David Feil-Seifer

University of Nevada, Reno, Department of Computer Science and Engineering, Faculty Member

Followers

182

Following

Co-authors

Public Views

I am an associate professor in Computer Science at the University of Nevada, Reno. My primary research interest is Socially Assistive Robotics (SAR). My research is motivated by the potential for SAR to address health-care crises that stem from a lack of qualified care professionals for an ever-growing population in need of personalized care.

Before I started at UNR, I was a Postdoctoral Associate at Yale University at the Social Robotics Lab under the direction of Prof. Brian Scassellati. In 2011, I was awarded a National Science Foundation Computing Innovation Fellowship to support my work.

I received my M.S. in Computer Science in 2007 and my Ph.D. in Computer Science in 2011 from the Viterbi School of Engineering (VSoE) at the University of Southern California. I worked in the Interaction Lab where my advisor was Prof. Maja Matarić. My research focused on socially assistive robotics (SAR), particularly the study of Human-Robot Interaction (HRI) for children with autism spectrum disorders (ASD).

I graduated from the University of Rochester in 2003 with a B.S. in Computer Science. While there I was a founding member of the Undergraduate Robot Research Team, winner of the 2002 AAAI Mobile Host Competition. We were advised by Prof. Chris Brown.
Supervisors: Brian Scassellati and Maja Mataric

less

InterestsView All (8)

Uploads

Papers by David Feil-Seifer

Perceived Social Intelligence Scales

PsycTESTS Dataset

A Distributed Control Framework of Multiple Unmanned Aerial Vehicles for Dynamic Wildfire Tracking

arXiv (Cornell University), Mar 19, 2018

Wild-land fire fighting is a hazardous job. A key task for firefighters is to observe the "fire f... more Wild-land fire fighting is a hazardous job. A key task for firefighters is to observe the "fire front" to chart the progress of the fire and areas that will likely spread next. Lack of information of the fire front causes many accidents. Using Unmanned Aerial Vehicles (UAVs) to cover wildfire is promising because it can replace humans in hazardous fire tracking and significantly reduce operation costs. In this paper we propose a distributed control framework designed for a team of UAVs that can closely monitor a wildfire in open space, and precisely track its development. The UAV team, designed for flexible deployment, can effectively avoid in-flight collisions and cooperate well with neighbors. They can maintain a certain height level to the ground for safe flight above fire. Experimental results are conducted to demonstrate the capabilities of the UAV team in covering a spreading wildfire.

Download

Securing a UAV Using Individual Characteristics From an EEG Signal

arXiv (Cornell University), Apr 14, 2017

Unmanned aerial vehicles (UAVs) have gained much attention in recent years for both commercial an... more Unmanned aerial vehicles (UAVs) have gained much attention in recent years for both commercial and military applications. The progress in this field has gained much popularity and the research has encompassed various fields of scientific domain. Cyber securing a UAV communication has been one of the active research field since the attack on Predator UAV video stream hijacking in 2009. Since UAVs rely heavily on on-board autopilot to function, it is important to develop an autopilot system that is robust to possible cyber attacks. In this work, we present a biometric system to encrypt the UAV communication by generating a key which is derived from Beta component of the EEG signal of a user. We have developed a safety mechanism that would be activated in case the communication of the UAV from the ground control station gets attacked. This system has been validated on a commercial UAV under malicious attack conditions during which we implement a procedure where the UAV return safely to a 'home' position.

Download

Using Machine Learning Approach for Computational Substructure in Real-Time Hybrid Simulation

arXiv (Cornell University), Apr 4, 2020

Hybrid simulation (HS) is a widely used structural testing method that combines a computational s... more Hybrid simulation (HS) is a widely used structural testing method that combines a computational substructure with a numerical model for well-understood components and an experimental substructure for other parts of the structure that are physically tested. One challenge for fast HS or real-time HS (RTHS) is associated with the analytical substructures of relatively complex structures, which could have large number of degrees of freedoms (DOFs), for instance. These large DOFs computations could be hard to perform in real-time, even with the all current hardware capacities. In this study, a metamodeling technique is proposed to represent the structural dynamic behavior of the analytical substructure. A preliminary study is conducted where a one-bay one-story concentrically braced frame (CBF) is tested under earthquake loading by using a compact HS setup at the University of Nevada, Reno. The experimental setup allows for using a smallscale brace as the experimental substructure combined with a steel frame at the prototype full-scale for the analytical substructure. Two different machine learning algorithms are evaluated to provide a valid and useful metamodeling solution for analytical substructure. The metamodels are trained with the available data that is obtained from the pure analytical solution of the prototype steel frame. The two algorithms used for developing the metamodels are: (1) linear regression (LR) model, and (2) basic recurrent neural network (RNN). The metamodels are first validated against the pure analytical response of the structure. Next, RTHS experiments are conducted by using metamodels. RTHS test results using both LR and RNN models are evaluated, and the advantages and disadvantages of these models are discussed.

