Advanced eNose-Driven Pedestrian Tracking Pipeline for Intelligent Car Driver Assisting System: Preliminary Results

From a biological point of view, alcohol human attentional impairment occurs before reaching a Blood Alcohol Content (BAC index) of 0.08% (0.05% under the Italian legislation), thus generating a significant impact on driving safety if the drinker subject is driving a car. Car drivers must keep a safe driving dynamic, having an unaltered physiological status while processing the surrounding information coming from the driving scenario (e.g., traffic signs, other vehicles and pedestrians). Specifically, the identification and tracking of pedestrians in the driving scene is a widely investigated problem in the scientific community. The authors propose a full, deep pipeline for the identification, monitoring and tracking of the salient pedestrians, combined with an intelligent electronic alcohol sensing system to properly assess the physiological status of the driver. More in detail, the authors propose an intelligent sensing system that makes a common air quality sensor selective to alcohol. A downstream Deep 1D Temporal Residual Convolutional Neural Network architecture will be able to learn specific embedded alcohol-dynamic features in the collected sensing data coming from the GHT25S air-quality sensor of STMicroelectronics. A parallel deep attention-augmented architecture identifies and tracks the salient pedestrians in the driving scenario. A risk assessment system evaluates the sobriety of the driver in case of the presence of salient pedestrians in the driving scene. The collected preliminary results confirmed the effectiveness of the proposed approach.

Safety-aware Adversarial Inverse Reinforcement Learning (S-AIRL) for Highway Autonomous Driving

Inverse reinforcement learning (IRL) has been successfully applied in many robotics and autonomous driving studies without the need for hand-tuning a reward function. However, it suffers from safety issues. Compared to the reinforcement learning (RL) algorithms, IRL is even more vulnerable to unsafe situations as it can only infer the importance of safety based on expert demonstrations. In this paper, we propose a safety-aware adversarial inverse reinforcement learning algorithm (S-AIRL). First, the control barrier function (CBF) is used to guide the training of a safety critic, which leverages the knowledge of system dynamics in the sampling process without training an additional guiding policy. The trained safety critic is then integrated into the discriminator to help discern the generated data and expert demonstrations from the standpoint of safety. Finally, to further improve the safety awareness, a regulator is introduced in the loss function of the discriminator training to prevent the recovered reward function from assigning high rewards to the risky behaviors. We tested our S-AIRL in the highway autonomous driving scenario. Comparing to the original AIRL algorithm, with the same level of imitation learning (IL) performance, the proposed S-AIRL can reduce the collision rate by 32.6%.

An Empirical Study on Drivers’ Willingness to Use Automatic Features of Intelligent Vehicles: A Psychological Empowerment Perspective

With the advancement in AI and related technologies, we are witnessing more remarkable use of intelligent vehicles. Intelligent vehicles use smart automatic features that make travel happier, safer, and efficient. However, not many studies examine their adoption or the influence of intelligent vehicles on user behavior. In this study, we specifically examine how intelligent vehicles’ sensing and acting abilities drive their adoption from the lens of psychological empowerment theory. We identify three dimensions of users’ perceived empowerment (perceived cognitive empowerment, perceived emotional empowerment, and perceived behavioral empowerment). Based on this theory, we argue that product features (sensing and acting in intelligent vehicles) empower users to use the product. Our proposed model is validated by an online survey of 312 car owners who are familiar with driving conditions, the results of this study reveal that driver’s perceived empowerment is vital for using automatic features of intelligent vehicles. Theoretically, this study combines the concept of empowerment with the intelligent-driving scenario and reasonably explains the mechanism of the intelligence of vehicles on users’ behavior intention.

Efficient Algorithm to Calculate a Time-Domain Echo Signal from Moving Targets Based on Physical Optics and the Application to an Autonomous Driving Simulation

An automotive radar simulator is proposed that can consider a dynamic driving scenario. The impulse response is computed based on the distance between the radar and the mesh position and the radar equation. The first-order physical optics technique is used to calculate the backscattering by the meshes, which can efficiently consider the shape of the target; however, because the radar operating frequency is very high, the required amount of mesh for discretization is large. Hence, the calculation of the time-domain echo signal requires considerable computational time. To reduce this numerical complexity, a new scheme is proposed to accurately approximate the time-domain baseband signal generated by the large number of meshes. The radar adopts the frequency modulated continuous waveform. Range-Doppler processing is used to estimate the range and relative velocity of the targets based on which simulation results are numerically verified for a driving scenario.

An Integrated Model for User State Detection of Subjective Discomfort in Autonomous Vehicles

The quickly rising development of autonomous vehicle technology and increase of (semi-) autonomous vehicles on the road leads to an increased demand for more sophisticated human–machine-cooperation approaches to improve trust and acceptance of these new systems. In this work, we investigate the feeling of discomfort of human passengers while driving autonomously and the automatic detection of this discomfort with several model approaches, using the combination of different data sources. Based on a driving simulator study, we analyzed the discomfort reports of 50 participants for autonomous inner city driving. We found that perceived discomfort depends on the driving scenario (with discomfort generally peaking in complex situations) and on the passenger (resulting in interindividual differences in reported discomfort extend and duration). Further, we describe three different model approaches on how to predict the passenger discomfort using data from the vehicle’s sensors as well as physiological and behavioral data from the passenger. The model’s precision varies greatly across the approaches, the best approach having a precision of up to 80%. All of our presented model approaches use combinations of linear models and are thus fast, transparent, and safe. Lastly, we analyzed these models using the SHAP method, which enables explaining the models’ discomfort predictions. These explanations are used to infer the importance of our collected features and to create a scenario-based discomfort analysis. Our work demonstrates a novel approach on passenger state modelling with simple, safe, and transparent models and with explainable model predictions, which can be used to adapt the vehicles’ actions to the needs of the passenger.

Intelligent Real-Time Deep System for Robust Objects Tracking in Low-Light Driving Scenario

The detection of moving objects, animals, or pedestrians, as well as static objects such as road signs, is one of the fundamental tasks for assisted or self-driving vehicles. This accomplishment becomes even more difficult in low light conditions such as driving at night or inside road tunnels. Since the objects found in the driving scene represent a significant collision risk, the aim of this scientific contribution is to propose an innovative pipeline that allows real time low-light driving salient objects tracking. Using a combination of the time-transient non-linear cellular networks and deep architectures with self-attention, the proposed solution will be able to perform a real-time enhancement of the low-light driving scenario frames. The downstream deep network will learn from the frames thus improved in terms of brightness in order to identify and segment salient objects by bounding-box based approach. The proposed algorithm is ongoing to be ported over a hybrid architecture consisting of a an embedded system with SPC5x Chorus MCU integrated with an automotive-grade system based on STA1295 MCU core. The performances (accuracy of about 90% and correlation coefficient of about 0.49) obtained in the experimental validation phase confirmed the effectiveness of the proposed method.

Computational Models for Workload Analysis of Driving Tasks

This paper describes a methodology to design computational models to evaluate the workload for driving tasks. A computational model was configured for a driving scenario used in a pilot study that included a secondary task at varying levels of difficulty to increase the driver’s workload. The computational model results provided a workload analysis of the concurrent driving tasks. This analysis can be used to explain the experimental findings from subject experiments and to evaluate the workload trade-offs between primary and secondary driving tasks.