
Dražen BrščićKyoto University | Kyodai · Department of Social Informatics
Dražen Brščić
Doctor of Engineering
About
79
Publications
15,748
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
1,217
Citations
Introduction
Drazen Brscic currently works at the Department of Social Informatics, Kyoto University. He does research in Mobile Robotics and Human-Robot Interaction.
Additional affiliations
July 2023 - June 2024
January 2011 - September 2016
October 2008 - October 2010
Publications
Publications (79)
A method for tracking the position, orientation, and height of persons in large public environments is presented. Such a piece of information is known to be useful both for understanding their actions, as well as for applications such as human-robot interaction. We use multiple 3-D range sensors, which are mounted above human height to have less oc...
A robot working among pedestrians can attract crowds of people around it, and consequentially become a bothersome entity causing congestion in narrow spaces. To address this problem, our idea is to endow the robot with capability to understand humans' crowding phenomena. The proposed mechanism consists of three underlying models: a model of pedestr...
The Intelligent Space is an area (room, public space, etc.) that has networked distributed sensors, which can be used for observing and gathering information from the space. The main objective for the introduction of Intelligent Space is to provide services to humans inside the space. These services can be either informational, such as the ones pro...
Beyond mere formality, small talk plays a pivotal role in social dynamics, serving as a verbal handshake for building rapport and understanding. For conversational AI and social robots, the ability to engage in small talk enhances their perceived sociability, leading to more comfortable and natural user interactions. In this study, we evaluate the...
As foundation models increasingly permeate sensitive domains such as healthcare, finance, and mental health, ensuring their behavior meets desired outcomes and social expectations becomes critical. Given the complexities of these high-dimensional models, traditional techniques for constraining agent behavior, which typically rely on low-dimensional...
Service robots in public spaces can sometimes become victims of ‘abuse’, manifesting as persistent blocking of the robot’s path, physical violence such as pushing or pulling, or abusive language. This kind of abuse can be a serious obstacle to the deployment of robots. We studied the possibility of mitigating obstructive behaviour towards the robot...
Avatar robots allow a teleoperator to interact with the people and environment of a remote place. Malicious operators can use this technology to perpetrate malicious or low-moral actions. In this study, we used hazard identification workshops to identify low-moral actions that are possible through the locomotor movement, cameras, and microphones of...
In this philosophical exploration, we investigate the concept of robotic moral environment interaction. The common view understands moral interaction to occur between agents endowed with ethical and interactive capacities. However, recent developments in moral philosophy argue that moral interaction also occurs in relation to the environment. Here...
This article presents a cross-cultural replication of recent work on productively violating gender norms; specifically demonstrating that breaking norms can boost robot credibility while avoiding harmful stereotypes. In this work we demonstrate via a 3 (country) x 3 (robot behaviour) between-subject experiment that these findings replicate cross-cu...
Data-driven imitation learning enables service robots to learn social interaction behaviors, but these systems cannot adapt after training to changes in the environment, such as changing products in a store. To solve this, a novel learning system that uses neural attention and approximate string matching to copy information from a product informati...
We studied the use of a rotating multi-layer 3D Light Detection And Ranging (LiDAR) sensor (specifically the Velodyne HDL-32E) mounted on a social robot for the estimation of features of people around the robot. While LiDARs are often used for robot self-localization and people tracking, we were interested in the possibility of using them to estima...
Detecting and recognizing low-moral actions in public spaces is important. But low-moral actions are rare, so in order to learn to recognize a new low-moral action in general we need to rely on a limited number of samples. In order to study the recognition of actions from a comparatively small dataset, in this work we introduced a new dataset of hu...
Social robots often have expressive faces. However, it is not always clear how to design expressions that show a certain emotion. We present a method for a social robot to learn the emotional meaning of its own facial expressions, based on which it can automatically generate faces for any emotion. The robot collects data from an imitation game wher...
Various diseases are diagnosed using medical imaging used for analysing internal anatomical structures. However, medical images are susceptible to noise introduced in both acquisition and transmission processes. We propose an adaptive data-driven image denoising algorithm based on an improvement of the intersection of confidence intervals (ICI), ca...
