In this paper, we address the limitations of traditional teacher-student models, imitation learning, and behaviour cloning in the context of Autonomous/Automated Driving Systems (ADS), where these methods often struggle with incomplete coverage of real-world scenarios. To enhance the robustness of such models, we introduce the use of Counterfactual Explanations (CFEs) as a novel data augmentation technique for end-to-end ADS. CFEs, by generating training samples near decision boundaries through minimal input modifications, lead to a more comprehensive representation of expert driver strategies, particularly in safety-critical scenarios. This approach can therefore help improve the model's ability to handle rare and challenging driving events, such as anticipating darting out pedestrians, ultimately leading to safer and more trustworthy decision-making for ADS. Our experiments in the CARLA simulator demonstrate that CF-Driver outperforms the current state-of-the-art method, achieving a higher driving score and lower infraction rates. Specifically, CF-Driver attains a driving score of 84.2, surpassing the previous best model by 15.02 percentage points. These results highlight the effectiveness of incorporating CFEs in training end-to-end ADS. To foster further research, the CF-Driver code is made publicly available.

Lane changing and obstacle avoidance are one of the most important tasks in automated cars. To date, many algorithms have been suggested that are generally based on path trajectory or reinforcement learning approaches. Although these methods have been efficient, they are not able to accurately imitate a smooth path traveled by an expert driver. In this paper, a method is presented to mimic drivers' behavior using a convolutional neural network (CNN). First, seven features are extracted from a dataset gathered from four expert drivers in a driving simulator. Then, these features are converted from 1D arrays to 2D arrays and injected into a CNN. The CNN model computes the desired steering wheel angle and sends it to an adaptive PD controller. Finally, the control unit applies proper torque to the steering wheel. Results show that the CNN model can mimic the drivers' behavior with an R2-squared of 0.83. Also, the performance of the presented method was evaluated in the driving simulator for 17 trials, which avoided all traffic cones successfully. In some trials, the presented method performed a smoother maneuver compared to the expert drivers.

The technological and scientific challenges involved in the development of autonomous vehicles (AVs) are currently of primary interest for many automobile companies and research labs. However, human-controlled vehicles are likely to remain on the roads for several decades to come and may share with AVs the traffic environments of the future. In such mixed environments, AVs should deploy human-like driving policies and negotiation skills to enable smooth traffic flow. To generate automated human-like driving policies, we introduce a model-free, deep reinforcement learning approach to imitate an experienced human driver's behavior. We study a static obstacle avoidance task on a two-lane highway road in simulation (Unity). Our control algorithm receives a stochastic feedback signal from two sources: a model-driven part, encoding simple driving rules, such as lane-keeping and speed control, and a stochastic, data-driven part, incorporating human expert knowledge from driving data. To assess the similarity between machine and human driving, we model distributions of track position and speed as Gaussian processes. We demonstrate that our approach leads to human-like driving policies.

AI development today has become fixated on singular monolithic models trained end-to-end without any human assistance and encapsulating an almost general intelligence-like variety of tasks together. The resulting models have struggled in areas like content moderation to sufficiently abstract beyond their limited training data. Yet, as Waymo reminds us, the most successful complex AI systems combine multiple deep learning models with traditional hand-coded algorithms to address one of the greatest challenges confronting today's deep learning systems: their inability to abstract from correlation to causation. Waymo put it best this past December when the company noted that "deep learning identifies correlations in the training data, but it arguably cannot build causal models by purely observing correlations … knowing why an expert driver behaved the way they did and what they were reacting to is critical to building a causal model of driving. For this reason, simply having a large number of expert demonstrations to imitate is not enough." The first is hand-coding some rules, like simply telling the vehicle to stop at red stoplights, rather than forcing it to learn this rule from observation.