Zhaodan Kong

University of California, Davis | UCD · Department of Mechanical and Aerospace Engineering

Multirotor unmanned aerial vehicle is a prevailing type of aerial robots with wide real-world applications. The energy efficiency of the robot is a critical aspect of its performance, determining the range and duration of the missions that can be performed. This paper studies the energy-optimal planning of the multirotor, which aims at finding the...

Machine learning is revolutionizing nutrition science by enabling systems to learn from data and make intelligent decisions. However, the complexity of these models often leads to challenges in understanding their decision-making processes, necessitating the development of explainability techniques to foster trust and increase model transparency. A...

eXplainable Artificial Intelligence (XAI) has garnered significant attention for enhancing transparency and trust in machine learning models. However, the scopes of most existing explanation techniques focus either on offering a holistic view of the explainee model (global explanation) or on individual instances (local explanation), while the middl...

Objective We model factors contributing to rating timing for a single-dimensional, any-time trust in robotics measure. Background Many studies view trust as a slow-changing value after subjects complete a trial or at regular intervals. Trust is a multifaceted concept that can be measured simultaneously with a human-robot interaction. Method 65 subj...

Wildfires have the potential to cause severe damage to vegetation, property and most importantly, human life. In order to minimize these negative impacts, it is crucial that wildfires are detected at the earliest possible stages. A potential solution for early wildfire detection is to utilize unmanned aerial vehicles (UAVs) that are capable of trac...

This paper introduces an innovative approach to 3D environmental mapping through the integration of a compact, handheld sensor package with a two-stage sensor fusion pipeline. The sensor package, incorporating LiDAR, IMU, RGB, and thermal cameras, enables comprehensive and robust 3D mapping of various environments. By leveraging Simultaneous Locali...

Path-specific effect analysis is a powerful tool in causal inference. This paper provides a definition of causal counterfactual path-specific importance score for the structural causal model (SCM). Different from existing path-specific effect definitions, which focus on the population level, the score defined in this paper can quantify the impact o...

Explainability plays an increasingly important role in machine learning. Because reinforcement learning (RL) involves interactions between states and actions over time, it’s more challenging to explain an RL policy than supervised learning. Furthermore, humans view the world through a causal lens and thus prefer causal explanations over association...

The cortex has a disputed role in monitoring postural equilibrium and intervening in cases of major postural disturbances. Here, we investigate the patterns of neural activity in the cortex that underlie neural dynamics during unexpected perturbations. In both the primary sensory (S1) and motor (M1) cortices of the rat, unique neuronal classes diff...

Smoke plumes emitted from wildland-urban interface (WUI) wildfires contain toxic chemical substances that are harmful to human health, mainly due to the burning of synthetic components. Accurate measurement of these air toxics is necessary for understanding their impacts on human health. However, air pollution is typically measured using ground-bas...

Researchers have proposed various methods for visually interpreting the Convolutional Neural Network (CNN) via saliency maps, which include Class-Activation-Map (CAM) based approaches as a leading family. However, in terms of the internal design logic, existing CAM-based approaches often overlook the causal perspective that answers the core "why" q...

Brain-machine interface (BMI) technologies developed at the turn of the last century were expected to not only decode the intention to move, but to use that signal to stimulate back into the nervous system to restore movement to the patient’s own body. As the field moves to achieve these goals, two important events have spawned parallel pathways th...

Modern cyber-physical systems would often fall victim to unanticipated anomalies. Humans are still required in many operations to troubleshoot and respond to such anomalies, such those in future deep space habitats. To maximize the effectiveness and efficiency of the anomaly response process, the information provided by anomaly response technologie...

Electric Vertical-Take-Off-and-Landing multirotor aircraft has been emerging as a revolutionary transportation mode for both manned and unmanned applications, but this technology is limited by flight time and range restrictions. In this work, an energy-efficient model-based trajectory planning and feedback control framework is developed to improve...

Explainability plays an increasingly important role in machine learning. Because reinforcement learning (RL) involves interactions between states and actions over time, explaining an RL policy is more challenging than that of supervised learning. Furthermore, humans view the world from causal lens and thus prefer causal explanations over associatio...

In recent decades, unmanned aerial vehicles (UAVs) have gained considerable popularity in the agricultural sector, in which UAV-based actuation is used to spray pesticides and release biological control agents. A key challenge in such UAV-based actuation is to account for wind speed and UAV flight parameters to maximize precision-delivery of pestic...

Brain-machine interface (BMI) technologies developed at the turn of the last century were expected to not only decode the intention to move, but to use that signal to stimulate back into the nervous system to restore movement to the patient’s own body. As the field moves to achieve these goals, two important events have spawned parallel pathways th...