Being determined by human social behaviour, pedestrian group dynamics may depend on “intrinsic properties” such as the purpose of the pedestrians, their personal relation, gender, age, and body size. In this work we investigate the dynamical properties of pedestrian dyads (distance, spatial formation and velocity) by analysing a large data set of a...
r, x and y dependence on minimum age.
Black circles: r; red squares: x; blue triangles: y. Dashed lines provide standard error confidence intervals. The point at 75 years corresponds to the “70 years or more” slot.
(EPS)
Dependence of V on minimum age at different densities.
Blue squares: 0 ≤ ρ < 0.05 ped/m2 range; red circles: 0.15 ≤ ρ < 0.2 ped/m2 range. The point at 75 years corresponds to the “70 years or more” slot. Dashed lines show standard error confidence intervals.
(EPS)
r dependence on minimum height.
Data points shown by red circles. Continuous black line: linear best fit with r = α + βh, α = 1390 mm, β = -3.35. Dashed lines provide standard error confidence intervals, the point at 135 cm corresponds to the “less than 140 cm” slot, the one at 185 cm to the “more than 180 cm” slot.
(EPS)
Comparison between minimum, average and maximum height.
(PDF)
V dependence on minimum age.
Dashed lines provide standard error confidence intervals. The point at 75 years corresponds to the “70 years or more” slot.
(EPS)
x dependence on minimum height.
Data points shown by red circles. Continuous black line: linear best fit with x = α + βh, α = 258 mm, β = 2.42. Dashed lines provide standard error confidence intervals, the point at 135 cm corresponds to the “less than 140 cm” slot, the one at 185 cm to the “more than 180 cm” slot.
(EPS)
Statistical analysis of observables.
(PDF)
Statistical analysis of overall probability distributions.
(PDF)
Accounting for other effects.
(PDF)
V dependence on minimum height.
Data points shown by red circles. Continuous black line: linear best fit with V = α + βh, α = 715 mm/s, β = 2.81 s−1. Dashed lines provide standard error confidence intervals, the point at 135 cm corresponds to the “less than 140 cm” slot, the one at 185 cm to the “more than 180 cm” slot.
(EPS)
Group trajectories and coding data set.
(ZIP)
y dependence on minimum height.
Data points shown by red circles. Continuous black line: linear best fit with y = α + βh, α = 1530 mm, β = -7.01. Dashed lines provide standard error confidence intervals, the point at 135 cm corresponds to the “less than 140 cm” slot, the one at 185 cm to the “more than 180 cm” slot.
(EPS)
x dependence on minimum height for different genders.
Red circles: two females; blue squares: two males (continuous lines: linear fits x = α + βh, αfemale = 154 mm, βfemale = 2.98; αmale = 211 mm, βmale = 2.79). The points at 135 and 185 cm represent the “less than 140” and “more than 180” cm slots). Dashed lines show confidence intervals.
(EPS)
Dependence on average and maximum age.
(PDF)
Being determined by human social behaviour, pedestrian group dynamics depends on "intrinsic properties" of the group such as the purpose of the pedestrians, their personal relation, their gender, age, and body size. In this work we quantitatively study the dynamical properties of pedestrian dyads by analysing a large data set of automatically track...
In this work, we were interested in creating a robot service for offering help to people who appear to be in need for guidance. In order to achieve that, we first developed a technique to detect pedestrians who walk in an atypical way (e.g., people who do not know their way). In our approach, a motion model of typical pedestrians developed in our p...
Social robots working among pedestrians can attract crowds of people around them and consequently become bothersome entities causing congestion in narrow spaces. This in turn can affect the comfort of pedestrians who wish to pass through. To address this problem, our idea is to endow the robot with three capabilities: anticipating pedestrian crowdi...
The use of 3D range sensors for human position tracking has grown in recent years, especially for augmenting robotic sensing for human-robot interaction. However, extrinsic calibration of the relative positions of 3D range sensors is difficult, due to their limited range, narrow field of view, and distortion at large distances. 2D laser range finde...
