Autonomous vehicles decision-making enhancement using self-determination theory and mixed-precision neural networks

The safe human-level decision-making for expressing the autonomous vehicles and the estimation of the eco vehicles has been proposed for the motion control for the driving behavior. For efficient decision-making, the sensor-based tracking of the autonomous machine for blockchain is to be done. The sensor-based history recording management has to propose, and storing the vehicle's traveling history must be managed. For security reasons, the blockchain is done. Self-determination theory and energy-efficient mixed-precision neural networks are used in autonomous vehicles' decision-making, and this technique is used in making moral decisions. The self-determination theory is used in creating the vehicles traveling steps using the innovative signal delivery system of the autonomous vehicles. The energy-efficient mixed-precision neural networks are used in managing the problem that travels the signal to the vehicles using the mixed-precision neural networks. The vehicle network has been made more efficient for storing the data of the mixed precision value and its neural network from autonomous vehicles. Here 80% of the precision value is raised compared to the previous days. In previous days, 20% of the precision has been calculated in autonomous vehicles. Comparing this, 60% of the precision value has been raised in traveling history. According to these variations, 40%-50% of autonomous vehicles' data transmission that delivers the neural network has been proposed. By improving autonomous vehicles, the efficiency of mixed precision neural networks is the decision-making for efficient precision.