Arkady Zgonnikov

Arkady Zgonnikov
Delft University of Technology | TU · Cognitive Robotics

PhD

About

51
Publications
6,088
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
156
Citations
Introduction
I explore ways to enable artificial agents to anticipate humans' decisions using cognitive models, building up on the extensive body of knowledge elaborated in cognitive psychology and neuroscience. I believe this can help us to develop autonomous vehicles which will reliably predict the decisions of human road users during traffic interactions. The overarching goal of my work is to keep the complex interactions between humans and artificial agents under meaningful human control.
Additional affiliations
November 2020 - present
Delft University of Technology
Position
  • Professor (Assistant)
June 2019 - November 2020
Delft University of Technology
Position
  • PostDoc Position
August 2017 - March 2019
The University of Aizu
Position
  • PostDoc Position
Education
October 2011 - September 2014
The University of Aizu
Field of study
  • Computer Science and Engineering
September 2004 - June 2009
Saint Petersburg State University
Field of study
  • Applied mathematics

Publications

Publications (51)
Preprint
Full-text available
The concept of meaningful human control has been proposed to address responsibility gaps and mitigate them by establishing conditions that enable a proper attribution of responsibility for humans (e.g., users, designers and developers, manufacturers, legislators). However, the relevant discussions around meaningful human control have so far not res...
Preprint
A major challenge for autonomous vehicles is interacting with other traffic participants safely and smoothly. A promising approach to handle such traffic interactions is equipping autonomous vehicles with interaction-aware controllers (IACs). These controllers predict how surrounding human drivers will respond to the autonomous vehicle's actions, b...
Preprint
Full-text available
Laboratory studies of abstract, highly controlled tasks point towards noisy evidence accumulation as the primary mechanism governing decision making. Yet it is unclear whether the cognitive processes implicated in simple, isolated decisions in the lab are as paramount to decisions that are ingrained in more complex behaviors, such as driving. Here...
Preprint
Recently, multiple naturalistic traffic datasets of human-driven trajectories have been published (e.g., highD, NGSim, and pNEUMA). These datasets have been used in studies that investigate variability in human driving behavior, for example for scenario-based validation of autonomous vehicle (AV) behavior, modeling driver behavior, or validating dr...
Article
A major challenge for autonomous vehicles is interacting with other traffic participants safely and smoothly. A promising approach to handle such traffic interactions is equipping autonomous vehicles with interaction-aware controllers (IACs). These controllers predict how surrounding human drivers will respond to the autonomous vehicle’s actions, b...
Article
Full-text available
How can humans remain in control of artificial intelligence (AI)-based systems designed to perform tasks autonomously? Such systems are increasingly ubiquitous, creating benefits - but also undesirable situations where moral responsibility for their actions cannot be properly attributed to any particular person or group. The concept of meaningful h...
Article
Approach-avoidance conflict is observed in the competing motivations towards the benefits and away from the costs of a decision. The current study investigates the action dynamics of response motion during such conflicts in an attempt to characterize their dynamic resolution. Approach-avoidance conflict was generated by varying the appetitive conse...
Conference Paper
Human highway-merging behavior is an important aspect when developing autonomous vehicles (AVs) that can safely and successfully interact with other road users. To design safe and acceptable human-AV interactions, the underlying mechanisms in human-human interactive behavior need to be understood. Exposing and understanding these mechanisms can be...
Preprint
Full-text available
Inferring reward functions from demonstrations and pairwise preferences are auspicious approaches for aligning Reinforcement Learning (RL) agents with human intentions. However, state-of-the art methods typically focus on learning a single reward model, thus rendering it difficult to trade off different reward functions from multiple experts. We pr...
Article
Full-text available
Purpose The purpose of the current study was to evaluate the social and cognitive underpinnings of miscommunication during an interactive listening task. Method An eye and computer mouse–tracking visual-world paradigm was used to investigate how a listener's cognitive effort (local and global) and decision-making processes were affected by a speak...
Article
Full-text available
Multimodal integration is an important process in perceptual decision-making. In humans, this process has often been shown to be statistically optimal, or near optimal: sensory information is combined in a fashion that minimizes the average error in perceptual representation of stimuli. However, sometimes there are costs that come with the optimiza...
Preprint
Full-text available
Multimodal integration is an important process in perceptual decision-making. In humans, this process has often been shown to be statistically optimal, or near optimal: sensory information is combined in a fashion that minimises the average error in perceptual representation of stimuli. However, sometimes there are costs that come with the optimiza...
Article
Full-text available
Decisions are occasionally accompanied by changes-of-mind. While considered a hallmark of cognitive flexibility, the mechanisms underlying changes-of-mind remain elusive. Previous studies on perceptual decision making have focused on changes-of-mind that are primarily driven by the accumulation of additional noisy sensory evidence after the initial...