Download

Towards GPU-Accelerated PRM for Autonomous Navigation

Advances in intelligent systems and computing, 2020

Sampling based planning is an important step for longrange navigation for an autonomous vehicle. ... more Sampling based planning is an important step for longrange navigation for an autonomous vehicle. This work proposes a GPU-accelerated sampling based path planning algorithm which can be used as a global planner in autonomous navigation tasks. A modified version of the generation portion for the Probabilistic Road Map (PRM) algorithm is presented which reorders some steps of the algorithm in order to allow for parallelization and thus can benefit highly from utilization of a GPU. The GPU and CPU algorithms were compared using a simulated navigation environment with graph generation tasks of several different sizes. It was found that the GPU-accelerated version of the PRM algorithm had significant speedup over the CPU version (up to 78×). This results provides

Download

Birds of a Feather Flock Together: A Study of Status Homophily in HRI

Lecture Notes in Computer Science, 2021

Understanding Agency in Interactions Between ChildrenWith Autism and Socially Assistive Robots

Journal of human-robot interaction, Dec 25, 2017

Socially assistive robotics (SAR) has increasingly been shown to have potential as a tool for soc... more Socially assistive robotics (SAR) has increasingly been shown to have potential as a tool for social skills therapy for children with autism, a developmental disorder associated with atypical social development. This work presents the results of a study of robot agency on child-robot interactions involving children with autism. We describe the development of a SAR interaction scenario with both agent-like and object-like robot behaviors and present the results of a pilot study of six children with autism interacting with a humanoid robot with the full controller, as well as three types of control: a non-humanoid "box" robot with similar behavior (reduced morphological agency), a humanoid robot with random behavior (reduced behavioral agency), and a robotic toy (reduced morphological and behavioral agency). We find that the children can be divided into two groups depending on their reaction to the robot; for some children, the robot was an engaging object that elicited social behavior by providing novel and appealing sensory experiences (primarily bubbleblowing), while for other children, the robot was an agent and elicited social behavior through agentlike actions such as autonomous movement. We found that the first group had small differences between robot conditions and vocalized most with the bubble-blowing toy, while the second group vocalized most with the humanoid robots and looked less at the humanoid portion of the robot with reduced behavioral agency.

Download

Exploring the Use of a Drone to Guide Blind Runners

People with visual impairments have a hard time getting consistent physical exercise, as they can... more People with visual impairments have a hard time getting consistent physical exercise, as they can not do some exercises, such as run ning outside, without a sighted guide. People with visual impair ments have been shown to have higher spatial localization skills than sighted people, which lead us to believe that they could fol low a drone on a running-track environment. This paper presents a feasibility study where we investigate the ability to localize and fol low a low-cost flying drone in people with visual impairments. A Wizard of Oz style study was conducted with 2 blind participants. Our results indicate that blind individuals can accurately localize the drone and follow it. Qualitative results also indicate that the participants were comfortable with following the drone and had high efficacy when it came to following and localizing the drone. The study supports future development of a fully functioning pro totype.

Download

Exploring Human Compliance Toward a Package Delivery Robot

Socially-Aware Navigation: A Non-linear Multi-Objective Optimization Approach

arXiv (Cornell University), Nov 10, 2019

Mobile robots are increasingly populating homes, hospitals, shopping malls, factory floors, and o... more Mobile robots are increasingly populating homes, hospitals, shopping malls, factory floors, and other human environments. Human society has social norms that people mutually accept; obeying these norms is an essential signal that someone is participating socially with respect to the rest of the population. For robots to be socially compatible with humans, it is crucial for robots to obey these social norms. In prior work, we demonstrated a Socially-Aware Navigation (SAN) planner, based on Pareto Concavity Elimination Transformation (PaCcET), in a hallway scenario, optimizing two objectives so that the robot does not invade the personal space of people. This paper extends our PaCcET based SAN planner to multiple scenarios with more than two objectives. We modified the Robot Operating System's (ROS) navigation stack to include PaCcET in the local planning task. We show that our approach can accommodate multiple Human-Robot Interaction (HRI) scenarios. Using the proposed approach, we achieved successful HRI in multiple scenarios like hallway interactions, an art gallery, waiting in a queue, and interacting with a group. We implemented our method on a simulated PR2 robot in a 2D simulator (Stage) and a pioneer-3DX mobile robot in the real-world to validate all the scenarios. A comprehensive set of experiments shows that our approach can handle multiple interaction scenarios on both holonomic and non-holonomic robots; hence, it can be a viable option for a Unified Socially-Aware Navigation (USAN). CCS Concepts: • Mathematics of computing → Mathematical optimization; • Human-centered computing; • Computer systems organization → Robotics;

Download

Embodiment, Situatedness, and Morphology for Humanoid Robots Interacting with People

