Investigating the Safety Implications of Implementing Artificial General Intelligence in Robots

Description
Due to monumental advancements in large language models (LLMs), such as OpenAI's ChatGPT, there is widespread interest in integrating this general AI’s capabilities into various applications, including robotics. However, the rush to deploy this technology has left safety as an

Due to monumental advancements in large language models (LLMs), such as OpenAI's ChatGPT, there is widespread interest in integrating this general AI’s capabilities into various applications, including robotics. However, the rush to deploy this technology has left safety as an afterthought, if at all. This study investigates the potential for LLM-fused robots to operate safely in real-world settings. This study begins with a review of ChatGPT, highlighting its capabilities and current challenges, particularly with integrating LLMs into robotics, and continues with similar applications as AI agents though APIs. To assess the safety implications of LLM-driven robots, the study presents experimental methods involving the navigation of a TurtleSim robot in 2D environments when given different scenarios. Various parameters are analyzed to determine the current capabilities of ChatGPT to understand how to adjust any agents it possesses based on the situation. Current findings reveal that ChatGPT-driven robots demonstrate adaptive behavior based on the scenario provided, indicating their potential for real-time safety adjustments and eliciting further research to ensure safe and successful integration of these robots into diverse work environments.
Date Created
2024-05
Agent

Mild Traumatic Brain Injury Executive Function Rehabilitation Through Serious Gamification

189315-Thumbnail Image.png
Description
The purpose of the present study is to explore a potential rehabilitation alternative/additive, when time, insurance, finances, or lack of knowledge are limitations for mild traumatic brain injury (mTBI) executive function (EF) rehabilitation. The experimental intervention involved two sets of

The purpose of the present study is to explore a potential rehabilitation alternative/additive, when time, insurance, finances, or lack of knowledge are limitations for mild traumatic brain injury (mTBI) executive function (EF) rehabilitation. The experimental intervention involved two sets of participants an experimental group and a control group. Participants within the experimental and control groups partook in initial (week 1) and final (week 6) EF and TBI assessments. The experimental group additionally participated in four weeks (weeks 2 - 5) of an experimental intervention in beta stage of a web-based application. The aim of the intervention was to train EF skills planning, organization, and cognitive flexibility through serious gamification. At the conclusion of the study, it was observed that participants within the experimental group achieved higher scores on the experimental executive function assessment when compared to the control group. The difference in scores can be attributed to the weekly participation in executive function training.
Date Created
2023
Agent

Unintentional Costs of Vehicle Warning Modality for Driving Hazards

187611-Thumbnail Image.png
Description
Proper allocation of attention while driving is imperative to driver safety, as well as the safety of those around the driver. There is no doubt that in-vehicle alerts can effectively direct driver attention. In fact, visual, auditory, and tactile alert

Proper allocation of attention while driving is imperative to driver safety, as well as the safety of those around the driver. There is no doubt that in-vehicle alerts can effectively direct driver attention. In fact, visual, auditory, and tactile alert modalities have all shown to be more effective than no alert at all. However, research on in-vehicle alerts has primarily been limited to single-hazard scenarios. The current research examines the effects of in-vehicle alert modality on driver attention towards simultaneously occurring hazards. When a driver is presented with multiple stimuli simultaneously, there is the risk that they will experience alert masking, when one stimulus is obscured by the presence of another stimulus. As the number of concurrent stimuli increases, the ability to report targets decreases. Meanwhile, the alert acts as another target that they must also process. Recent research on masking effects of simultaneous alerts has shown masking to lead to breakdowns in detection and identification of alarms during a task, outlining a possible cost of alert technology. Additionally, existing work has shown auditory alerts to be more effective in directing driver attention, resulting in faster reaction times (RTs) than visual alerts. Multiple Resource Theory suggests that because of the highly visual nature of driving, drivers may have more auditory resources than visual resources available to process stimuli without becoming overloaded. Therefore, it was predicted that auditory alerts would be more effective in allowing drivers to recognize both potential hazards, measured though reduced brake reaction times and increased accuracy during a post-drive hazard observance question. The current study did not support the hypothesis. Modality did not result in a significant difference in drivers’ attention to simultaneously occurring hazards. The salience of hazards in each scenario seemed to make the largest impact on whether participants observed the hazard. Though the hypothesis was not supported, there were several limitations. Additionally, and regardless, the study results did point to the importance of further research on simultaneously occurring hazards. These scenarios pose a risk to drivers, especially when their attention is allocated to only one of the hazards.
Date Created
2023
Agent

Investigating Human Advisor Interventions and Team Compliance in a Search-and-Rescue
Human-AI Team Task

