Imitation Learning for Generalizable Self-driving Policy with Sim-to-real Transfer

Zoltán Lőrincz, Márton Szemenyei, Robert Moni

Keywords: Imitation Learning, Sim-to-real, Domain Randomization, Domain Adaptation, self-driving policy learning

TL;DR: In this paper, we used Imitation Learning techniques to solve a complex self-driving robotics task. Our results demonstrate that it is favorable to use DAgger as it achieves the best performance with slightly more training time compared to BC.

Abstract:

Imitation Learning uses the demonstrations of an expert to uncover the optimal policy and it is suitable for real-world robotics tasks as well. In this case, however, the training of the agent is carried out in a simulation environment due to safety, economic and time constraints. Later, the agent is applied in the real-life domain using sim-to-real methods. In this paper, we apply Imitation Learning methods that solve a robotics task in a simulated environment and use transfer learning to apply these solutions in the real-world environment. Our task is set in the Duckietown environment, where the robotic agent has to follow the right lane based on the input images of a single forward-facing camera. We present three Imitation Learning and two sim-to-real methods capable of achieving this task. A detailed comparison is provided
on these techniques to highlight their advantages and disadvantages.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2206.10797/code)