More Like this

1. Performance and Relative Risk Dynamics during Driving Simulation Tasks under Distinct Automation Conditions

   https://doi.org/10.1177/1071181322661471  

   Rodriguez Rodriguez, Lucero; Bustamante Orellana, Carlos; Gremillion, Gregory M.; Huang, Lixiao; Demir, Mustafa; Cooke, Nancy; Metcalfe, Jason S.; Amazeen, Polemnia G.; Kang, Yun (September 2022, Proceedings of the Human Factors and Ergonomics Society Annual Meeting)

   Risk has been a key factor influencing trust in Human-Automation interactions, though there is no unified tool to study its dynamics. We provide a framework for defining and assessing relative risk of automation usage through performance dynamics and apply this framework to a dataset from a previous study. Our approach allows us to explore how operators’ ability and different automation conditions impact the performance and relative risk dynamics. Our results on performance dynamics show that, on average, operators perform better (1) using automation that is more reliable and (2) using partial automation (more workload) than full automation (less workload). Our analysis of relative risk dynamics indicates that automation with higher reliability has higher relative risk dynamics. This suggests that operators are willing to take more risk for automation with higher reliability. Additionally, when the reliability of automation is lower, operators adapt their behavior to result in lower risk. 

   more » « less
2. A Computational Model of Coupled Human Trust and Self-confidence Dynamics

   https://doi.org/10.1145/3594715  

   Williams, Katherine J; Yuh, Madeleine S; Jain, Neera (June 2023, ACM Transactions on Human-Robot Interaction)

   Autonomous systems that can assist humans with increasingly complex tasks are becoming ubiquitous. Moreover, it has been established that a human’s decision to rely on such systems is a function of both their trust in the system and their own self-confidence as it relates to executing the task of interest. Given that both under- and over-reliance on automation can pose significant risks to humans, there is motivation for developing autonomous systems that could appropriately calibrate a human’s trust or self-confidence to achieve proper reliance behavior. In this article, a computational model of coupled human trust and self-confidence dynamics is proposed. The dynamics are modeled as a partially observable Markov decision process without a reward function (POMDP/R) that leverages behavioral and self-report data as observations for estimation of these cognitive states. The model is trained and validated using data collected from 340 participants. Analysis of the transition probabilities shows that the proposed model captures the probabilistic relationship between trust, self-confidence, and reliance for all discrete combinations of high and low trust and self-confidence. The use of the proposed model to design an optimal policy to facilitate trust and self-confidence calibration is a goal of future work. 

   more » « less
3. Individual Characteristics and Operator Dependence Behaviors in Human-Automation Interaction: An Exploratory Study

   https://doi.org/10.1177/10711813241268783  

   Hidalgo, Drew; Schuler, Patrik_T; Yang, X_Jessie (November 2024, Proceedings of the Human Factors and Ergonomics Society Annual Meeting)

   Understanding the impact of operator characteristics on human-automation interaction (HAI) is crucial as automation becomes pervasive. Despite extensive HAI research, the association between operator characteristics and their dependence on automation has not been thoroughly examined. This study, therefore, examines how individual characteristics affect operator dependence behaviors when interacting with automation. Through a controlled experiment involving 52 participants in a dual-task scenario, we find that operators’ decision-making style, risk propensity, and agreeableness are associated with their dependence behaviors when using automation. This research illuminates the role of personal characteristics in HAI, facilitating personalized team interactions, trust building, and enhanced performance in automated settings. 

   more » « less
4. Human operators’ blind compliance, reliance, and dependence behaviors when working with imperfect automation: A meta-analysis

   https://doi.org/10.1109/ICHMS56717.2022.9980609  

   Schuler, Patrik T.; Yang, X. Jessie (January 2022, 2022 IEEE 3rd International Conference on Human-Machine Systems (ICHMS))

   We conducted a meta-analysis to determine how people blindly comply with, rely on, and depend on diagnostic automation. We searched three databases using combinations of human behavior keywords with automation keywords. The period ranges from January 1996 to June 2021. In total, 8 records and a total of 68 data points were identified. As data points were nested within research records, we built multi-level models (MLM) to quantify relationships between blind compliance and positive predictive value (PPV), blind reliance and negative predictive value (NPV), and blind dependence and overall success likelihood (OSL).Results show that as the automation’s PPV, NPV, and OSL increase, human operators are more likely to blindly follow the automation’s recommendation. Operators appear to adjust their reliance behaviors more than their compliance and dependence. We recommend that researchers report specific automation trial information (i.e., hits, false alarms, misses, and correct rejections) and human behaviors (compliance and reliance) rather than automation OSL and dependence. Future work could examine how operator behaviors change when operators are not blind to raw data. Researchers, designers, and engineers could leverage understanding of operator behaviors to inform training procedures and to benefit individual operators during repeated automation use. 

   more » « less
5. RLDRM: Closed Loop Dynamic Cache Allocation with Deep Reinforcement Learning for Network Function Virtualization

   https://doi.org/10.1109/NetSoft48620.2020.9165471  

   Li, Bin; Wang, Yipeng; Wang, Ren; Tai, Charlie; Iyer, Ravi; Zhou, Zhu; Herdrich, Andrew; Zhang, Tong; Haj-Ali, Ameer; Stoica, Ion; et al (June 2020, 2020 6th IEEE International Conference on Network Softwarization (NetSoft))

   null (Ed.)

   Network function virtualization (NFV) technologyattracts tremendous interests from telecommunication industryand data center operators, as it allows service providers to assignresource for Virtual Network Functions (VNFs) on demand,achieving better flexibility, programmability, and scalability. Toimprove server utilization, one popular practice is to deploy besteffort (BE) workloads along with high priority (HP) VNFs whenhigh priority VNF’s resource usage is detected to be low. The keychallenge of this deployment scheme is to dynamically balancethe Service level objective (SLO) and the total cost of ownership(TCO) to optimize the data center efficiency under inherentlyfluctuating workloads. With the recent advancement in deepreinforcement learning, we conjecture that it has the potential tosolve this challenge by adaptively adjusting resource allocationto reach the improved performance and higher server utilization.In this paper, we present a closed-loop automation systemRLDRM1to dynamically adjust Last Level Cache allocationbetween HP VNFs and BE workloads using deep reinforcementlearning. The results demonstrate improved server utilizationwhile maintaining required SLO for the HP VNFs. 

   more » « less