Springer eBooks, Oct 10, 2018

B<sup>3</sup>IA: A control architecture for autonomous robot-assisted behavior intervention for children with Autism Spectrum Disorders

This paper describes a novel control architecture, B 3 IA, designed to address the challenges of ... more This paper describes a novel control architecture, B 3 IA, designed to address the challenges of developing autonomous robot systems for use as behavior intervention tools for children with Autism Spectrum Disorders (ASD). Our goal is to create a system that can be easily adapted for use by nonroboticists engaged in ASD therapy. B 3 IA is a behavior-based architecture for control of socially assistive robots using humanrobot interaction in the ASD context. We hypothesize that the organization of a robot control architecture is important to the success of a robot-assisted intervention, because the success of such intervention hinges on the behavior of the robot. We detail the organization of B 3 IA and present preliminary results from experiments that begin to experimentally test this hypothesis.

Download

A distributed control framework for a team of unmanned aerial vehicles for dynamic wildfire tracking

Wildland fire fighting is a very dangerous job, and the lack of information of the fire front is ... more Wildland fire fighting is a very dangerous job, and the lack of information of the fire front is one of main reasons that causes many accidents. Using unmanned aerial vehicle (UAV) to cover wildfire is promising because it can replace human in hazardous fire tracking and save operation costs significantly. In this paper we propose a distributed control framework designed for a team of UAVs that can closely monitor a wildfire in open space, and precisely track its development. The UAV team, designed for flexible deployment, can effectively avoid in-flight collision as well as cooperate well with other neighbors. Experimental results are conducted to demonstrate the capabilites of the UAV team in covering a spreading wildfire.

Download

The Effectiveness of Multi-Label Classification and Multi-Output Regression in Social Trait Recognition

Sensors, Jun 16, 2021

This article is an open access article distributed under the terms and conditions of the Creative... more

Download

Development of a Swarm UAV Simulator Integrating Realistic Motion Control Models For Disaster Operations

arXiv (Cornell University), Apr 24, 2017

Simulation environments for Unmanned Aerial Vehicles (UAVs) can be very useful for prototyping us... more Simulation environments for Unmanned Aerial Vehicles (UAVs) can be very useful for prototyping user interfaces and training personnel that will operate UAVs in the real world. The realistic operation of such simulations will only enhance the value of such training. In this paper, we present the integration of a model-based waypoint navigation controller into the Reno Rescue Simulator for the purposes of providing a more realistic user interface in simulated environments. We also present potential uses for such simulations, even for real-world operation of UAVs.

Download

Using a Machine Learning Approach for Computational Substructure in Real-Time Hybrid Simulation

Conference proceedings of the Society for Experimental Mechanics, Sep 13, 2020

Download

A compact task representation for hierarchical robot control

Robot tasks for real-world applications typically involve multiple paths of execution, where the ... more Robot tasks for real-world applications typically involve multiple paths of execution, where the same task can be achieved in different ways. This poses challenges with respect to the representation and execution of such tasks, as enumerating all possible execution paths leads to combinatorial increases in the size of the representation. We present a novel robot control architecture that addresses these challenges. The architecture 1) provides an efficient, compact encoding of tasks with multiple paths of execution, 2) uses the same compact representation as the controller that the robot will use to achieve its goals, 3) allows the robot to dynamically decide which execution path to follow using an activation spreading mechanism that relies on environmental conditions, and 4) provides a mechanism for robustness to changes in the environment during the task execution. We validate our architecture using a humanoid PR2 robot, showing that the robot dynamically selects a path of execution based on the current state of the environment, and is robust to environmental changes.

Download

Socially Assistive Robotics

Download

The Effects of Voice Pitch on Perceptions of Robots

Low Bandwidth Geometric Point Cloud Approximations for Subterranean Environments

Aerial robots are becoming increasingly important for exploration and mapping of unknown, subterr... more Aerial robots are becoming increasingly important for exploration and mapping of unknown, subterranean environments for scenarios where human labor is unsafe or costly such as mining and underground warfare. In order to explore and map subterranean environments LiDAR is needed, however, LiDAR maps can be extremely data intensive and are often unsuitable for wireless communication. In subterranean environments, robots are forced to use low bandwidth wireless communication channels. Because of the high bandwidth LiDAR data we currently have no way of communicating our maps over a low bandwidth wireless channel. In this paper, we present a solution for low bandwidth mapping using a geometric approximation of the LiDAR point cloud. We use RANSAC to fit cylinders to point cloud segments, adapting in real time for intersections and changes in tunnel curvature. The RANSAC models are able to condense the point cloud into a set of tuples containing shape, centroid coordinates, quaternions, and radius; thus enabling real time, low bandwidth map communication. The map can then be used to accelerate path planning in a constrained coordinate space using the cylindrical approximation and a dynamic, low bandwidth, connectivity graph. The algorithm is validated on a real time, subterranean robot in a commercial mine

David Feil-Seifer

Uploads

Papers by David Feil-Seifer

Log In