From Here to Autonomy Endsley, Mica R.
Human factors,
02/2017, Letnik:
59, Številka:
1
Journal Article
Recenzirano
As autonomous and semiautonomous systems are developed for automotive, aviation,
cyber, robotics and other applications, the ability of human operators to
effectively oversee and interact with them ...when needed poses a significant
challenge. An automation conundrum exists in which as more
autonomy is added to a system, and its reliability and robustness increase, the
lower the situation awareness of human operators and the less likely that they
will be able to take over manual control when needed. The human–autonomy systems
oversight model integrates several decades of relevant autonomy research on
operator situation awareness, out-of-the-loop performance problems, monitoring,
and trust, which are all major challenges underlying the automation conundrum.
Key design interventions for improving human performance in interacting with
autonomous systems are integrated in the model, including human–automation
interface features and central automation interaction paradigms comprising
levels of automation, adaptive automation, and granularity of control
approaches. Recommendations for the design of human–autonomy interfaces are
presented and directions for future research discussed.
The automation of longitudinal and lateral control has enabled drivers to become “hands and feet free” but they are required to remain in an active monitoring state with a requirement to resume ...manual control if required. This represents the single largest allocation of system function problem with vehicle automation as the literature suggests that humans are notoriously inefficient at completing prolonged monitoring tasks. To further explore whether partially automated driving solutions can appropriately support the driver in completing their new monitoring role, video observations were collected as part of an on-road study using a Tesla Model S being operated in Autopilot mode. A thematic analysis of video data suggests that drivers are not being properly supported in adhering to their new monitoring responsibilities and instead demonstrate behaviour indicative of complacency and over-trust. These attributes may encourage drivers to take more risks whilst out on the road.
•On-road study using a Tesla Model S operated in Autopilot mode.•Thematic analysis of driver behaviour highlights the impact of autonomous functionality on driver behaviour.•Findings reveal evidence of mode error, complacency and over-trust.
•We evaluate the safety impact of connected vehicles and connected vehicles lower level automation in an arterial section.•This study considered two automated features such as automated braking and ...lane keeping assistance.•Safety impact on both segment and intersection crash risks were explored.•A logistic regression model was also developed to quantify the intersection crash risk.
This paper aims to investigate the safety impact of connected vehicles and connected vehicles with the lower level of automation features under vehicle-to-vehicle (V2V) and infrastructure-to-vehicle (I2V) communication technologies. Examining the lower level of automation is more realistic in the foreseeable future. This study considered two automated features such as automated braking and lane keeping assistance which are widely available in the market with low penetration rates. Driving behavior of connected vehicles (CV) and connected vehicles lower level automation (CVLLA) were modeled in the C++ programming language with considering realistic car following models in VISSIM. To this end, safety impact on both segment and intersection crash risks were explored through surrogate safety assessment techniques under various market penetration rates (MPRs). Segment crash risk was analyzed based on both time proximity-based and evasive action-based surrogate measures of safety: time exposed time-to-collision (TET), time integrated time-to-collision (TIT), time exposed rear-end crash risk index (TERCRI), lane changing conflicts (LCC), and number of critical jerks (NCJ). However, the intersection crash risk was evaluated through the number of conflicts extracted from microsimulation (VISSIM) using the Surrogate Safety Assessment Model (SSAM). A logistic regression model was also developed to quantify the crash risk in terms of observed conflicts obtained in the intersection influence areas. The results suggest that both CV and CVLLA reduce segment crash risk significantly in terms of the five surrogate measures of safety. Furthermore, the logistic regression results clearly showed that both CV and CVLLA have lower intersection crash risks compared to the base scenario. In terms of both segment and intersection crash risks, CVLLA significantly outperforms CV when MPRs are 60% or higher. Thus, the results indicate a significant safety improvement resulting from implementing CV and CVLLA technologies at both segments and intersections on arterials.
This study assessed the effects of different levels of automation and non-driving related tasks (NDRT) on driver performance and workload. A systematic literature review was conducted in March 2021 ...using Compendex, Google Scholar, Web of Science, and Scopus databases. Forty-five studies met the inclusion criteria. A meta-analysis was conducted and Cochrane risk of bias tool and Cochran's Q test were used to assess risk of bias and homogeneity of the effect sizes respectively. Results suggested that drivers exhibited safer performance when dealing with critical incidents in manual driving than partially automated driving (PAD) and highly automated driving (HAD) conditions. However, drivers reported higher workload in the manual driving mode as compared to the HAD and PAD conditions. Haptic, auditory, and visual-auditory takeover request modalities are preferred over the visual-only modality to improve takeover time. Use of handheld NDRTs significantly degraded driver performance as compared to NDRTs performed on mounted devices.
