Sensorimotor representation and knowledge-based reasoning for spatial exploration and localisation

We investigate a hybrid system for autonomous exploration and navigation, and implement it in a virtual mobile agent, which operates in virtual spatial environments. The system is based on several distinguishing properties. The representation is not map-like, but based on sensorimotor features, i.e. on combinations of sensory features and motor actions. The system has a hybrid architecture, which integrates a bottom-up processing of sensorimotor features with a top-down, knowledge-based reasoning strategy. This strategy selects the optimal motor action in each step according to the principle of maximum information gain. Two sensorimotor levels with different behavioural granularity are implemented, a macro-level, which controls the movements of the agent in space, and a micro-level, which controls its eye movements. At each level, the same type of hybrid architecture and the same principle of information gain are used for sensorimotor control. The localisation performance of the system is tested with large sets of virtual rooms containing different mixtures of unique and non-unique objects. The results demonstrate that the system efficiently performs those exploratory motor actions that yield a maximum amount of information about the current environment. Localisation is typically achieved within a few steps. Furthermore, the computational complexity of the underlying computations is limited, and the system is robust with respect to minor variations in the spatial environments.     

Interaction between pedestrians and automated vehicles: A Wizard of Oz experiment

Automated vehicles (AVs) will be introduced on public roads in the future, meaning that traditional vehicles and AVs will be sharing the urban space. There is currently little knowledge about the interaction between pedestrians and AVs from the point of view of the pedestrian in a real-life environment. Pedestrians may not know with which type of vehicle they are interacting, potentially leading to stress and altered crossing decisions. For example, pedestrians may show elevated stress and conservative crossing behavior when the AV driver does not make eye contact and performs a non-driving task instead. It is also possible that pedestrians assume that an AV would always yield (leading to short critical gaps). This study aimed to determine pedestrians’ crossing decisions when interacting with an AV as compared to when interacting with a traditional vehicle. We performed a study on a closed road section where participants (N = 24) encountered a Wizard of Oz AV and a traditional vehicle in a within-subject design. In the Wizard of Oz setup, a fake ‘driver’ sat on the driver seat while the vehicle was driven by the passenger by means of a joystick. Twenty scenarios were studied regarding vehicle conditions (traditional vehicle, ‘driver’ reading a newspaper, inattentive driver in a vehicle with “self-driving” sign on the roof, inattentive driver in a vehicle with “self-driving” signs on the hood and door, attentive driver), vehicle behavior (stopping vs. not stopping), and approach direction (left vs. right). Participants experienced each scenario once, in a randomized order. This allowed assessing the behavior of participants when interacting with AVs for the first time (no previous training or experience). Post-experiment interviews showed that about half of the participants thought that the vehicle was (sometimes) driven automatically. Measurements of the participants’ critical gap (i.e., the gap below which the participant will not attempt to begin crossing the street) and self-reported level of stress showed no statistically significant differences between the vehicle conditions. However, results from a post-experiment questionnaire indicated that most participants did perceive differences in vehicle appearance, and reported to have been influenced by these features. Future research could adopt more fine-grained behavioral measures, such as eye tracking, to determine how pedestrians react to AVs. Furthermore, we recommend examining the effectiveness of dynamic AV-to-pedestrian communication, such as artificial lights and gestures.     

Competence,equipment and behavioural adaptation on Norwegian winter roads: A comparison of foreign and Norwegian HGV drivers

