Batteries are primary source of clean energy for various applications such as transportation, grid storage & mobile systems. In case of transportation, the effective use of existing battery technology in Electrical Vehicles (EVs) & Hybrid Electrical Vehicles (HEVs) remains a challenge because of inaccurate battery state-of-charge (SoC) & state-of-health (SoH) models. A battery’s stored energy & its performance are difficult to infer from electrically measured parameters of a battery. This research paper aims at describing different battery technologies used in transportation applications & their performance comparison, comparison of different SoC & SoH indication algorithms and commercially available Battery Management System (BMS). The goal of all the presented SoC & SoH indication algorithms is to select an accurate algorithm and to design an advanced BMS capable of providing an accurate indication of battery state. Further, this research paper describes the Neuro- Fuzzy & statistical controllers to be incorporated in Advanced BMS for accurate monitoring of battery’s SoC & SoH respectively. In Neuro-Fuzzy approach, a neural network is used to model a nonlinear electrochemical behavior of the Lead-acid battery. In statistical model, a regression method is employed to predict the SoH. This paper also describes MATLAB simulation of artificial neural network (ANN) model selected for Advanced BMS design & the Field Programmable Gate Array (FPGA) design scheme for BMS implementation. The SoC and SoH estimation results of lead-acid battery using Simulink and RTL (register transfer level) models are also summarized in this paper. FPGA implementation would provide the chip design to determine accurate SoC & SoH of the lead acid battery.