Image-Based Conditioning for Action Policy Smoothness in Autonomous Miniature Car Racing with Reinforcement Learning

TL;DR

This paper introduces an image-based conditioning method called CAPS to improve control smoothness in autonomous miniature car racing, leading to faster lap times and more stable control using reinforcement learning.

Contribution

The paper proposes CAPS with image input and sim-to-real transfer to enhance control smoothness and speed in autonomous racing, a novel approach in this domain.

Findings

CAPS reduces average lap time by 21.80%

CAPS stabilizes control at higher speeds

Extensive experiments analyze CAPS components' impact

Abstract

In recent years, deep reinforcement learning has achieved significant results in low-level controlling tasks. However, the problem of control smoothness has less attention. In autonomous driving, unstable control is inevitable since the vehicle might suddenly change its actions. This problem will lower the controlling system's efficiency, induces excessive mechanical wear, and causes uncontrollable, dangerous behavior to the vehicle. In this paper, we apply the Conditioning for Action Policy Smoothness (CAPS) with image-based input to smooth the control of an autonomous miniature car racing. Applying CAPS and sim-to-real transfer methods helps to stabilize the control at a higher speed. Especially, the agent with CAPS and CycleGAN reduces 21.80% of the average finishing lap time. Moreover, we also conduct extensive experiments to analyze the impact of CAPS components.