Urban parking prices are uniform over large areas and do not reflect spatially heterogeneous parking supply and demand. Underpricing results in high parking occupancy in the subareas where the demand exceeds supply and lengthy searches for vacant parking, whereas overpricing leads to low occupancy and hampered economic vitality. In recent years several cities around the world initiated pilot projects for adjusting curb-parking prices to demand. The San Francisco project was reviewed by scholars who found that it achieved its goals. However estimation of parking occupation in these projects relies on sensors that cost millions of dollars to set up and operate. We present the GIS-Based Nearest Pocket for Prices Algorithm (NPPA), a spatially explicit algorithm for establishing on-and off-street parking prices that guarantee a predetermined uniform level of occupation over the entire area. We apply the NPPA for establishing adaptive parking prices that guarantee 90% parking occupancy in the Israeli city of Bat Yam. For the Autonomous Vehicles (AV) parking prices can be established at a resolution of a street link, whereas for the human drivers sufficiently large zones of the uniform parking prices are preferable. During the period of transition, AV can react to high-resolution and human drivers to low-resolution price patterns.