Machine learning-based methods have achieved successful applications in machinery fault diagnosis. However, the main limitation that exists for these methods is that they operate as a black box and are generally not interpretable. This paper proposes a novel neural network structure, called temporal logic neural network (TLNN), in which the neurons...

Effective human-multiagent teams will incorporate the cognitive skills of the human with the autonomous capabilities of the multiagent group to maximize task performance. However, producing a seamless fusion requires a greater understanding of the human’s cognitive state as it reacts to uncertainties in both the task environment and agent dynamics....

Electric Vertical-Take-Off-and-Landing aircraft has been emerging as a revolutionary transportation mode. A major limiting factor for unmanned and manned applications is the energy performance, which determines the flight time and range. Characterization and modeling of the underlying multi-physical dynamics is critical for the efforts on design, m...

Multirotor airplanes are widely used in many outdoor applications, e.g., agriculture, transportation, and public safety, where winds might be strong and prevalent. However, the effects of wind on multirotor aircraft are still not fully understood yet. The objective of this paper is to investigate and model wind effects on a real hovering octocopter...

There have been many researchers studying how to enable unmanned aerial vehicles UAVs) to navigate in complex and natural environments autonomously. In this paper, we develop an imitation learning framework and use it to train navigation policies for the UAV flying inside complex and GPS-denied riverine environments. The UAV relies on a forward-poi...

Cyberphysical systems (CPSs) are vulnerable to catastrophic fault propagation due to the strong connectivity among their subsystems. This article introduces a learning-based method to enable CPSs to explain their faults to human users, facilitating effective and efficient collaborative error diagnosis.

This paper advocates for adaptive autonomy for future spacecraft habitats through unobtrusive monitoring of human states. We propose to estimate states with models derived from human action and physiology and adapt the system or robot's level of autonomy to improve performance and safety within human-autonomy teams. We discuss the prior work in thi...

Electric multirotor aircraft with vertical-take-off-and-landing capabilities are emerging as a revolutionary transportation mode. This paper studies optimal control of a multirotor unmanned aerial vehicle based on a system-level multiphysical model. The model considers aerodynamics of the rotor-propeller assembly, electro-mechanical dynamics of the...

Multiple-player games involving cooperative and adversarial agents are a type of problems of great practical significance. In this paper, we consider an attack-defense game with a single attacker and multiple defenders. The attacker attempts to enter a protected region, while the defenders attempt to defend the same region and capture the attacker...

Timed Failure Propagation Graphs (TFPGs) have been widely used for the failure modeling and diagnosis of safety-critical systems. Currently most TFPGs are manually constructed by system experts, a process that can be time-consuming, error-prone, and even impossible for systems with highly nonlinear and machine-learning-based components. This paper...

The maturity of sensor network technologies has facilitated the emergence of an Industrial Internet of Things (IIoT), which has collected an increasing volume of data. Converting these data into actionable intelligence for fault diagnosis is key to, e.g., reducing unscheduled downtime and performance degradation. This paper formalizes a problem cal...

Arthropod pest outbreaks are unpredictable and not uniformly distributed within fields. Early outbreak detection and treatment application are inherent to effective pest management, allowing management decisions to be implemented before pests are well-established and crop losses accrue. Pest monitoring is time-consuming and may be hampered by lack...

Precision pest management Machine learning Natural enemies Precision agriculture Predatory mites Multirotor unmanned aerial vehicles (UAVs), or drones, are increasingly being used to spray liquid pesticides to control emerging pest infestations in field crops. In recent years, UAVs have been used to release predatory mites and other natural enemies...

Mitigating ground effect becomes a big challenge for autonomous aerial vehicles when they are flying in close proximity to the ground. This paper aims to develop a precise model of ground effect on mini quadcopters, provide an advanced control algorithm to counter the model uncertainty and, as a result, improves the command tracking performance whe...

In this paper we examine the performance of a human-multi-agent system by evaluating both the neurophysiological and behavioral characteristics of human subjects using both gaze tracking and electroencephalogram (EEG) devices. Unlike traditional computer simulations, these tests use real robots with the human directly embedded in the task space. Th...

In this paper, we examine whether the geometric complexity of a robotic group affects performance in a human-swarm target acquisition task, and if these changes are reflected in average neurophysiological and behavioral characteristics. This is one of the first studies to utilize both the distribution of EEG spectral power and external behaviors to...

Formal specification plays crucial roles in the rigorous verification and design of automobile steering systems. The challenge of getting high-quality formal specifications is well documented. This paper presents a problem called 'semantic parsing', the goal of which is to automatically translate the behavior of an automobile steering system to a f...

