Robots

George Mason PhD student looks at deception and human-robot interactions

Colleen Rich — Thu, 13 Feb 2025 14:20:46 +0000

George Mason PhD student looks at deception and human-robot interactions Colleen Rich Thu, 02/13/2025 - 09:20

How likely are humans to trust a robot, especially if that robot has the capacity to lie? This is the question 海角社区 psychology doctoral candidate Andres Rosero is exploring in his research on human-robot interaction.

鈥淎s robots become more integrated in human society, their roles will transition into those of a collaborative nature rather than as tools used by people,鈥� said Rosero, who works in Applied Psychology and Autonomous Systems (ALPHAS) Lab in the Human Factors and Applied Cognition Program. 鈥淚n response, these robots must be programmed with enough social awareness to navigate complex interpersonal interactions to build relationships and maintain a positive interaction with the humans they share their environment with.鈥�

Almost 500 participants took part in Rosero's study 鈥淗uman perceptions of social robot deception behaviors: an exploratory analysis,鈥� which he conducted with George Mason graduate teaching assistant Harris Kelly and psychology professor Elizabeth Phillips. This study gauges how likely participants are to accept a lie told by a robot in various situational contexts and is one of the three manuscripts that comprise Rosero's dissertation.

Participants ranked specific scenarios involving robot deception and evaluated how deceptive the lie was, whether they approved of the robot鈥檚 actions, and if the robot鈥檚 behavior could be justified. The study placed these scenarios into three different environments: medical, domestic, and retail.

鈥淭he goal is to examine human perceptions of AI and robot collaborations across different complex social interactions,鈥� explains Rosero, who received an MA in psychology from George Mason in 2022. 鈥淭his study is one of two that examine moral norms in robots and how in breaking these moral norms, humans accept and justify the robot's behaviors.鈥�

Each environment presented a unique quandary for the participant. For example, in the medical environment, the robot lied to a patient with Alzheimer鈥檚, telling the patient that her deceased husband was coming home. In the other environments, the robot was evasive rather than uttering false statements.

George Mason PhD candidate Andres Rosero, pictured here with "Pepper," is exploring deception and human-robot interactions. Photo by Ron Aira/Office of University Branding

In the domestic environment, the robot did not reveal to the individual that they were being secretly filmed. And in the retail environment, the robot did not disclose that it was capable of completing an assigned task and didn鈥檛 require human assistance. Overall, participants widely believed the robot鈥檚 lie in the first scenario, but once the robot鈥檚 capacity for deception and manipulation was revealed, they became less trusting. They also were more likely to say that the robot鈥檚 behavior in the medical environment was justified than in the other two scenarios.

鈥淎ny technology that is designed with the intention of being utilized by people is an intersection of that technology and the humanities,鈥� said Rosero. 鈥淥ur challenge as psychologists is to design experiments that properly explore this interaction to provide direction to the development of these technologies in the real world.鈥�

Technology鈥檚 ability to potentially conceal its true capabilities remains a concern of Rosero, as a focus on human-robot dynamics continues to fuel his research. "I am planning on defending my dissertation in the summer, and I am hoping to continue doing human factors research,鈥� says Rosero. 鈥淢y goal is to conduct impactful research that can assist people in their interactions with cutting-edge technology.鈥�

When offering advice to students in an age of artificial intelligence and its advancements, Rosero recommends understanding 鈥渢he practical applications of your work.鈥�

鈥淎s an applied psychologist, one of the most important questions I ask myself is how my research can be applied in the real world,鈥� he said. 鈥淚t is important to understand how your work helps to build upon the current knowledge of the field and how it could impact the development of the larger technology in society.鈥�

Learn more about AI research at George Mason

Topics

Artificial Intelligence

College of Humanities and Social Sciences

Alumni

Advancing sensor tech for foggy situations

Nathan Kahl — Mon, 13 Jan 2025 13:15:50 +0000

Advancing sensor tech for foggy situations Nathan Kahl Mon, 01/13/2025 - 08:15

Devices that rely on sensors to accurately navigate and perceive the world around them are more and more commonplace, from drones to autonomous vehicles to ground robots on rescue missions. Parth Pathak, an associate professor in the Department of Computer Science at 海角社区, is working to ensure the sensors have 20/20 vision.

