For self-driving cars to navigate safely and efficiently in cities, they need smart path planning strategies. This research explores ways to improve these strategies using the CARLA simulator, focusing on autonomy, trajectory planning, and obstacle avoidance. We use the A* algorithm to find the shortest and most efficient routes, helping vehicles move smoothly even around static obstacles. But it is not just about finding the best route: Our approach also ensures safer and more natural driving by optimizing trajectories and avoiding sudden movements. These improvements make autonomous vehicles better suited for real-world challenges, such as complex road networks and unpredictable situations. Our work contributes to the future of intelligent transportation, bringing self-driving technology one step closer to everyday use. By refining these techniques, we help make autonomous vehicles safer, more efficient, and better prepared to handle the demands of urban environments.
Path Optimization for Autonomous Vehicles in Static Environments Using CARLA Simulation
2025-03-06
417610 byte
Conference paper
Electronic Resource
English
A Waypoint Tracking Controller for Autonomous Vehicles Using CARLA Simulator
Springer Verlag | 2022
|Safe Navigation: Training Autonomous Vehicles using Deep Reinforcement Learning in CARLA
ArXiv | 2023
|Injecting Conflict Situations in Autonomous Driving Simulation using CARLA
ArXiv | 2025
|