This paper studies artistic expression in human movement by exploring the performance art form salsa. The motions of a salsa performance are constructed as concatenations of motion primitives, each of which specifies the movement of the dance pair over the course of eight musical beats. To analyze the syntax of artistic expression, the choreography...

The inherent and increasing complexity of many cyber-physical systems (CPSs) makes it challenging for human users or designers to comprehend and interpret their performance. This issue, without proper attention paid, may lead to unwanted and even catastrophic consequences, particularly with safety-critical CPSs. This paper presents a new methodolog...

Due to its high versatility and scalability, manual grinding is an important and widely used technology in production for rework, repair, deburring, and finishing of large or unique parts. To make the process more interactive and reliable, manual grinding needs to incorporate "skill-based design," which models a person-based system and can go signi...

How to effectively and reliably guarantee the correct functioning of safety-critical cyber-physical systems in uncertain conditions is a challenging problem. This paper presents a data-driven algorithm to derive approximate abstractions for piecewise affine systems with unknown dynamics. It advocates a significant shift from the current paradigm of...

This paper presents new techniques to analyze and understand the sensorimotor characteristics of manual operations such as grinding, and links their influence on process performance. A grinding task, though simple, requires the practitioner to combine elements from the large repertoire of his or her skillset. Based on the joint gaze, force, and vel...

The paper presents a new formal way of modeling and designing reconfigurable robots, in which case the robots are allowed to reconfigure not only structurally but also functionally. We call such kind of robots “self-evolvable”, which have the potential to be more flexible to be used in a wider range of tasks, in a wider range of environments, and w...

The paper presents a new formal way of modeling and designing reconfigurable robots, in which case the robots are allowed to reconfigure not only structurally but also functionally. We call such kind of robots "self-evolvable", which have the potential to be more flexible to be used in a wider range of tasks, in a wider range of environments, and w...

This paper reports our progress in developing techniques for “parsing” raw gaze and force data from manual grinding tasks into a principled model. A grinding task, though simple, requires the practitioner to combine elements from the large repertoire of her skillset. Based on the joint, gaze, and force data collected from a series of experiments, a...

This paper addresses the problem of learning optimal policies for satisfying signal temporal logic (STL) specifications by agents with unknown stochastic dynamics. The system is modeled as a Markov decision process, in which the states represent partitions of a continuous space and the transition probabilities are unknown. We formulate two synthesi...

Flying animals accomplish high-speed navigation through fields of obstacles using a suite of sensory modalities that blend spatial memory with input from vision, tactile sensing, and, in the case of most bats and some other animals, echolocation. Although a good deal of previous research has been focused on the role of individual modes of sensing i...

This paper uses active learning to solve the problem of mining bounded-time signal temporal requirements of cyber-physical systems or simply the requirement mining problem. By utilizing robustness degree, we formulates the requirement mining problem into two optimization problems, a parameter synthesis problem and a falsification problem. We then p...

The increased complexity of modern systems necessitates automated anomaly detection methods to detect possible anomalous behavior determined by malfunctions or external attacks. We present formal methods for inferring (via supervised learning) and detecting (via unsupervised learning) anomalous behavior. Our procedures use data to construct a signa...

We consider the problem of steering a system with unknown, stochastic dynamics to satisfy a rich, temporally layered task given as a signal temporal logic formula. We represent the system as a Markov decision process in which the states are built from a partition of the state space and the transition probabilities are unknown. We present provably c...

Networked dynamical systems are increasingly used as models for a variety of processes ranging from robotic teams to collections of genetically engineered living cells. As the complexity of these systems increases, so does the range of emergent properties that they exhibit. In this work, we define a new logic called Spatial-Temporal Logic (SpaTeL)...

We consider the problem of controlling a system with unknown, stochastic dynamics to achieve a complex, time-sensitive task. An example of this problem is controlling a noisy aerial vehicle with partially known dynamics to visit a pre-specified set of regions in any order while avoiding hazardous areas. In particular, we are interested in tasks whi...

Modeling agile and versatile spatial behavior remains a challenging task, due to the intricate coupling of planning, control, and perceptual processes. Previous results have shown that humans plan and organize their guidance behavior by exploiting patterns in the interactions between agent or organism and the environment. These patterns, described...

This study proposes a formal way of representing the dancers in a salsa performance as a transition system. The model involves two finite state machines that communicate through a channel and the goal is to understand the notion of optimality in salsa. This is achieved by integrating two complexity metrics that measure the energy and entropy of the...

As the complexity of cyber-physical systems increases , so does the number of ways an adversary can disrupt them. This necessitates automated anomaly detection methods to detect possible threats. In this paper, we extend our recent results in the field of inference via formal methods to develop an unsupervised learning algorithm. Our procedure cons...