Deep Deterministic Path Following
This is an incremental application of an existing reinforcement learning method to a specific autonomous driving task.
The paper tackled the problem of controlling a simulated car for path following using the Deep Deterministic Policy Gradient algorithm, resulting in the agent learning a policy that achieved small cross-track error and adapted acceleration to minimize velocity error.
This paper deploys the Deep Deterministic Policy Gradient (DDPG) algorithm for longitudinal and lateral control of a simulated car to solve a path following task. The DDPG agent was implemented using PyTorch and trained and evaluated on a custom kinematic bicycle environment created in Python. The performance was evaluated by measuring cross-track error and velocity error, relative to a reference path. Results show how the agent can learn a policy allowing for small cross-track error, as well as adapting the acceleration to minimize the velocity error.