Regardless of the terrain, weather, visibility, or road surface conditions, improving detection and forecast accuracy is a critical priority for autonomous cars. Little shifts in the images to be collected should be understood even in low-light settings because the vehicle needs more data to make a binding judgment. As a subfield of AI and DL, Recurrent Neural Networks (RNNs) are structured with temporally aware connections between their nodes. As a result, the network can engage in sequential action driven entirely by internal incentives for an extended period. Moreover, cars require enormous computational capacity and a substantial quantity of data sets in an autonomous environment, such as unexpected events, opposing movement, lane conditions, and indestructible barriers. This study presents an effective deep recurrent neural network (Deep RNN) technique for autonomous cars to meet the need for recurrent nodes and capture sequence patterns within the acquired data. In addition, this study shows how to use deep RNN for efficient data annotation. Simulated findings show a significant drop in error when the proposed Deep RNN is utilized in autonomous cars. © 2023 Elsevier B.V., All rights reserved.