Reinforcement learning for safety-critical control of an automated vehicle

TL;DR

This paper presents a reinforcement learning-based neural network controller for automated vehicle navigation, trained with PPO, validated through KPIs, and deployed on FPGA hardware for real-world testing.

Contribution

It introduces a data-driven decision-making approach for vehicle control using reinforcement learning, with validation in simulation and real-world deployment on FPGA hardware.

Findings

Controller successfully follows predefined paths

Effective obstacle avoidance demonstrated

Deployed on FPGA for real-time control

Abstract

We present our approach for the development, validation and deployment of a data-driven decision-making function for the automated control of a vehicle. The decisionmaking function, based on an artificial neural network is trained to steer the mobile robot SPIDER towards a predefined, static path to a target point while avoiding collisions with obstacles along the path. The training is conducted by means of proximal policy optimisation (PPO), a state of the art algorithm from the field of reinforcement learning. The resulting controller is validated using KPIs quantifying its capability to follow a given path and its reactivity on perceived obstacles along the path. The corresponding tests are carried out in the training environment. Additionally, the tests shall be performed as well in the robotics situation Gazebo and in real world scenarios. For the latter the controller is deployed on a FPGA-based development platform, the FRACTAL platform, and integrated into the SPIDER software stack.