The transportation sector is under increasing pressure to reduce greenhouse gas emissions by decarbonizing its operations. One prominent solution that has emerged is the adoption of electric vehicles (EVs). As the electric vehicles market experiences rapid growth, the utilization of lithium-ion batteries (LiB) has become the predominant choice for energy storage. However, it is important to note that lithium-ion battery technology is sensitive to factors, like excessive voltage and temperature. Therefore, the development of an accurate battery model and a reliable state of charge (SOC) estimator is crucial to safeguard against the overcharging and over-discharging of the battery. Numerous studies have been conducted to address lithium-ion battery cell modeling and SOC estimations. These studies have explored variations in the number of RC networks within the model and different estimation methods. However, it is worth mentioning that the capacity of a single lithium-ion battery cell is relatively low and cannot be directly employed in electric vehicles. To meet the total capacity and voltage requirements for electric vehicles, multiple cells are typically connected in series or parallel configurations to form a battery pack. Surprisingly, this aspect has often been overlooked in previous research. To tackle this overlooked challenge, our study introduces a comprehensive battery pack model and an advanced Battery Management System (BMS). We then integrate these components into an electric vehicle model. Subsequently, we simulate the integrated EV-BMS model under the conditions of four different urban driving scenarios to replicate real-world driving conditions. The BMS that we have developed includes an Extended Kalman Filter (EKF)-based SOC estimation system, a mechanism for controlling coolant flow, and a passive cell-balancing algorithm. These components work together to ensure the safe and efficient operation of the battery pack within the electric vehicles.

Feasible local motion planning for autonomous mobile robots in dynamic environments requires predicting how the scene evolves. Conventional navigation stakes rely on a local map to represent how a dynamic scene changes over time. However, these navigation stakes depend highly on the accuracy of the environmental map and the number of obstacles. This study uses semantic segmentation-based drivable area estimation as an alternative representation to assist with local motion planning. Notably, a realistic 3D simulator based on an Unreal Engine was created to generate a synthetic dataset under different weather conditions. A transfer learning technique was used to train the encoder-decoder model to segment free space from the occupied sidewalk environment. The local planner uses a nonlinear model predictive control (NMPC) scheme that inputs the estimated drivable space, the state of the robot, and a global plan to produce safe velocity commands that minimize the tracking cost and actuator effort while avoiding collisions with dynamic and static obstacles. The proposed approach achieves zero-shot transfer from a simulation to real-world environments that have never been experienced during training. Several intensive experiments were conducted and compared with the dynamic window approach (DWA) to demonstrate the effectiveness of our system in dynamic sidewalk environments.