From left, Rezoan Ahmed Nazib, Parth Pathak, and Ahmad Kamari with a rescue robot that can "see" through smoke and fog. Photo provided

Pathak received $660K in funding from the Army Research Office (ARO) for this work, some of which is done in collaboration with colleagues at the University of California, Davis, where he did his post-doc.

鈥淐onventional sensors rely on cameras or LiDAR (light detection and ranging) to pursue objects around them, but they don't work very well when there's smoke, fog, or generally a visually degraded environment,鈥� said Pathak. 鈥淏ut the mmwave wireless radar sensors that we are working on don't get affected by that. If there is dirt on the sensor, well, that's okay. They can see through things and see around things."

Imagine a rescue robot going into a building filled with smoke, trying to navigate with little to no visibility, Pathak said. "These wireless sensors can enable them to perceive the environment and even self-localize without cameras, LiDARs, or other positioning systems.鈥�

Another positive aspect of the devices is that while they can sense鈥hey don鈥檛 sense too much, which is important for privacy concerns. The disadvantage, of course, is that when a sensor depicts an object such as a car, the resolution is not particularly good, and the images are 鈥渘oisy.鈥� Pathak is not just improving navigation and perception, but using multiple robots, for example, cooperatively. In a rescue mission, a swarm of robots can share their data, allowing them to collectively 鈥渟ee鈥� a better picture.

Photo provided

鈥淭hey can self-localize based on what they see, like how our brains work. But the robots only have wireless sensors to rely on, so part of the work is developing very good signatures of what they see from these very low resolution and noisy images,鈥� said Pathak. 鈥淲e can build 3D models of a room by scanning it through the wireless sensors and using machine learning to capture and recreate every minute detail. This is something that these sensors were never designed for. We are developing custom-tailored deep learning models of wireless sensing, essentially pushing the limits of what they can perceive using wireless signals.鈥�

In addition to the research, ARO鈥檚 funding also supports testbed-to-prototype development and solution evaluation.

Pathak and colleagues published this research at the Association for Computing Machinery鈥檚 ACM Mobicom conference and have submitted it to other conferences for potential publication. Two PhD students from his team, Ahmed Kamari and Rezoan Ahmed Nazib, are working actively on the project, along with three high school students who participated in prototyping over the summer as part of George Mason's Aspiring Scientists Summer Internship Program.

Connect with Computer Science at 海角社区

In This Story

Parth Pathak

Topics

Tech Talent Investment Program (TTIP)

Aspiring Scientists Summer Internship Program (ASSIP)

Artificial Intelligence

Science and engineering meet to create new surface water robot

Sarah Holland — Tue, 17 Oct 2023 13:35:06 +0000

Science and engineering meet to create new surface water robot Sarah Holland Tue, 10/17/2023 - 09:35

In his research on freshwater systems in the DC/Virginia area, 海角社区 College of Science professor R. Christian Jones was spending much of his time hauling boats. Too much, he thought.

McCue and Li with the autonomous surface water vehicle. Photo by Evan Cantwell/海角社区.

鈥淚n order to take a sample from a pond,鈥� he said, 鈥淚 would need to haul a boat in, put the equipment in, launch it, and then bring it all back. It would add at least an hour and required the body of water to have an access point for a boat.鈥�

As the director of Mason鈥檚 Potomac Environmental Research and Education Center (PEREC), Jones knew of a colleague who also works at the Potomac Science Center (PSC) where PEREC is housed, and who could help with this conundrum. He approached College of Engineering and Computing professor Leigh McCue and undergraduate student Ze Li with an idea: a machine that could go out on the pond, skim for plankton samples and collect water samples, and return to shore鈥攁ll while the researcher remains on land.

This project is part of a larger grant from the National Science Foundation for Persistent and Accessible Maritime Monitoring (PAMM), of which McCue is the lead investigator. The multiyear grant鈥攁warded in 2022 for more than $500,000鈥攆ocuses on increasing educational, research, and robotics operations and development for students ranging from sixth grade to graduate level, in order to improve the applications of and expanded the use of unmanned marine vehicles. It also includes making such vehicles more accessible for individuals with motion limitations, which in turn can increase accessibility for all researchers.

