Abstract
In this study, an obstacle avoidance controller based on nonlinear model predictive control is designed in autonomous vehicle navigation. The reference trajectory is predefined using a sigmoid function in accordance with road conditions. When obstacles suddenly appear on a predefined trajectory, the reference trajectory should be adjusted dynamically. For dynamic obstacles, a moving trend function is constructed to predict the obstacle position variances in the predictive horizon. Furthermore, a risk index is constructed and introduced into the cost function to realize collision avoidance by combining the relative position relationship between vehicle and obstacles in the predictive horizon. Meanwhile, lateral acceleration constraint is also considered to ensure vehicle stability. Finally, trajectory dynamic planning and tracking are integrated into a single-level model predictive controller. Simulation tests reveal that the designed controller can ensure real-time trajectory tracking and collision avoidance.
Highlights
With the rapid development of technology in the 21st century, autonomous vehicles have become an attainable reality [1]
Obstacle avoidance refers to perceiving environmental information and generating control commands to navigate a vehicle around obstacles safely [10]–[12]
The reinforcement learning approach is widely applied to autonomous vehicles and robots for trajectory planning or obstacle avoidance
Summary
With the rapid development of technology in the 21st century, autonomous vehicles have become an attainable reality [1]. The reinforcement learning approach is widely applied to autonomous vehicles and robots for trajectory planning or obstacle avoidance Such application can usually ensure safety by mastering a complete state and environment knowledge after experiencing failures during training time [15], [16]. S. Li et al.: Dynamic Trajectory Planning and Tracking for Autonomous Vehicle With Obstacle Avoidance Based on MPC of predicting the future dynamics of a system and receding horizon optimization [20], [21]. Gao proposed a hierarchical obstacle avoidance control architecture in literatures [14], [23]–[25] In his literatures, the path reference values obtained by the upper level re-planning controller were sent to the lower level for path tracking.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
