Vehicle Situational Awareness Research Articles

5G‐based passive radar on a moving platform—Detection and imaging

AbstractIn recent times, the development of radar systems for automotive applications has gathered significant interest due to the increasing necessity of vehicle situational awareness for new active protection systems and the intensive development of higher autonomous level driving solutions. Therefore, the number of active radars in automotive applications is growing, causing spectrum sharing and interference between radars operating in the same band. Alternative solutions without dedicated electromagnetic transmissions, such as joint communication and radar systems, or even no transmission at all, such as passive radars, have emerged in recent years and are promising solutions to help mitigate the interference problem. A passive automotive radar based on 5G communication signals is proposed as an alternative to active radars to provide situational awareness. The data downlink transmissions provided by an operative 5G base station were combined with a dual‐channel passive radar (PR) system deployed on a moving platform to provide moving target detection and radar imaging of the vehicle's surroundings. The outcomes show a possibility of commensal utilisation of the new telecommunication standard for automotive radar applications. The idea of mounting the PR receiver on a moving platform was tested using simulated and real‐life data, which shows great potential for joining the new radio (NR) with sensing capabilities using PR. The theory, numerical experiments, and measurement results are dealt with a cooperative 5G base station and PR demonstrator.

Refining autonomous vehicle situational awareness due to varying sensor error

AbstractPilots use their senses and training to generate situational awareness (SA). They then use this SA to make sound aeronautical decisions. Autonomous vehicles, by contrast, cannot rely on pilot expertise in off‐nominal situations. They must rely on their onboard sensors to build SA of the environment. As these sensors degrade, it is hypothesized that a point exists where the SA generated by these sensors is inadequate to allow the autonomous vehicle to make sound aeronautical decisions. In previous work, a point was defined based on broad assumptions within a modeling and simulation environment (i.e., the error within each sensor was known and not random). This research used a larger data set that contained random errors within the sensors. The data was then used to build predictive equations through a Monte Carlo simulation in the same simulation environment as previous work. While the data showed there was a statistically significant relationship between the error values in each sensor and the fused distance value, the resulting predictive equations were not able to provide adequate SA to make sound aeronautical decisions. This research highlights multiple issues the test and evaluation community will face when trying to develop new techniques for the verification and validation of autonomous systems.

Will Weather Dampen Self-Driving Vehicles?

Abstract Innovative technologies that support implementation of automated vehicles continue to develop at a rapid pace. These advances strive to increase efficiency and safety throughout the global transportation network. One important challenge to these emergent technologies that remains underappreciated is how the vehicles will perform in adverse weather. Each year, weather-related vehicular crashes account for approximately 21% of all highway crashes in the United States. These crashes result in over 5,300 fatalities, injure over 418,000 people, and cost billions of dollars in insurance claims, liability, emergency services, congestion delays, rehabilitation, and environmental damage annually. Automated vehicles have the potential to significantly mitigate these statistics; however, public, private, and academic partnerships between the meteorological and transportation communities must be established to develop solutions to weather impacts now. To date, such interactions have been sparse and largely contribute to a lack of awareness in how these two communities may collaborate together. The purpose of this manuscript is to call the meteorological community to action and proactive engagement with the transportation community. A secondary goal is to make the transportation community aware of the advantages of teaming with the weather enterprise. Automated vehicles will not only increase travel safety, but also have benefits to the meteorological community through increasing availability of high-resolution surface data observations. The future challenges of these emergent technologies in the context of road weather implications focus on vehicle situational awareness and technological sensing capability in all weather conditions, and transforming how drivers and vehicles are informed of weather threats beyond sensing capabilities.

