A new speed planning method based on predictive curvature calculation for autonomous driving

As the number of vehicles in traffic is increasing day by day, the accident rates and driving effort are significantly raising. For this reason, ensuring safety and driving comfort is becoming more and more important. Driver assistance systems are the most common systems that are adopted for this purpose. With the development of technology, lane tracking support and adaptive cruise control systems are now being sold as standard equipment. More advanced research is being done for fully autonomous driving. One of the most critical parts of autonomous driving is speed profile planning. In this paper, a curvature-based predictive speed planner is designed using a fuzzy logic strategy. In addition to the predictive curvature value, lateral error to the planned path is considered for the final decision. With the help of the proposed predictive nature, which is not included in classical curvature-based planners, the vehicle is able to reduce the speed before cornering. Similarly, it starts increasing the speed when it is still in a curve but very near to the straight part of the road. In order to illustrate the efficiency of the proposed method and compare it with other approaches, the simulations are performed using realistic vehicle dynamics models of CarMaker software. After the comparative analysis, the designed planner is utilized on a real 1/10 scaled autonomous vehicle platform to show its real-world performance. The results show that the proposed speed planner is an effective and promising algorithm for both the comfort and path tracking performance.