Modern transportation stipulates reliability through Electric Vehicles, therefore, it is crucial to have a projection of Electric Vehicle’s battery life and health. A corresponding attribute which characterizes the battery’s life and reliability is its Remaining Useful Life (RUL). It renders an exclusive indication of how long the battery can function or the number of discharge cycles remaining before it must be put out of action due to failure, degradation or wear (maximum threshold). This paper proposes a quantitative methodology for the Remaining Useful Life (RUL) estimation of Li-ion Batteries to utilize it in Electric Vehicle’s Battery. The “Nasa Prognostics Centre of Excellence Battery Dataset (Nasa PCoE Battery Dataset)” was used in RUL estimation of a battery leveraging sophisticated data-driven Deep Learning (DL) models- ‘Neural Controlled Differential Equation (NCDE)’, ‘TabNet Regressor’, and ‘Time Series Transformers (TST)’. These models used time series sensor data collected during charge-discharge cycles. This study applies these models to gain an understanding of ranging features like voltage, current, temperature and capacity. The results of NCDE, TabNet and TST shows the RMSE of 2.2734, 6.2313, and 3.8311 and R2 of 0.9965, 0.9839 and 0.9939, respectively.