Multimodal Safe Control for Human-Robot Interaction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Pandya, Ravi, Wei, Tianhao, Liu, Changliu
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929405211705344
author Pandya, Ravi
Wei, Tianhao
Liu, Changliu
author_facet Pandya, Ravi
Wei, Tianhao
Liu, Changliu
contents Generating safe behaviors for autonomous systems is important as they continue to be deployed in the real world, especially around people. In this work, we focus on developing a novel safe controller for systems where there are multiple sources of uncertainty. We formulate a novel multimodal safe control method, called the Multimodal Safe Set Algorithm (MMSSA) for the case where the agent has uncertainty over which discrete mode the system is in, and each mode itself contains additional uncertainty. To our knowledge, this is the first energy-function-based safe control method applied to systems with multimodal uncertainty. We apply our controller to a simulated human-robot interaction where the robot is uncertain of the human's true intention and each potential intention has its own additional uncertainty associated with it, since the human is not a perfectly rational actor. We compare our proposed safe controller to existing safe control methods and find that it does not impede the system performance (i.e. efficiency) while also improving the safety of the system.
format Preprint
id arxiv_https___arxiv_org_abs_2311_11898
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Multimodal Safe Control for Human-Robot Interaction
Pandya, Ravi
Wei, Tianhao
Liu, Changliu
Robotics
Generating safe behaviors for autonomous systems is important as they continue to be deployed in the real world, especially around people. In this work, we focus on developing a novel safe controller for systems where there are multiple sources of uncertainty. We formulate a novel multimodal safe control method, called the Multimodal Safe Set Algorithm (MMSSA) for the case where the agent has uncertainty over which discrete mode the system is in, and each mode itself contains additional uncertainty. To our knowledge, this is the first energy-function-based safe control method applied to systems with multimodal uncertainty. We apply our controller to a simulated human-robot interaction where the robot is uncertain of the human's true intention and each potential intention has its own additional uncertainty associated with it, since the human is not a perfectly rational actor. We compare our proposed safe controller to existing safe control methods and find that it does not impede the system performance (i.e. efficiency) while also improving the safety of the system.
title Multimodal Safe Control for Human-Robot Interaction
topic Robotics
url https://arxiv.org/abs/2311.11898