Abstract
Existing potential functions (PFs) utilized in autonomous vehicles mainly focus on solving the path-planning problems in some conventional driving scenarios; thus, their performance may not be satisfactory in the context of emergency obstacle avoidance. Therefore, we propose a novel model predictive path-planning controller (MPPC) combined with PFs to handle complex traffic scenarios (e.g., emergency avoidance when a sudden accident occurs). Specifically, to enhance the safety of the PFs, we developed an MPPC to handle an emergency case with a sigmoid-based safe passage embedded in the MPC constraints (SPMPC) with a specific triggering analysis algorithm on monitoring traffic emergencies. The presented PF-SPMPC algorithm was compiled in a comparative simulation study using MATLAB/Simulink and CarSim. The algorithm outperformed the latest PF-MPC approach to eliminate the severe tire oscillations and guarantee autonomous driving safety when handling the traffic emergency avoidance scenario.
Highlights
I N RECENT years, researchers from both industry and academia have attempted to develop autonomous driving technologies that can ensure better safety during daily travel
Safety planning has been recently stressed in autonomous vehicles, e.g., interactive planning considering riskaverse decisions is used for adversarial scenarios [3], and probabilistic planning with safety assurance is proposed in the traffic weaving scenario for human-robot vehicle interactions [4]
To guarantee the safety of potential functions (PFs) even in traffic emergencies, we propose a novel model predictive path-planning controller (MPPC) with a built-in safe passage (SP) to handle situations where PFs fail to plan a safe and smooth path when the front obstacle vehicle suddenly decelerates
Summary
I N RECENT years, researchers from both industry and academia have attempted to develop autonomous driving technologies that can ensure better safety during daily travel. Research on autonomous vehicles has encountered some obstacles because experimental road tests have caused major accidents. These safety issues have drawn public attention to the fact that current autonomous vehicles cannot guarantee safety in dangerous situations (e.g., inclement weather conditions, uneven pavement, and sudden obstacles). To expand the safety planning for emergency scenarios, potential functions (PFs), which model the 3D risk field for real-time path generation, become one of the mainstream planning algorithms in the current research focus [5].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
