the-loop. This paper explores the intellige...

The aim of Canada’s Joint Unmanned Surveillance and Target Acquisition System program is to acquire an Unmanned Aircraft System (UAS) for Royal Canadian Air Force’s domestic and international operations. This UAS will be capable of complementing existing reconnaissance, surveillance, target acquisition, and engagement capabilities. Defence Research...

In military simulations, software agents are used to represent individuals, weapon platforms or aggregates thereof. Modeling the behavioral capabilities and limitations of such agents may be time-consuming, requiring extensive interaction with subject matter experts and complicated scripts, but nevertheless resulting in rigid, predictable performan...

Defence Research and Development Canada has conducted a number of human factors analysis tasks and experiments to support the Canadian Armed Force’s acquisition of an unmanned aircraft system for domestic and international operations. Experiments were run on a simulation-based UAS mission experimentation testbed. Results promoted the design and dev...

Commercial/Military-Off-The-Shelf (COTS/MOTS) Computer Generated Forces (CGF) packages are widely used in modeling and simulation for training purposes. Conventional CGF packages often include artificial intelligence (AI) interfaces, but lack behavior generation and other adaptive capabilities. We believe Machine Learning (ML) techniques can be ben...

This paper provides guidance for adaptive learning systems designers by reviewing the evolution of learning theories and their associated progress, which is enabled by computers, artificial intelligence and augmented cognition. A generic conceptual framework of intelligent adaptive learning systems is discussed in detail for individualised learning...

Canada’s Joint Unmanned Surveillance and Target Acquisition System program for acquiring an uninhabited aircraft system requires an interim ground control station for developing operator interface technologies and investigate training needs for the future aircraft. Defence Research and Development Canada is developing the Test-bed for Integrated Gr...

This documment describes preliminary work to develop a training tool for payload operators of unmanned aerial vehicles (UAVs) in support of the Royal Canadian Air Force (RCAF) Joint Unmanned Aerial Vehicle Surveillance Target Acquisition System (JUSTAS) project. The tool is to enhance sustained operator attention when monitoring UAV sensor displays...

Commercial/Military-Off-The-Shelf (COTS/MOTS) Computer Generated Forces (CGF) packages are widely used in modelling and simulation for training purposes. Conventional CGF packages often include artificial intelligence (AI) interfaces, with which the end user define CGF behaviors. We believe machine learning (ML) techniques can be beneficial to the...

To support the concept development and evaluation of future Unmanned Aircraft System (UAS) operations for the Royal Canadian Air Force (RCAF), Defence Research and Development Canada (DRDC) requires the development of UAS mission scenarios with the context of manned-unmanned aerial vehicle interaction. The development of scenarios is often the firs...

Performance and mental workload were observed for the administration of a rest break or exogenous vibrotactile signals in auditory and visual monitoring tasks. Sustained attention is mentally demanding. Techniques are required to improve observer performance in vigilance tasks. Participants (N = 150) monitored an auditory or a visual display for ch...

This chapter presents a unified agent-based design framework and methodologies to guide operator interface design for complex human-machine systems (HMSs) (e.g. unmanned aerial vehicle (UAV) control station). It discusses the evolution of interface technologies and describes the concepts and associated conceptual framework of intelligent adaptive i...

This chapter determines the requirements for roles by examining collaboration in a group. Roles are fundamental tools to support collaboration activities. It considers "collaboration" as a generalized concept. The chapter denotes collaboration in the following categories: among people, that is, natural collaboration; among people through systems, t...

A synthesis of recent research and developments on intelligent adaptive systems from the HF (human factors) and HCI (human-computer interaction) domains, this book provides integrated design guidance and recommendations for researchers and system developers. It addresses a recognized lack of integration between the HF and HCI research communities,...

Adaptive Collaboration (AC) is essential for maintaining optimal team performance on collaborative tasks. However, little research has discussed AC in multi-agent systems. This paper introduces AC within the context of solving real-world team performance problems using computer-based algorithms. Based on the authors’ previous work on the Environmen...

An Intelligent Adaptive System (IAS) is a synergy between an intelligent interface and adaptive automation technologies capable of context sensitive interaction with operators. A well-designed IAS should enable flexible task allocation between the operator and the machine. Research suggests that the in-tegration of real-time operator state assessme...

An Intelligent Adaptive System (IAS) is a synergy between an intelligent interface and adaptive automation technologies capable of context sensitive interaction with operators. A well-designed IAS should enable flexible task allocation between the operator and the machine. Research suggests that the integration of real-time operator state assessmen...

ABSTRACT This study investigated the efficacy of a multimodal display ground control station (GCS) for the control of an unmanned aerial vehicle (UAV) to convey system faults and environmental hazards. The participant's task was to fly a short UAV mission, detect critical events, and land safely in possibly strong turbulence and wind shear. While m...

This document presents the results of a literature review on Questioning Technique (QT) and the development of a scenario, instructional material, and evaluation criteria that support the development of an Intelligent Tutoring System (ITS). The use of QT across multiple domains was surveyed and synthesized to illustrate how this knowledge can be in...

Micro aerial vehicles (MAVs) are small lightweight unmanned aerial vehicles used by dismounted soldiers for aerial reconnaissance and acquiring information for local situation awareness. MAVs require a portable handheld ground control station (GCS) that allows the operator to control and monitor the flight of the MAV. This paper investigated two me...

With increased understanding of cognitive informatics and the advance of computer technologies, it is becoming clear that human-computer interaction (HCI) is an interaction between two kinds of intelligences, i.e., natural intelligence and artificial intelligence. This paper attempts to clarify interaction-related terminologies through step-by-step...