Zero-Shot Policy Transferability for the Control of a Scale Autonomous Vehicle

TL;DR

This paper demonstrates zero-shot transfer of a neural network control policy for a scale autonomous vehicle using a custom simulation platform, without real-world training data, across different operational scenarios.

Contribution

It introduces a novel in-house simulation platform and a neural network controller trained solely on circular trajectories for zero-shot transfer in autonomous vehicle control.

Findings

Successful zero-shot transfer of control policies demonstrated

Neural network trained on circular trajectories generalizes to waypoint-following tasks

Two training approaches: human-in-the-loop and MPC-based training

Abstract

We report on a study that employs an in-house developed simulation infrastructure to accomplish zero shot policy transferability for a control policy associated with a scale autonomous vehicle. We focus on implementing policies that require no real world data to be trained (Zero-Shot Transfer), and are developed in-house as opposed to being validated by previous works. We do this by implementing a Neural Network (NN) controller that is trained only on a family of circular reference trajectories. The sensors used are RTK-GPS and IMU, the latter for providing heading. The NN controller is trained using either a human driver (via human in the loop simulation), or a Model Predictive Control (MPC) strategy. We demonstrate these two approaches in conjunction with two operation scenarios: the vehicle follows a waypoint-defined trajectory at constant speed; and the vehicle follows a speed profile that changes along the vehicle's waypoint-defined trajectory. The primary contribution of this work is the demonstration of Zero-Shot Transfer in conjunction with a novel feed-forward NN controller trained using a general purpose, in-house developed simulation platform.