Learning-based Inverse Perception Contracts and Applications

TL;DR

This paper introduces a learning-based method to characterize perception errors and construct inverse perception contracts (IPCs) for safe control in autonomous systems, demonstrated on a quadcopter landing task.

Contribution

It presents a novel approach to automatically learn perception error bounds and incorporate them into control algorithms for safety assurance.

Findings

Successfully constructed an IPC for a vision pipeline on a quadcopter.

The control algorithm using the learned IPC safely landed the quadcopter.

Baseline control without IPC failed to ensure safe landing.

Abstract

Perception modules are integral in many modern autonomous systems, but their accuracy can be subject to the vagaries of the environment. In this paper, we propose a learning-based approach that can automatically characterize the error of a perception module from data and use this for safe control. The proposed approach constructs an inverse perception contract (IPC) which generates a set that contains the ground-truth value that is being estimated by the perception module, with high probability. We apply the proposed approach to study a vision pipeline deployed on a quadcopter. With the proposed approach, we successfully constructed an IPC for the vision pipeline. We then designed a control algorithm that utilizes the learned IPC, with the goal of landing the quadcopter safely on a landing pad. Experiments show that with the learned IPC, the control algorithm safely landed the quadcopter despite the error from the perception module, while the baseline algorithm without using the learned IPC failed to do so.