CaltechAUTHORS
  A Caltech Library Service

Multi-objective Optimal Control for Proactive Decision Making with Temporal Logic Models

Chinchali, Sandeep P. and Livingston, Scott C. and Pavone, Marco (2019) Multi-objective Optimal Control for Proactive Decision Making with Temporal Logic Models. In: Robotics Research: The 18th International Symposium ISRR. Springer Proceedings in Advanced Robotics. No.10. Springer , Cham, pp. 127-144. ISBN 978-3-030-28618-7. https://resolver.caltech.edu/CaltechAUTHORS:20210423-142417194

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20210423-142417194

Abstract

The operation of today’s robots entails interactions with humans, in settings ranging from autonomous driving amidst human-driven vehicles to collaborative manufacturing. To effectively do so, robots must proactively decode the intent or plan of humans and concurrently leverage such a knowledge for safe, cooperative task satisfaction—a problem we refer to as proactive decision making. However, the problem of proactive intent decoding coupled with robotic control is computationally intractable as a robot must reason over several possible human behavioral models and resulting high-dimensional state trajectories. In this paper, we address the proactive decision making problem using a novel combination of algorithmic and data mining techniques. First, we distill high-dimensional state trajectories of human-robot interaction into concise, symbolic behavioral summaries that can be learned from data. Second, we leverage formal methods to model high-level agent goals, safe interaction, and information-seeking behavior with temporal logic formulae. Finally, we design a novel decision-making scheme that simply maintains a belief distribution over high-level, symbolic models of human behavior, and proactively plans informative control actions. Leveraging a rich dataset of real human driving data in crowded merging scenarios, we generate temporal logic models and use them to synthesize control strategies using tree-based value iteration and reinforcement learning (RL). Results from cooperative and adversarial simulated self-driving car scenarios demonstrate that our data-driven control strategies enable safe interaction, correct model identification, and significant dimensionality reduction.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1007/978-3-030-28619-4_16DOIArticle
Additional Information:© 2020 Springer Nature Switzerland AG. First Online: 28 November 2019. The authors were partially supported by the Office of Naval Research, ONR YIP Program, under Contract N00014-17-1-2433.
Funders:
Funding AgencyGrant Number
Office of Naval Research (ONR)N00014-17-1-2433
Subject Keywords:Decision-making; Formal methods; Human-robot interaction; Data-mining
Series Name:Springer Proceedings in Advanced Robotics
Issue or Number:10
DOI:10.1007/978-3-030-28619-4_16
Record Number:CaltechAUTHORS:20210423-142417194
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20210423-142417194
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:108818
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:23 Apr 2021 22:46
Last Modified:23 Apr 2021 22:46

Repository Staff Only: item control page