Article
Full-text available
Executing an important decision can be as easy as moving a mouse cursor or reaching towards the preferred option with a hand. But would we decide differently if choosing required walking a few steps towards an option? More generally, is our preference invariant to the means and motor costs of reporting it? Previous research demonstrated that asymme...
Preprint
Full-text available
Decisions are occasionally accompanied by changes-of-mind. While considered a hallmark of cognitive flexibility, the mechanisms underlying changes-of-mind remain elusive. Previous studies on perceptual decision making have focused on changes-of-mind that are primarily driven by the accumulation of additional noisy sensory evidence after the initial...
Preprint
Approach-avoidance conflict is observed in the competing motivations towards the benefits and away from the costs of a decision. The current study employs the action dynamics of response motion, via mouse-tracking, in an attempt to characterize the continuous dynamic resolution of such conflicts. Approach-avoidance conflict (AAC) was generated by v...
Preprint
Full-text available
Executing an important decision can be as easy as moving a mouse cursor or reaching towards the preferred option with a hand. But would we decide differently if choosing required walking a few steps towards an option? More generally, is our preference invariant to the means and motor costs of reporting it? Previous research demonstrated that asymme...
Preprint
Full-text available
Response delay is an inherent and essential part of human actions. In the context of human balance control, the response delay is traditionally modeled using the formalism of delay-differential equations, which adopts the approximation of fixed delay. However, experimental studies revealing substantial variability, adaptive anticipation, and non-st...
Preprint
Full-text available
Human operators often employ intermittent, discontinuous control strategies in a variety of tasks. A typical intermittent controller monitors control error and generates corrective action when the deviation of the controlled system from the desired state becomes too large to ignore. Most contemporary models of human intermittent control employ simp...
Conference Paper
Human operators often employ intermittent, discontinuous control strategies in a variety of tasks. A typical intermittent controller monitors control error and generates corrective action when the deviation of the controlled system from the desired state becomes too large to ignore. Most contemporary models of human intermittent control employ simp...
Poster
Full-text available
The present work mentions some preliminary data from two experiments in a novel Approach-Avoidance Task using mouse-tracking. Avoidance paradigms have traditionally relied on the analysis of discrete responses (e.g., rate of avoided trials) in the presence of threats, in other words, the outcome of a decision to avoid or not. However, during appro...
Article
Full-text available
Computerized paradigms have enabled gathering rich data on human behaviour, including information on motor execution of a decision, e.g. by tracking mouse cursor trajectories. These trajectories can reveal novel information about ongoing decision processes. As the number and complexity of mouse-tracking studies increase, more sophisticated methods...
Chapter
According to the modern theory of adaption of socioeconomic systems to unknown environments only the interaction between agents can be responsible for various emergent phenomena governed by decision-making and agent learning. Previously we advocated the idea that adopting a more complex model for the agent individual behavior including rational and...
Poster
Full-text available
This project explored the potential of implementing response trajectories (alongside traditional measures) as a measure of conflict in an approach-avoidance task. Preliminary results are shared.
Article
Full-text available
Archetypal stick balancing task represents a wide class of unstable processes under human control. The currently dominant theory of human control in stick balancing is based on the concept of discontinuous, or intermittent control. Traditionally, intermittent control models involve threshold-driven control activation, however, recently it has been...
Preprint
Full-text available
Computerized paradigms have enabled gathering rich data on human behaviour, including information on motor execution of a decision, e.g. by tracking mouse cursor trajectories. These trajectories can reveal novel information about ongoing decision processes. As the number and complexity of mouse-tracking studies increase, more sophisticated methods...
Article
Full-text available
Humans face the task of balancing dynamic systems near an unstable equilibrium repeatedly throughout their lives. Much research has been aimed at understanding the mechanisms of intermittent control in the context of human balance control. The present paper deals with one of the recent developments in the theory of human intermittent control, namel...
Article
Full-text available
A fair simple car driving simulator was created based on the open source engine TORCS and used in car-following experiments aimed at studying the basic features of human behavior in car driving. Four subjects with different skill in driving real cars participated in these experiments. The subjects were instructed to drive a car without overtaking a...
Article
Full-text available
Recent progress in motor control suggests that in controlling unstable systems humans switch intermittently between the passive and active behavior instead of controlling the system in a continuous manner. Traditionally, the models of intermittent control employ the notion of threshold to mimic control switching mechanisms in humans. The notion of...
Article
Full-text available
