Route Planning for Automatic Indoor Driving of Smart Cars

Abstract

While various types of traffic navigation maps play an important role in our life, the complex layout of large number of buildings in the city makes it difficult for people to find destinations and walking routes indoors. Since GPS does not work very accurately inside the buildings, for indoor navigation problem we still have to depend on the traditional front desk human resource consultation. In recent years, the rapid development of artificial intelligence technology has made it possible for smart car navigation instead of the manual consultation. Not only that, smart cars can even handle short-distance goods transportation. Combining indoor positioning technology with different video signals or any other non-GPS satellite positioning technology for directing the smart car to the designated position is a hot research direction these days. In this paper, we mainly study the realization and application of a smart car in the indoor automated driving system. Our proposed smart car, built using the Raspberry Pi 3, uses a series of famous path planning algorithms such as Dijkstra's algorithm, Best priority search and A*(A star) algorithm to plan the driving path of the car's automatic driving. Finally, the real-time obstacle avoidance function is also realized by using ultrasonic ranging, infrared ranging and pan-tilt camera. Several experiments were conducted to compare the efficiency of using different path finding algorithms and the results of using infrared ranging and ultrasonic ranging during obstacle avoidance.