A risk model for autonomous marine systems and operation focusing on human–autonomy collaboration

Autonomous marine systems, such as autonomous ships and autonomous underwater vehicles, gain increased interest in industry and academia. Expected benefits of autonomous marine system in comparison to conventional marine systems are reduced cost, reduced risk to operators, and increased efficiency of such systems. Autonomous underwater vehicles are applied in scientific, commercial, and military applications for surveys and inspections of the sea floor, the water column, marine structures, and objects of interest. Autonomous underwater vehicles are costly vehicles and may carry expensive payloads. Hence, risk models are needed to assess the mission success before a mission and adapt the mission plan if necessary. The operators prepare and interact with autonomous underwater vehicles to carry out a mission successfully. Risk models need to reflect these interactions. This article presents a Bayesian belief network to assess the human–autonomy collaboration performance, as part of a risk model for autonomous underwater vehicle operation. Human–autonomy collaboration represents the joint performance of the human operators in conjunction with an autonomous system to achieve a mission aim. A case study shows that the human–autonomy collaboration can be improved in two ways: (1) through better training and inclusion of experienced operators and (2) through improved reliability of autonomous functions and situation awareness of vehicles. It is believed that the human–autonomy collaboration Bayesian belief network can improve autonomous underwater vehicle design and autonomous underwater vehicle operations by clarifying relationships between technical, human, and organizational factors and their influence on mission risk. The article focuses on autonomous underwater vehicle, but the results should be applicable to other types of autonomous marine systems.

Effects of conversation on situation awareness and working memory in simulated driving.

In the present research, we investigated the hypothesis that working memory mediates conversation-induced impairment of situation awareness (SA) while driving. Although there is empirical evidence that conversation impairs driving performance, the cognitive mechanisms that mediate this relationship remain underspecified. Researchers have reported that a phonological working memory task decreased drivers' SA for vehicles located behind them whereas a visuospatial working memory task impaired SA for vehicles ahead. Conversation, therefore, might impair SA for vehicles behind the driver by preferentially taxing the phonological loop. A 20-questions task was used as a proxy for natural conversation. In Experiment I, driving performance was measured across three within-subjects conversation conditions (i.e., no conversation, driver asks questions, driver answers questions) with the use of a driving simulator. In Experiment 2, participants drove in the same simulator while either conversing (20-questions task) or not Participants estimated the positions of other vehicles after the screens were blanked at the end of each trial. Speed monitoring and responses to visual probes were impaired by the 20-questions conversation task (Experiment 1). As predicted, conversation impaired SA for the location of other vehicles more for vehicles located behind the driver than for those in front (Experiment 2). Conversation impairs drivers' SA of vehicles behind them by taxing working memory's phonological loop and impairs SA generally by taxing working memory's central executive. Provides a theoretical framework that links driver SA to working memory and a mechanism for understanding why conversation impairs driving performance.

Crafting a software engineering capston project course

When properly constructed, a project-based capstone software engineering course can provide the challenging, but essential bridge from academic computing to the world of professional software development while fostering critical teamwork, leadership, and communications skills. In this work, we discuss experiences with five distinct student projects that involved heterogeneous teams, both systems and software engineering disciplines, industrial partnerships, component-based in addition to traditional development methodologies, and interactions with real customers. The heterogeneous teams included computer science, systems engineering, and systems engineering management majors and ranged in size from five to nine students. The projects included a protocol for file transfers between ground stations and on-orbit satellites, a satellite telemetry archiving and visualization tool, porting and extending an evolutionary algorithm for runway damage optimization, an unmanned aerial vehicle situational awareness capability, and a pedagogical interactive game for learning the concepts and applications of public key infrastructures. Partnership with an aerospace industry corporation exposed our students to Capability Maturity Model (CMM) Level 3 processes and facilitated enriching professional mentorships while stimulating student motivation and ownership of their efforts. The structure of the course afforded students significant autonomy to develop and explore both their interpersonal communication skills as well as the tenets of effective project management including scheduling, project tracking, and risk management. In addition, each project was specifically selected to offer the teams the opportunity to develop a useful deliverable with potential for use beyond this pedagogical setting. The result was a high-energy, dynamic, and demanding learning experience with plenty of lessons and opportunities for improvement by the instructor as well as the student.

Developing safety critical software for an unmanned aerial vehicle situational awareness tool

In this paper, we describe our application of the SPARK programming language to the development of flight control software for an Unmanned Aerial Vehicle (UAV). The SPARK language was used during a senior-level software engineering course at the US Air Force Academy. This paper uses the year-long project from this course as an example application of SPARK. The process we used to build an interface between C++ and Ada is discussed along with our experiences with using SPARK.