Trajectory Planning for a Tractor with Multiple Trailers in Extremely Narrow Environments: A Unified Approach
We propose a driver modeling process and its evaluation results of an intelligent autonomous driving policy, which is obtained through reinforcement learning techniques. Assuming a MDP decision making model, Q-learning method is applied to simple but descriptive state and action spaces, so that a policy is developed within limited computational load. The driver could perform reasonable maneuvers, like acceleration, deceleration or lane-changes, under usual traffic conditions on a multi-lane highway. A traffic simulator is also construed to evaluate a given policy in terms of collision rate, average travelling speed, and lane change times. Results show the policy gets well trained under reasonable time periods, where the driver acts interactively in the stochastic traffic environment, demonstrating low collision rate and obtaining higher travelling speed than the average of the environment. Sample traffic simulation videos are postedsit on YouTube.
Master's thesis about Deep Reinforcement Learning for Decision Making in autonomous driving
RRT (Rapidly-Exploring Random Trees) using Dubins curve, with collision check in MATLAB
Modified RRT*-based trajectory planning algorithm with customized heuristic function and feedback linearization controller
This is an RRT demonstartion for a finite volume robot with kinodynamic constraints.