When facing a task of balancing a dynamic system near an unstable equilibrium, humans often adopt intermittent control strategy: Instead of continuously controlling the system, they repeatedly switch the control on and off. Paradigmatic example of such a task is stick balancing. Despite the simplicity of the task itself, the complexity of human int...
Article
Full-text available
In controlling unstable systems humans switch intermittently between the passive and active behavior instead of controlling the system in a continuous manner. The notion of noise-driven control activation provides a richer alternative to the conventional threshold-based models of intermittent motor control. The present study represents the control...
Article
Full-text available
Learning and adaptation play great role in emergent socio-economic phenomena. Complex dynamics has been previously found in the systems of multiple learning agents interacting via a simple game. Meanwhile, the single agent adaptation is considered trivially stable. We advocate the idea that adopting a more complex model of the individual behavior m...
Article
Full-text available
Understanding how humans control unstable systems is central to many research problems, with applications ranging from quiet standing to aircraft landing. Increasingly much evidence appears in favor of event-driven control hypothesis: human operators are passive by default and only start actively controlling the system when the discrepancy between...
Article
The results of experiments on balancing a virtual inverted pendulum with over-damped dynamics are reported. Three types of pendulum, namely, an inverted stick, a triangle pendulum, and a vibrating spring were used in experiments and subjects of different age, gender, and skill of balancing participated in these experiments. It is demonstrated that...
Article
Full-text available
Humans are often incapable of precisely identifying and implementing the desired control strategy in controlling unstable dynamical systems. That is, the operator of a dynamical system treats the current control effort as acceptable even if it deviates slightly from the desired value, and starts correcting the actions only when the deviation has be...
Chapter
Dynamical traps as a new emergence mechanism related to the bounded capacity of human cognition is considered. It assumes that individuals (operators) governing the dynamics of a certain system try to follow an optimal strategy in controlling its motion but fail to do this perfectly because similar strategies are indistinguishable for them. This is...
Article
Full-text available
Understanding how humans control unstable systems is central to many research problems, with applications ranging from quiet standing to aircraft landing. Much evidence appears in favor of event-driven control hypothesis: human operators are passive by default and only start actively controling the system when the discrepancy between the current an...
Article
Full-text available
A new emergence mechanism related to the bounded capacity of human cognition is considered. It assumes that individuals (operators) governing the dynamics of a certain system try to follow an optimal strategy in controlling its motion but fail to do this perfectly because similar strategies are indistinguishable for them, which is called human fuzz...
Conference Paper
Full-text available
We conduct a theoretical analysis of the effects of intrinsic motivation on learning dynamics. We study a simple example of a single agent adapting to unknown environment; the agent is biased by the desire to take those actions she has little information about. We show that the intrinsic motivation may induce the instability (namely, periodic oscil...
Article
Full-text available
We consider the dynamical traps model of human fuzzy rationality which describes the behavior of human controling a dynamical system near an equilibrium point. The basic dynamical trap model describes the behavior of human operator neglecting small deviations from the equilubrium point. We propose the extended model that takes into account the effe...
Article
Human behavior during the process of virtual inverted pendulum balancing in viscous environment is analyzed. The results of the virtual experiments are compared to the results of previous studies on so called dynamical trap effect. It is shown that the phase trajectories and phase variables distributions of the virtual stick motion under human cont...
Chapter
We present the experimental evidence of the dynamical traps model describing the human fuzzy rationality in the dynamical systems framework. The results of the experiments on virtual stick balancing are compared to the results of the previous studies on the dynamical trap effect. According to the results obtained, we suggest that the dynamical trap...
Article
Full-text available
We develop a mathematical description of human fuzzy rationality. Human operators controlling dynamical systems are often incapable of precisely identifying and implementing the desired control strategy. The operator of a dynamical system treats the current value of the control effort as acceptable if it deviates insignificantly from the desired, o...
Conference Paper
Full-text available
We propose the dynamical model describing the effect of boredom in the human learning process. It is shown numerically that the instability may appear in the dynamics of the system corresponding to the simple case of the single agent performing repeated choice between two alternatives. The discovered patterns of the periodic preference oscillations...
Article
Full-text available
We analyze data collected during the series of experiments aimed at elucidation of basic properties of human perception, namely, the limited capacity of ordering events, actions, etc. according to their preference. Previously it was shown that in a wide class of human-controlled systems small deviations from the equilibrium position do not cause an...

Network

Cited By