We study the dependence on crowd density of the spatial size, configuration, and velocity of pedestrian social groups. We find that, in the investigated density range, the extension of pedestrian groups in the direction orthogonal to that of motion decreases linearly with the pedestrian density around them, both for two- and three-person groups. Fu...
Social robots working in public space often stimulate children's curiosity. However, sometimes children also show abusive behavior toward robots. In our case studies, we observed in many cases that children persistently obstruct the robot's activity. Some actually abused the robot by saying bad things, and at times even kicking or punching the robo...
Robotic technology is gradually entering our everyday environments and it is expected that in future social robots will be used to provide various services to users of public spaces. However, robots nowadays still lack the abilities to sense and understand their surroundings, and even more importantly, they lack the knowledge on the persons' usual...
We tracked the movement of people during a one year span in a shopping mall to study pedestrian behaviour under different density and usage conditions. We analyse the time and space dependence of pedestrian density and velocity, showing good agreement with the predictions of our “social norm” collision model. We also show that along with the expect...
We recently introduced a potential to describe pedestrian interaction in walking groups. The potential was used to derive the spatial distribution and velocity of small groups under scarce density conditions and its predictions are in good agreement with observations. In the present work we apply the same method to a new data set regarding pedestri...
Knowledge about space usage from variables such as density and walking speed could support a variety of service applications. However, there is not much knowledge on how the usage of space changes during extended periods of time and what affects the changes. We have installed a person tracking system in a large area of a shopping center and collect...
An important ability for mobile robots is to process multiple tasks in complex environments. Since the sensor resources on a robot are limited, it is necessary to distribute the sensors' atention to different tasks along the time scale. A human inspired temporal attention control method is proposed, which aims at detecting multiple objects and esti...
An important ability for mobile robots is to process multiple tasks in complex environments. Since the sensor resources on a robot are limited, it is necessary to distribute the sensors attention to different tasks along the time scale. This paper proposes a temporal attention control method which aims at detecting multiple objects and estimating t...
Real time human body motion estimation plays an important role in the perception for robotics nowadays, especially for the applications of human robot interaction and service robotics. In this paper, we propose a method for real-time 3D human body motion estimation based on 3-layer laser scans. All the useful scanned points, presenting the human bo...
There exist various applications where tracking of humans or robots in
an area is needed. An example of such applications are Intelligent
Spaces, where humans and robots share a common space and their positions
are tracked by a system of sensors in the space. In this paper a system
for tracking both humans and robots that utilizes laser range finde...
The overall performance of a robotic system is commonly expressed by a single scenario-specific metric which is supposed to be optimized. However, the metric describing the performance of a single subtask within a scenario may be different. Nevertheless, the scenario performance is most likely dependent on the subtask performances but a mutual tran...
Cognition in technical systems is especially relevant for the interaction with humans. We present a newly emerging application
for autonomous robots: companion robots that are not merely machines performing tasks for humans, but assistants that achieve joint goals with humans. This collaborative aspect entails specific challenges for AI and robotic...
Robotic systems operating in the real-world have to cope with unforeseen events by determining appropriate decisions based on noisy or partial knowledge. In this respect high functional robots are equipped with many sensors and actuators and run multiple processing modules in parallel. The resulting complexity is even further increased in case of c...
In this paper, a mobile robot navigation method based on the observation of human walking is presented. The proposed method extracts paths that are frequently used by human and builds a topological map of the environment from the observed human walking paths. Unlike the conventional methods, the proposed method enables us to generate paths which ar...
This work considers the joint use of robot onboard sensors and a network of sensors distributed in the environment for tracking the position of the robot and other objects. This is motivated by our research on Intelligent Spaces, which combine the use of distributed sensors with mobile robots to provide various services to users. Here we analyze th...
This paper presents a novel robotic architecture that is suitable for modular distributed multi-robot systems. The architecture
is based on an interface supporting real-time inter-process communication, which allows simple and highly efficient data exchange
between the modules. It allows monitoring of the internal system state and easy logging, thu...