•Drivers reported higher workload in manual driving than HAD and PAD conditions.•Presenting secondary tasks on handheld devices impairs driver performance.•This review offers recommendations to improve automated vehicles.
•Factors influencing fatal crashes involving PAVs are compared with non-AVs within their vicinity.•PAVs are less likely to be involved in a fatal crash at four-way intersections and on two-way roads ...with wide medians.•PAVs are less likely to be involved in a fatal crash at nighttime and in poor lighting condition.•PAVs are more likely to be involved in a fatal crash with non-motorists.•PAEB and LKA reduce collision with a pedestrian and roadside departure, respectively. Other smart features are not yet very effective.
Automated vehicles (AVs) are expected to improve safety by gradually reducing human decisions while driving. However, there are still questions on their effectiveness as we transition from almost 0% AVs to 100% AVs with different levels of vehicle autonomy. The focus of this study, therefore, is on synthesizing and identifying risk factors influencing fatal crashes involving partially automated vehicles (PAVs) i.e., level 1 AVs and level 2 AVs, in the United States. Fatal crashes involving non-AVs (level 0 vehicles) within their vicinity were used for comparison, to minimize unobserved heterogeneity and randomness associated with the influencing risk factors. The fatal crash data for the years 2016 to 2019 is used for the analysis. A partial proportional odds model is developed using crash, road, and vehicle characteristics as independent variables while the fatal crash involving a vehicle with a specific level of automation (0, 1, or 2) is used as the dependent variable. The level of automation was captured by developing tools and identifying advanced features in each vehicle based on the vehicle identification number (VIN). The odds ratios varied for PAVs compared to non-AVs. PAVs are safer but are more likely to be involved in a fatal crash with non-motorists. Pedestrian automatic emergency braking (PAEB) and lane-keeping assistance (LKA) were observed to improve safety by reducing possible collision with a pedestrian and roadside departure, respectively. Contrarily, vehicles with other smart features are still highly likely to be involved in fatal crashes, demanding further research and attention.
Given the impending introduction of self-driving cars to Japan within the next several years, gaining a better understanding of public opinion and risk perception of autonomous vehicles (AVs) is ...crucial. Though AVs have numerous potential social and economic benefits, including reduced travel time and environmental impacts, their implementation will depend on public acceptance. This study expanded on existing work by directly examining which aspects of AV use and function most affect risk perception. Participants were shown short animated video clips depicting the introduction of AVs into society at large, as well as three specific possible risk factors: system error, external interference with car controls (i.e., hacking), and the inability of the car to cope with unexpected events. Participants were then surveyed about their attitudes toward AVs and other potentially risky activities and technologies. The study established that the perceived advantages of all AV types (cars and buses, different automation levels) outweighed their perceived risks. Consistent with prior research, the two major aspects of perceived risk were dread and unfamiliarity. The results showed compared with other technologies, AV scores were neutral for dread risk but higher for unfamiliarity risk. The finding of high unfamiliarity indicates that public acceptance and perceived risks are likely to change as the public's knowledge increases. We also found that receiving information about a potential system error indirectly reduced AV acceptability, where dread and unfamiliarity to the AV risks served as mediators. The results suggest that proper management on the diffusion of information, which includes public information campaigns, test-ride events and transparency about safety options, will likely influence the ultimate social acceptability of AVs and will be crucial towards its successful introduction on the market.
Crane-lift operations are critical in construction. With the advancement of information and communications technologies, crane-lift automation (CLA) has been increasingly explored, but still not ...systematically understood. This paper aims to examine the key technologies, categorize the levels, and identify the research directions of CLA through a systematic literature review. The review covers 106 journal articles and 15 products, which are examined in terms of sensing and perception, planning and decision-making, and motion control. Results reveal that camera-based sensing and perception dominates CLA studies, and intelligent path re-planning and closed-loop control strategies witness an increase over the past two decades. CLA is categorized into four levels, namely, Operator Assistance, Partial Automation, High Automation, and Full Automation. Six research directions are identified for achieving High and Full Automation, remarkably the multi-sensor integration for real-time collision-free path re-planning. The paper provides a milestone of CLA research and facilitates the development of autonomous cranes.