There seems to be a widespread view that foreign lorry drivers’ lack of competence on Norwegian roads, especially related to winter driving, is a significant safety problem. It has, however, been suggested that foreign heavy goods vehicle (HGV) drivers perform better than expected on Norwegian winter roads, as they feel less safe than Norwegian drivers, and adapt by driving slower and more carefully. The aim of the present paper is twofold. First, we examine whether foreign HGV drivers in Norway actually have poorer competence on, training for, experience with and equipment for winter driving than Norwegian HGV drivers. Second, we discuss whether the expected negative effect of these safety challenges is mitigated, as foreign HGV drivers adapt their behaviours. We use four data sources to shed light on the aims: (1) interviews, (2) roadside inspections, (3) small-scale survey and (4) towing incidents. Our data support the hypothesis about behavioural adaptation, indicating that foreign HGV drivers experience winter driving as more difficult or unsafe, as they have supposedly less suitable vehicles and equipment, less experience, training and competence for winter driving. They are therefore more likely to get stuck while driving uphill on winter roads, supposedly as they drive more carefully and slower than Norwegian HGV drivers. Norwegian HGV drivers feel safer and more confident while driving on winter roads, because of their equipment and their experience.     

Car-following behavioural adaptation when driving next to automated vehicles on a dedicated lane on motorways: A driving simulator study in the Netherlands

Automated vehicles (AVs) are expected to improve traffic flow efficiency and safety. The deployment of AVs on motorways is expected to be the first step in their implementation. One of the main concerns is how human drivers will interact with AVs. Dedicating specific lanes to AVs have been suggested as a possible solution. However, there is still a lack of evidence-based research on the consequence of dedicated lanes for AVs on human drivers’ behavior. To bridge this research gap, a driving simulator experiment was conducted to investigate the behavior of human drivers exposed to different road design configurations of dedicated lanes on motorways. The experiment sample consisted of 34 (13 female) licensed drivers in the age range of 20–30. A repeated measures ANOVA was applied, which revealed that the type of separation between the dedicated lane and the other lanes has a significant influence on the behavior of human drivers driving in the proximity of AV platoons. Human drivers maintained a significantly lower time headway (THW) when driving in the proximity of a continuous access dedicated lane as compared to a limited-access dedicated lane with a guardrail separation for AV platoons. A similar result was found for the limited-access dedicated lane in comparison to the limited-access dedicated lane with guardrail separation. Moreover, the results regarding the empirical relationships between THW and sociodemographic variables indicate a significant THW difference between males and females as well as a significant inverse relationship between THW and the years of driving experience.     

Autonomous buses: Intentions to use,passenger experiences,and suggestions for improvement

Research on the use of autonomous vehicles as a mode of public transport in a city context is lacking. This paper focuses on the use of recently established autonomous buses (self-driving electric shuttle buses) running along a regular public transport line in a residential area of Oslo, Norway. We use a mixed-methods approach based on survey and interview data from two independent studies. The paper examines intentions to use autonomous buses before and after these were introduced in the case area as well as how passengers experience traveling by autonomous bus. Results show that the intention to use the autonomous buses was mostly positive both before and after using them. Most users felt safe while traveling by autonomous bus. Two suggestions for improvement made by the users were to: increase the speed and reduce the abrupt breaking of the autonomous buses. Overall, outcomes from this paper suggest that residents would be willing to use autonomous buses if these offer more frequent bus departures than the existing ones. However, as full automation has not been achieved yet and there is a host on board who can control the vehicle if necessary, passenger experiences and intentions to use should be reassessed with fully automated buses in future studies.     

How do familiarity and fatal accidents affect acceptance of self-driving vehicles?

Expected benefits of disruptive technologies such as self-driving vehicles may only materialize if they are publicly accepted. Acceptance increases when implementation is experienced as initial concerns become unfounded and individuals become familiar with the new technology. Fatal accidents, however, negatively affect acceptance. This paper examines citizens' acceptance of self-driving vehicles by contrasting pre- and post-implementation of a self-driving shuttle in Switzerland and before and after the first fatal accident involving a self-driving vehicle in Arizona (USA) in 2018 gaining high media attention. To gauge acceptance, a panel survey using a random sample of 1408 Swiss residents was used. The results indicate that news about the fatal accident abroad exerts a stronger effect on acceptance than experiencing a self-driving bus trial. Latent scepticism causes acceptance to decrease in the event of an accident but only lasts short term. However, acceptance levels are stable and at high levels, which also explains the comparably low familiarity effects. As public acceptance is necessary for technology transitions, this article provides policymakers practical insights on how citizens form preferences towards traffic automation and related policy regulations. More specifically, results show how attitudes change over time while residents experience a trial and the first fatal accident with the technology at hand.     