Description

With the increasing popularity of AI and machine learning, human-AI teaming has a wide range of applications in transportation, healthcare, the military, manufacturing, and people’s everyday life. Measurement of human-AI team effectiveness is essential for guiding the design of AI

With the increasing popularity of AI and machine learning, human-AI teaming has a wide range of applications in transportation, healthcare, the military, manufacturing, and people’s everyday life. Measurement of human-AI team effectiveness is essential for guiding the design of AI and evaluating human-AI teams. To develop suitable measures of human-AI teamwork effectiveness, we created a search and rescue task environment in Minecraft, in which Artificial Social Intelligence (ASI) agents inferred human teams’ mental states, predicted their actions, and intervened to improve their teamwork (Huang et al., 2022). As a comparison, we also collected data from teams with a human advisor and with no advisor. We investigated the effects of human advisor interventions on team performance. In this study, we examined intervention data and compliance in a human-AI teaming experiment to gain insights into the efficacy of advisor interventions. The analysis categorized the types of interventions provided by a human advisor and the corresponding compliance. The finding of this paper is a preliminary step towards a comprehensive study on ASI agents, in which results from the human advisor study can provide valuable comparisons and insights. Future research will focus on analyzing ASI agents’ interventions to determine their effectiveness, identify the best measurements for human-AI teamwork effectiveness, and facilitate the development of ASI agents.

Date Created
2023-05
Agent

Evaluating Situational Awareness in Human-Robot Interaction

Description

I compared scores of situational awareness to mission performance scores from the Human-Robot Interaction Lab at the ASU campus. This study uses Roblox in a virtual environment to simulate a search and rescue environment. Higher situational awareness was seen to

I compared scores of situational awareness to mission performance scores from the Human-Robot Interaction Lab at the ASU campus. This study uses Roblox in a virtual environment to simulate a search and rescue environment. Higher situational awareness was seen to be positively correlated with mission performance scores, but the study is yet to be complete.

Date Created
2023-05
Agent

Decision-Making Biases in Cybersecurity: Measuring the Impact of the Sunk Cost Fallacy to Delay Attacker Behavior

172009-Thumbnail Image.png
Description
Cyber operations are a complex sociotechnical system where humans and computers are operating in an environments in constant flux, as new technology and procedures are applied. Once inside the network, establishing a foothold, or beachhead, malicious actors can collect sensitive

Cyber operations are a complex sociotechnical system where humans and computers are operating in an environments in constant flux, as new technology and procedures are applied. Once inside the network, establishing a foothold, or beachhead, malicious actors can collect sensitive information, scan targets, and execute an attack.Increasing defensive capabilities through cyber deception shows great promise by providing an opportunity to delay and disrupt an attacker once network perimeter security has already been breached. Traditional Human Factors research and methods are designed to mitigate human limitations (e.g., mental, physical) to improve performance. These methods can also be used combatively to upend performance. Oppositional Human Factors (OHF), seek to strategically capitalize on cognitive limitations by eliciting decision-making errors and poor usability. Deceptive tactics to elicit decision-making biases might infiltrate attacker processes with uncertainty and make the overall attack economics unfavorable and cause an adversary to make mistakes and waste resources. Two online experimental platforms were developed to test the Sunk Cost Fallacy in an interactive, gamified, and abstracted version of cyber attacker activities. This work presents the results of the Cypher platform. Offering a novel approach to understand decision-making and the Sunk Cost Fallacy influenced by factors of uncertainty, project completion and difficulty on progress decisions. Results demonstrate these methods are effective in delaying attacker forward progress, while further research is needed to fully understand the context in which decision-making limitations do and do not occur. The second platform, Attack Surface, is described. Limitations and lessons learned are presented for future work.
Date Created
2022
Agent

"Can I Consider You My Friend?" Moving Beyond One-Sided Conversation in Social Robotics

171933-Thumbnail Image.png
Description
As people begin to live longer and the population shifts to having more olderadults on Earth than young children, radical solutions will be needed to ease the burden on society. It will be essential to develop technology that can age with

As people begin to live longer and the population shifts to having more olderadults on Earth than young children, radical solutions will be needed to ease the burden on society. It will be essential to develop technology that can age with the individual. One solution is to keep older adults in their homes longer through smart home and smart living technology, allowing them to age in place. People have many choices when choosing where to age in place, including their own homes, assisted living facilities, nursing homes, or family members. No matter where people choose to age, they may face isolation and financial hardships. It is crucial to keep finances in mind when developing Smart Home technology. Smart home technologies seek to allow individuals to stay inside their homes for as long as possible, yet little work looks at how we can use technology in different life stages. Robots are poised to impact society and ease burns at home and in the workforce. Special attention has been given to social robots to ease isolation. As social robots become accepted into society, researchers need to understand how these robots should mimic natural conversation. My work attempts to answer this question within social robotics by investigating how to make conversational robots natural and reciprocal. I investigated this through a 2x2 Wizard of Oz between-subjects user study. The study lasted four months, testing four different levels of interactivity with the robot. None of the levels were significantly different from the others, an unexpected result. I then investigated the robot’s personality, the participant’s trust, and the participant’s acceptance of the robot and how that influenced the study.
Date Created
2022
Agent

