ML-ANet:A Transfer Learning Approach Using Adaptation Network for Multi-label Image Classification in Autonomous Driving

To reduce the discrepancy between the source and target domains,a new multi-label adaptation network(ML-ANet)based on multiple kernel variants with maximum mean discrepancies is proposed in this paper.The hidden representations of the task-specific layers in ML-ANet are embedded in the reproducing kernel Hilbert space(RKHS)so that the mean-embeddings of specific features in different domains could be precisely matched.Multiple kernel functions are used to improve feature distribution efficiency for explicit mean embedding matching,which can further reduce domain discrepancy.Adverse weather and cross-camera adaptation examinations are conducted to verify the effectiveness of our proposed ML-ANet.The results show that our proposed ML-ANet achieves higher accuracies than the compared state-of-the-art methods for multi-label image classification in both the adverse weather adaptation and cross-camera adaptation experiments.These results indicate that ML-ANet can alleviate the reliance on fully labeled training data and improve the accuracy of multi-label image classification in various domain shift scenarios.

On‑Ramp Merging for Highway Autonomous Driving:An Application of a New Safety Indicator in Deep Reinforcement Learning

This paper proposes an improved decision-making method based on deep reinforcement learning to address on-ramp merging challenges in highway autonomous driving.A novel safety indicator,time difference to merging(TDTM),is introduced,which is used in conjunction with the classic time to collision(TTC)indicator to evaluate driving safety and assist the merging vehicle in finding a suitable gap in traffic,thereby enhancing driving safety.The training of an autonomous driving agent is performed using the Deep Deterministic Policy Gradient(DDPG)algorithm.An action-masking mechanism is deployed to prevent unsafe actions during the policy exploration phase.The proposed DDPG+TDTM+TTC solution is tested in on-ramp merging scenarios with different driving speeds in SUMO and achieves a success rate of 99.96%without significantly impacting traffic efficiency on the main road.The results demonstrate that DDPG+TDTM+TTC achieved a higher on-ramp merging success rate of 99.96%compared to DDPG+TTC and DDPG.

Study of Longitudinal-Vertical Dynamics for In-Wheel Motor-Driven Electric Vehicles

The in-wheel motor(IWM)-driven electric vehicles(EVs)attract increasing attention due to their advantages in dimensions and controllability.The majority of the current studies on IWM are carried out with the assumption of an ideal actuator,in which the coupling effects between the non-ideal IWM and vehicle are ignored.This paper uses the braking process as an example to investigate the longitudinal-vertical dynamics of IWM-driven EVs while considering the mechanical-electrical coupling effect.First,a nonlinear switched reluctance motor model is developed,and the unbalanced electric magnetic force(UEMF)induced by static and dynamic mixed eccentricity is analyzed.Then,the UEMF is decomposed into longitudinal and vertical directions and included in the longitudinal-vertical vehicle dynamics.The coupling dynamics are demonstrated under different vehicle braking scenarios;numerical simulations are carried out for various road grades,road friction,and vehicle velocities.A novel dynamics vibration absorbing system is adopted to improve the vehicle dynamics.Finally,the simulation results show that vehicle vertical dynamic performance is enhanced.

Depth Estimation Based on Monocular Camera Sensors in Autonomous Vehicles: A Self‑supervised Learning Approach

Estimating depth from images captured by camera sensors is crucial for the advancement of autonomous driving technologies and has gained significant attention in recent years.However,most previous methods rely on stacked pooling or stride convolution to extract high-level features,which can limit network performance and lead to information redundancy.This paper proposes an improved bidirectional feature pyramid module(BiFPN)and a channel attention module(Seblock:squeeze and excitation)to address these issues in existing methods based on monocular camera sensor.The Seblock redistributes channel feature weights to enhance useful information,while the improved BiFPN facilitates efficient fusion of multi-scale features.The proposed method is in an end-to-end solution without any additional post-processing,resulting in efficient depth estimation.Experiment results show that the proposed method is competitive with state-of-the-art algorithms and preserves fine-grained texture of scene depth.

Drivers’ EEG Responses to Different Distraction Tasks

Driver distraction has been deemed a major cause of traffic accidents.However,drivers’brain response activities to different distraction types have not been well investigated.The purpose of this study is to investigate the response of electroencephalography(EEG)activities to different distraction tasks.In the conducted simulation tests,three secondary tasks(i.e.,a clock task,a 2-back task,and a navigation task)are designed to induce different types of driver distractions.Twenty-four participants are recruited for the designed tests,and differences in drivers’brain response activities concerning distraction types are investigated.The results show that the differences in comprehensive distraction are more significant than that in single cognitive distraction.Friedman test and post hoc two-tailed Nemenyi test are conducted to further identify the differences in band activities among brain regions.The results show that the theta energy in the frontal lobe is significantly higher than that in other brain regions in distracted driving,whereas the alpha energy in the temporal lobe significantly decreases compared to other brain regions.These results provide theoretical references for the development of distraction detection systems based on EEG signals.

Deep Reinforcement Learning Enabled Decision-Making for Autonomous Driving at Intersections

Road intersection is one of the most complex and accident-prone traffic scenarios,so it’s challenging for autonomous vehicles(AVs)to make safe and efficient decisions at the intersections.Most of the related studies focus on the solution to a single scenario or only guarantee safety without considering driving efficiency.To address these problems,this study proposed a deep reinforcement learning enabled decision-making framework for AVs to drive through intersections automatically,safely and efficiently.The mapping relationship between traffic images and vehicle operations was obtained by an end-to-end decision-making framework established by convolutional neural networks.Traffic images collected at two timesteps were used to calculate the relative velocity between vehicles.Markov decision process was employed to model the interaction between AVs and other vehicles,and the deep Q-network algorithm was utilized to obtain the optimal driving policy regarding safety and efficiency.To verify the effectiveness of the proposed decision-making framework,the top three accident-prone crossing path crash scenarios at intersections were simulated,when different initial vehicle states were adopted for better generalization capability.The results showed that the developed method could make AVs drive safely and efficiently through intersections in all of the tested scenarios.