Display omitted
•Crane-lift automation (CLA) was reviewed covering 106 journal articles and 15 products•Camera-based sensing and perception dominated CLA research and development•Research on intelligent path finding and closed-loop control witnessed a significant increase•CLA was classified into Operator Assistance, and Partial-, High-, and Full-Automation•Six research directions were identified, e.g., multi-sensor integration for path re-planning
Digitalization in intelligent manufacturing leads to the development of Industry 4.0/5.0 and human-cyber-physical systems. As many production technologies rely on teaming of human workers and ...intelligent cyber-physical systems such as industrial robots, human-robot collaboration is an intensively investigated topic in this transdisciplinary research area. To design industrial robots in a human-centered way, psychological knowledge concerning judgment and decision-making needs to be gained and integrated.
This paper reports results from an experimental study (
222, 2 × 4 within-subjects design) using eight moral dilemmas framed in the context of human-robot-collaboration to examine the influence of spatial distance of an industrial robot and humans (no direct contact, different tasks vs. no direct contact, same task vs. handing-over contact, same task vs. direct contact, same task) on moral decisions. Additionally, the type of dilemma was varied, with every four dilemmas depicting a life-or-death and an injury scenario. Participants responded on a four-point-response scale which actions they would take indicating deontological or utilitarian moral decision-making.
Results show a large effect of the proximity of the cooperation between robots and humans. The closer the collaboration the more a human tends to choose utilitarian moral choices.
It is argued that this effect might stem from an adaptation of human rationality to the robot or overreliance and shift of responsibility to the robot team partner.
•Extensive literature review of Adaptive Automation (AA).•Application focus on the manufacturing sector.•Historical evolution, design aspects, applications, and open challenges of AA.•First ...manufacturing applications promising but need further progress.
Automation modifies workplaces, tools, and production activities, leading to new modalities of human-machine interaction. Traditionally, the allocation of functions in automated systems is static over time, i.e., functions are assigned to humans or machines. Adaptive Automation (AA) makes functions allocation dynamic, resulting from system conditions, performance, and human attributes to face emerging or unpredictable contingencies, and to cope with traditional automation challenges and limits. Tracing the evolutionary stages of the topic, the paper provides an extensive literature review. First, the review details the current definition of AA, the starting motivations for AA, and the temporal evolution of the topic considering the pioneers’ theories. Then, the paper presents the design elements involved in AA systems, i.e., the Level Of Automation (LOA), the Human-Machine Interfaces (HMIs), and the different approaches than can guide the adaptive shift. Finally, the practical applications of AA in manufacturing are reported. In such a way, the research offers the state of the art of the topic, providing the main distinguishing features between static and AA, also outlining the open challenges and the future developments in manufacturing.
•Mapped and analyzed the level of automation of aerospace composite manufacturing process chains.•Current ‘Automated’ process chains have not reached the higher level of automation expected in ...Industry 4.0.•Highlights areas for improvements in automating non-value-added activities and core-process tasks.•Provides future directions towards a smart composite factory in the context of Industry 4.0.
Composites have become the go-to material of the aerospace industry during the past decades and a significant uptake in composite materials for aerospace applications was evident in recent years. Both expert academics and industry practitioners believe, to meet the future demand, the level of automation in the aerospace composite manufacturing process chains must be improved. The main focus of automation in composites so far has been given to automate siloed operations but limited attention has been paid to end-to-end integration of the process chains leading to inefficiencies, rising operational costs, and low productivity. This paper intends to compare and contrast the level of automation (LOA) in different aerospace composite manufacturing process chains to identify where the LOA triumphs and lacks. For this purpose, core-process and sub-process tasks involved in commonly used manufacturing process chains (i.e. Filament Winding, Automated Tape Layup, Automated Fiber Placement, Resin Transfer Molding, and Pultrusion) are identified by conducting a detailed literature review and verified by the experts. Then, the process chains are mapped and visualized to understand the workflow. Later, these tasks are evaluated based on an established LOA taxonomy developed for manufacturing processes. The study reveals that even the popular ‘automated’ processes are developed in silos and do not show consistent higher LOA throughout their process chain. While core-process tasks show intermediate LOA (Level 5–6), most non-value-added activities show poor LOA (Level 1–4). Most importantly, none of the tasks involved in the existing composite manufacturing process chains have reached a higher LOA (Level 7). The paper reveals that focusing on sub-process tasks, and tasks that lack automation should be the next step towards achieving fully automated composite manufacturing and presents a two-pronged approach to realize Industry 4.0.