Examination of the Relationship Between Customizable Heads-up-displays, Difficulty, and Player Satisfaction

171631-Thumbnail Image.png
Description
This paper documents a study of the relationship between heads up display (HUDs) customization and player performance. Additional measures capture satisfaction and prior gaming experience. The goal of this study was to develop a framework on which future Human Systems

This paper documents a study of the relationship between heads up display (HUDs) customization and player performance. Additional measures capture satisfaction and prior gaming experience. The goal of this study was to develop a framework on which future Human Systems Engineering studies could create games that are tailor made to examine a given area of interest. This study utilized a two-by-two design, where participants play a two-dimensional (2D) platformer game with a mechanic that incentivizes attention to the HUD. This study successfully developed a framework and was moderately successful in uncovering limitations and demonstrating areas for improvement in follow-on studies. Specifically, this study illuminated issues with the low amount of usable data caused by design issues, participant apathy, and reliance on self-reporting data collection. Extensions of this study can utilize this framework and should look to recruit beyond crowdsourcing platforms, collect more diverse data, reduce participant effort, and address other considerations that were found during execution.
Date Created
2022
Agent

Exploring the Relationship between Anticipatory Pushing of Information and Teammate Trust

161959-Thumbnail Image.png
Description
The prevalence of autonomous technology is advancing at a rapid rate and is becoming more sophisticated. As this technology becomes more advanced, humans and autonomy may work together as teammates in various settings. A crucial component of teaming is trust,

The prevalence of autonomous technology is advancing at a rapid rate and is becoming more sophisticated. As this technology becomes more advanced, humans and autonomy may work together as teammates in various settings. A crucial component of teaming is trust, but to date, researchers are limited in assessing trust calibration dynamically in human-autonomy teams. Traditional methods of measuring trust (e.g., Likert scale questionnaires) capture trust after the fact or at a specific time. However, trust fluctuates, and determining what causes this might give machine designers insight into how machines can be improved upon so that operator’s trust towards the machines is more properly calibrated. This thesis aimed to assess the validity of an interaction-based metric of trust: anticipatory pushing of information. Anticipatory pushing of information refers to teammate A anticipating the needs of teammate B and pushing that information to teammate B. It was hypothesized there would be a positive relationship between the frequency of anticipatory pushing and self-reported trust scores. To test this hypothesis, text chat data and self-reported trust scores were analyzed in a previously conducted study in two different sessions (routine and degraded). Findings indicate that the anticipatory pushing of information and the self-reported trust scores between the human-human pairs in the degraded sessions were higher than the routine sessions. In degraded sessions, the anticipatory pushing of information between the human-human pairs was associated with human-human trust.
Date Created
2021
Agent

Executive Function (Anticipation) Differences Between Soccer Players With and Without a History of Traumatic Brain Injury

161525-Thumbnail Image.png
Description
The present study sought to understand traumatic brain injuries (TBI) impact on executive function (EF) in terms of anticipation amongst individuals with a background in soccer; along with other contributing factors of EF curtailments that inhibit athletes. Within this study

The present study sought to understand traumatic brain injuries (TBI) impact on executive function (EF) in terms of anticipation amongst individuals with a background in soccer; along with other contributing factors of EF curtailments that inhibit athletes. Within this study 57 participants, with a background in soccer (high school, collegiate, and semi-professional), completed five EF tasks: working memory, cognitive flexibility, attentional control, and anticipation; pattern detection and athletic cues (temporal occlusion). The results of this study concluded that when TBI history, gender, and soccer athletic level are factors, athletes with a soccer level of collegiate and semi-professional had decrements related to pattern detection anticipation; meaning athletes at higher levels had lower average scores on the Brixton Spatial Anticipation Test (BSAT). Additionally, female athletes showed more anticipation decrements related to athletic cues, especially those that are reliant on the initiation of judgment. Overall undiagnosed TBIs and limited understanding on how to approach rehabilitation to mitigate EF decrements, continue to impede individual autonomy amongst athletes. Keywords: Traumatic brain injury, executive function, anticipation, soccer, temporal occlusion, Brixton Spatial Anticipation Test (BSAT), collegiate, semi-professional, pattern detection, rehabilitation
Date Created
2021
Agent