鈥淩esearchers around the globe are utilizing robotics to conduct maritime research, which is an increasingly critical field of study,鈥� explained McCue. 鈥淭hrough this grant, we鈥檙e developing more affordable maritime research tools to improve access for great science, whether citizen science or research-grade science. This project fit nicely into that mission.鈥�

The autonomous surface water device created by Li this summer was built from scratch using CAD modeling and 3D printed materials. Li鈥檚 experience working with robotics through extracurriculars like his job with Starship Technologies鈥攖he company that manages the famous food robots seen rolling around campus鈥攁nd the Mason Innovation Exchange鈥檚 (MIX) 3D printing training helped him navigate the challenges of creating this brand-new machine.

"We thought it was more beneficial to create something new by developing our design around an open-source hull model," Li said. 鈥淭here鈥檚 more opportunity for us to iterate on the prototype.鈥�

The team hopes to continue to improve the machine鈥檚 design, now that it鈥檚 being field-tested by Jones: improved autonomous capabilities and controls are both on the short list of potential improvements. Li also sees a potential for expanded testing of such data points as water temperature, turbidity, and salinity.

Jones predicts that this machine will be a boon for both access and efficiency. 鈥淭he number of accessible ponds will increase dramatically with this, and we鈥檒l be able to sample up to eight in a day instead of just one or two,鈥� Jones said.

The machine will also allow for more immediate responses to sudden, unpredictable, and time-sensitive events, like taking samples immediately after storms. Jones even sees possible uses for this machine to take samples during major pollution events, keeping the researchers safe from exposure to harmful chemicals while still acquiring necessary data.

Jones emphasized that this project was made possible by the collaboration between the two colleges. 鈥淎t a place like PSC where we鈥檙e all working together, seeing each other's labs and hearing about research, this sort of collaboration comes naturally,鈥� he said. 鈥淚t鈥檚 a beautiful opportunity for us all to become better researchers and do better science.鈥�

Jones, McCue, and Li outside PSC. Photo by Evan Cantwell/海角社区.

In This Story

Leigh McCue-Weil

Learn more about PEREC and its research

Design your own creations at the MIX

When robots meet sumo wrestling

Tama Moni — Mon, 25 Apr 2022 17:50:52 +0000

When robots meet sumo wrestling Tama Moni Mon, 04/25/2022 - 13:50

See Our Battlebots in Action

Systems Engineering students at the Norwalk Havoc Combat League on March 26.

From left to right: Rashed Almazrouei, Brian Romero, Nicholas Lechner, and

Sean Becker (team lead).

Battlebots is a nationally televised competition where robots battle in a closed arena. It is a breathtaking spectacle with robots colliding at high speeds and sparks flying. The winning robot must get a high score by hitting the opponent multiple times and pushing the opponent around the arena.

An enterprising team of Systems Engineering students in their Senior Design Capstone course designed, built, and tested a remotely controlled robot to compete in the 12-pound division in the Norwalk Havoc Robot Combat League (NHRL).

鈥淭he competition is unbelievably thrilling. The tension in the maintenance and repair bay preparing for the duel is high. Then you put your robot in the arena, and your heart is pumping at 120 beats per minute. Sparks flying, fans cheering. Whew!鈥� said Brian Romero, a Systems Engineering student.

The team, led by nationally ranked combat robotics builder and Systems Engineering student Sean Becker says: 鈥淚n the Systems Engineering class, we conducted a detailed analysis of the alternative attacking and defending mechanisms that are mounted on the robots.鈥� The team built a Monte Carlo simulation and played out bouts between robots with different attack and defense mechanisms. 鈥淏ased on the simulation, we came up with a unique design that attacks the opponent where they are least protected,鈥� explained Sean Becker.

