Currently used approach :-
Step 1: Use bayesian optimization to find the global optimal racing line and save the coordinates for the trajectory generated in a text file. References :- https://arxiv.org/pdf/2002.04794.pdf
Step 2: Run MPC on the global trajectory generated to locally avoid obstacles and perform overtaking maneuver with competitor vehicles. References :- Model-predictive active steering and obstacle avoidance for autonomous ground vehicles, Optimization‐based autonomous racing of 1:43 scale RC cars, “Kinematic and Dynamic Vehicle Models for Autonomous Driving Control Design” ,Jason Kong , Mark Pfeiffer, Georg Schildbach , Francesco Borrelli
- Install rtidds-connext, scadi python libraries using pip install