Modeling dispositional and initial learned trust in automated vehicles with predictability and explainability

Technological advances in the automotive industry are bringing automated driving closer to road use. However, one of the most important factors affecting public acceptance of automated vehicles (AVs) is the public’s trust in AVs. Many factors can influence people’s trust, including perception of risks and benefits, feelings, and knowledge of AVs. This study aims to use these factors to predict people’s dispositional and initial learned trust in AVs using a survey study conducted with 1175 participants. For each participant, 23 features were extracted from the survey questions to capture his/her knowledge, perception, experience, behavioral assessment, and feelings about AVs. These features were then used as input to train an eXtreme Gradient Boosting (XGBoost) model to predict trust in AVs. With the help of SHapley Additive exPlanations (SHAP), we were able to interpret the trust predictions of XGBoost to further improve the explainability of the XGBoost model. Compared to traditional regression models and black-box machine learning models, our findings show that this approach was powerful in providing a high level of explainability and predictability of trust in AVs, simultaneously.     

Sharing the road with autonomous vehicles: A qualitative analysis of the perceptions of pedestrians and bicyclists

Public perception assessment is important for gaining a better understanding of the acceptance of autonomous vehicles (AVs) and identifying potential ways to resolve public concerns. This study investigated how pedestrians and bicyclists perceived AVs based on their knowledge and road sharing experiences, applying a combined inductive and deductive data analysis approach. Survey responses of pedestrians and bicyclists in Pittsburgh, Pennsylvania, USA collected by Bike Pittsburgh (BikePGH) in 2019, were analyzed in this research. AVs following traffic rules appropriately and AVs driving safer than the human drivers were the most notable positive perceptions towards AVs. Pedestrians and bicyclists showed comparatively fewer negative perceptions towards AVs than positive perceptions. Negative perceptions mostly included a lack of perceived safety and comfort around AVs and trust in the AV technology. Respondents also concerned about AV technology issues (e.g., slow and defensive driving, disruptive maneuver), while sharing the road with AVs. Perceptions of the respondents were significantly influenced by their views on AV safety, familiarity with the technology, the extent respondents followed AV on the news, and household automobile ownership. Regulating AV movement on roadways, developing safety assessment guidelines, and controlling oversights of improper practices by AV companies were the major suggestions from the survey participants. Findings of this study might help AV companies to identify potential improvement needed in AV technology to increase pedestrians and bicyclists acceptance, and policymakers to develop policy guidelines to ensure safe road sharing among pedestrians, bicyclists, and AVs.     

Safety of autonomous vehicles: what are the insights from experienced industry professionals?

Many drivers support the push towards the automation of transportation. Technology and automotive companies, the general public, and governments are all seen as the main groups pushing the automation revolution forward. The key to this revolution's success will rest with the perception of the professionals in the field as their perception will affect the way that Autonomous Vehicles (AVs) are adopted. This study surveyed 185 experienced industry professionals to gather their comments and opinions on AVs' purported safety benefits and drawbacks. The results in this paper illustrate that the ‘incorrect understanding of the surrounding objects by AVs’ could be the most significant technical concern and may lead to accidents. Some professionals had concerns about trusting the AVs’ safe operation without steering wheels, while some others believed that there is a chance that having steering wheels may increase safety concerns. The findings also suggest that while AVs might reduce the number of accidents, this may not necessarily be the case for the severity of any accidents. The severity may remain unchanged or even increase as a result of the adoption of AVs. This paper's results show that the majority of the professionals consulted agreed that AVs have the potential to increase road safety significantly. However, the consensus was that more research and testing is needed in this field.