鈥淲e also took a step back and conducted a thorough design and analysis of the Life-cycle of a robot in the competition,鈥� explained Systems Engineering student Nicholas Lechner. 鈥淭his led us to realize the importance of modularity in the robot design.鈥� Teams can have only 20 minutes between bouts to disassemble the robot and replace malfunctioning parts. 鈥淚f you have ever watched a Battlebot fight, you know how much damage is done,鈥� says Nicholas.

The team developed CAD designs and ran a Finite Elements Analysis on the components. The team fabricated the components, assembled, and tested the robot. 鈥淲e broke a lot of components in testing and had to go back to the drawing board to redesign over and over again,鈥� explained Sean Becker. 鈥淚 never really appreciated the importance of testing, testing, testing,鈥� says Brian Romero.

鈥淲e also practiced and timed the maintenance and repair to be ready for the competitions,鈥� says Systems Engineering student Rashed Almazrouei. 鈥淚t is like a Formula One race car pit stop. The parts and tools have to be lined up, and everyone has a specific role. The interaction has to be choreographed perfectly,鈥� Rashed explained.

The team drove up to Norwalk, Connecticut, to compete in the Norwalk Havoc Robot Combat League on March 26, 2022. The robot won four six bouts and finished third overall.

鈥淎s systems engineers, and by applying the systems engineering methods, we had a big advantage over the competition,鈥� says Sean Becker. 鈥淭he Life-cycle analysis and the attack-defense simulation reduced the time and costs by learning in the digital world, what we would have to learn by competing in ten competitions.鈥�

鈥淲e would like to thank all our professors in the Systems Engineering department for sharing their wisdom with us,鈥� says Rashed. 鈥淎lso, your encouragement, support, and belief in us as engineers made a big difference,鈥� says Nicholas.

They are not out of the tournament yet. Since succeeding in the 12-pound class, the team is raising funding and applying to the 250-pound class Battlebot competition, which will premiere on the Discovery Channel.

To learn more about Systems Engineering, Robotics, and the Battlebot team, contact Systems Engineering and Operations Research Department Chair John Shortle.

Topics

Mason Engineering students and faculty compete at 99 Luftballoons competition

Anonymous — Fri, 08 Jan 2021 17:02:30 +0000

Mason Engineering students and faculty compete at 99 Luftballoons competition Anonymous (not verified) Fri, 01/08/2021 - 12:02

Left to right: Dinesh Karri, Robert Hooks, and Joseph Matthew Prince getting ready to compete at the Luftballoons competition at Indiana University.

It鈥檚 a bird, it鈥檚 a plane, it鈥檚 a Lighter-Than-Air (LTA) robotic shark blimp, which is what a team of 海角社区 students and faculty used to participate in the 99++ Luftballoons Competition at Indiana University on November 9 through 13.

The competition took place at the Indiana University Bloomington campus where people from Mason, the University of California Los Angeles, Indiana University at Bloomington, Pennsylvania State University, the Office of Naval Research, the Naval Surface Warfare Center 鈥� Crane Division, and the Army Research Laboratory competed in an aerial soccer match using remote-controlled LTA robots.

鈥淟TA robots don鈥檛 need any support to hold them in the air. Helicopters need propellers, but all LTA robots can stay in the air on their own. Instead, they need controls to move them about in the air,鈥� says Mason graduate student and competition teammate Joseph Prince Mathew.

Each team had defenders and seekers to protect their goal and score points against the other team. 鈥淚t got pretty competitive,鈥� says Dinesh Karri, another team member. 鈥淏ut it was so much fun.鈥�

Every team played each other, and the teams with the most points faced off at the end of the five-day event. 鈥淯nfortunately, we lost, but we had the most points overall throughout the week,鈥� says Mathew.

Mathew and Karri were working with Assistant Professor Feitian Zhang to develop an underwater glider as part of their PhD studies when they found out about the opportunity to bring their skills to the air. 鈥淚t was a change of medium, from underwater to air. The dynamics are pretty similar,鈥� says Mathew.

Robert Hooks, a junior undergraduate electrical engineering major, jumped on the project because of his interest in robotics and autonomous systems. 鈥淲hen I heard about it from one of my professors, I was very intrigued. It was a valuable and fun experience to learn hands-on,鈥� says Hooks.