Automotive Science and Engineering

---

The control of Antilock Braking Systems (ABS) is a difficult problem, because of their nonlinearities and uncertainties appearing in their dynamics and parameters. To overcome these issues, this paper proposes a new adaptive controller for the next generation of ABS. After considering a complex vehicle dynamic, a triple adaptive fuzzy control system is presented. Important parameters of the vehicle dynamic include two separated brake torques for front ands rear wheels, as well as longitudinal weight transfer which is caused by the acceleration or deceleration. Because of the nonlinearity of the vehicle dynamic model, three fuzzy-estimators have been suggested to eliminate nonlinear terms of the front and rear wheels’ dynamic. Since the vehicle model parameters change due to variations of road conditions, an adaptive law of the controller is derived based on Lyapunov theory to adapt the fuzzy-estimators and stabilize the entire system. The performance of the proposed controller is evaluated by some simulations on the ABS system. The results demonstrate the effectiveness of the proposed method for ABS under different road conditions.

---

Ensuring that ethically sound decisions are made under complex, real-world conditions is a central challenge in deploying autonomous vehicles (AVs). This paper introduces a human-centric risk mitigation framework using Deep Q-Networks (DQNs) and a specially designed reward function to minimize the likelihood of fatal injuries, passenger harm, and vehicle damage. The approach uses a comprehensive state representation that captures the AV’s dynamics and its surroundings (including the identification of vulnerable road users), and it explicitly prioritizes human safety in the decision-making process. The proposed DQN policy is evaluated in the CARLA simulator across three ethically challenging scenarios: a malfunctioning traffic signal, a cyclist’s sudden swerve, and a child running into the street. In these scenarios, the DQN-based policy consistently minimizes severe outcomes and prioritizes the protection of vulnerable road users, outperforming a conventional collision-avoidance strategy in terms of safety. These findings demonstrate the feasibility of deep reinforcement learning for ethically aligned decision-making in AVs and point toward a pathway for developing safer and more socially responsible autonomous transportation systems.