This work considers the joint use of robot onboard sensors and a network of sensors distributed in the environment for tracking the position of the robot and other objects. This is motivated by our research on Intelligent Spaces, which combine the use of distributed sensors with mobile robots to provide various services to users. Here we analyze th...
In this paper we present a method for estimating the position of mobile robots using a combination of both robotpsilas onboard sensors and sensors at fixed locations in the environment, where we use laser range finders as sensors. This is a situation which arises in so-called intelligent spaces, where there are both static sensors and mobile robots...
In this paper we discuss methods for estimating the position of objects in environments that have both distributed sensing devices as well as mobile robots equipped with sensors - intelligent spaces. The aim is to use both types of devices for the estimation. We focus on the utilization of laser range finder devices as sensors, due to their good se...
By virtually re-creating and visualizing an intelligent space (iSpace) geographically far from the original version, one opens up the possibility of remote control and interaction between the real iSpace and the virtual copy. Here we present the required components for such a mixed environment: the actual iSpace in a form of a laboratory built for...
This paper deals with sensing using laser range finders and improving or altering their characteristics using mirrors. The idea that is presented here is to use one or multiple mirrors to change the direction of the laser ray, thereby resulting in some characteristics that are not available to a simple laser range finder, such as: scanning in multi...
In this paper we present an approach to tracking of humans in spaces with ubiquitous distributed sensors and actuators - Intelligent Spaces. In order to be able to implement services that depend on the position of humans, a reliable tracking method is needed. In addition to the sensors distributed in space, mobile sensors are also considered. A mob...
This paper deals with the problem of object tracking and environment mapping inside a space with distributed sensors - intelligent space. In a conventional approach the distributed sensors are used for these tasks, however since the sensors are static this has several disadvantages. In this paper in addition to static sensors we introduce the use o...
This paper presents our implementation of the control of mobile robot as actuator in intelligent space. The intelligent space has distributed sensors that can be used for tracking and mapping the space. Furthermore, it can use these measurements to control a mobile robot in the space. This way physical acting inside the space can be achieved. Here...
In this paper, we introduce a basic framework of intelligent space (iSpace) and automated calibration of the distributed sensors using mobile robots. iSpace is a room or area where many intelligent sensors and actuators are distributed and networked. In iSpace, the embedded sensors can monitor the whole environment by communicating with each other...
This paper deals with the problem of robot localization and object tracking inside a space with distributed sensors - Intelligent Space. In addition to static sensors distributed in the space, a mobile robot is used as a mobile sensor to gather additional information and improve the estimation. We discuss the characteristics of such a tracking syst...
In this paper we present an approach to tracking of humans and mobile robots in spaces with ubiquitous distributed sensors and actuators - Intelligent Spaces. In order to be able to implement services that depend on the position of humans, a reliable tracking method is needed. Also, for the implementation of mobile robot control it is important to...
In this paper we present the implementation of mobile robot control in the intelligent space (iSpace). The mobile robot in iSpace is primarily used as a mean of offering physical services to users, or as a mobile sensor for providing more details about the space. On the other hand, the distributed sensors in iSpace offer advantages in standard robo...
In this paper the problem mobile robot control in the Intelligent Space (iSpace) is analyzed. The mobile robot in iSpace is used as a mean of offering physical services to users. On the other hand, using the distributed sensors in iSpace offers advantages in standard robot control tasks. Advantages in tasks such as localization, mapping and path pl...
This paper presents the current work on the development of a tool for remote control of mobile robots. The tool consists of a local controller on the robot side and a user interface for simulation and remote control that connects with the robot through the network. The user interface is implemented as an HTML page with a Java applet for remote cont...
In this paper, the design of available bit rate (ABR) congestion control in ATM (asynchronous transfer mode) networks is considered. The goals of congestion control are high link utilization, low cell loss, and low network delay. Various algorithms for congestion control can be found in the literature. Most of them are based on a network model, whi...