Adaptive Inter-Robot Trust for Robust Multi-Robot Sensor Coverage

Pierson, Alyssa; Schwager, Mac

doi:10.1007/978-3-319-28872-7_10

Cited by 20 publications

(18 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, in a human-robot collaboration task, human and robot share the same objective metric of task performance. Therefore, similar to previous work [7,31,32,36,38], we assume that human teammates will not expect the robot to deceive them on purpose, and their trust will depend mainly on the perceived robot ability to complete the task successfully.…”

Section: Related Workmentioning

confidence: 95%

Trust-Aware Decision Making for Human-Robot Collaboration

Chen

Nikolaidis

Soh

et al. 2020

J. Hum.-Robot Interact.

View full text Add to dashboard Cite

Trust in autonomy is essential for effective human-robot collaboration and user adoption of autonomous systems such as robot assistants. This paper introduces a computational model which integrates trust into robot decision-making. Specifically, we learn from data a partially observable Markov decision process (POMDP) with human trust as a latent variable. The trust-POMDP model provides a principled approach for the robot to (i) infer the trust of a human teammate through interaction, (ii) reason about the effect of its own actions on human trust, and (iii) choose actions that maximize team performance over the long term. We validated the model through human subject experiments on a table-clearing task in simulation (201 participants) and with a real robot (20 participants). In our studies, the robot builds human trust by manipulating low-risk objects first. Interestingly, the robot sometimes fails intentionally in order to modulate human trust and achieve the best team performance. These results show that the trust-POMDP calibrates trust to improve human-robot team performance over the long term. Further, they highlight that maximizing trust alone does not always lead to the best performance.:2 M. Chen et al. Fig. 1. A robot and a human collaborate to clear a table. The human, with low initial trust in the robot, intervenes to stop the robot from moving the wine glass.This study revealed that, in order to achieve fluent human-robot collaboration, the robot should monitor human trust and influence it so that it matches the system's capabilities. In our study, for instance, the robot should build human trust first by acting in a trustworthy manner, before going for the wine glass.We propose a trust-based computational model of robot decision making: Since trust is not fully observable, we model it as a latent variable in a partially observable Markov decision process (POMDP) [19]. Our trust-POMDP model contains two key components: (i) a trust dynamics model, which captures the evolution of human trust in the robot, and (ii) a human decision model, which connects trust with human actions. Our POMDP formulation can accommodate a variety of trust dynamics and human decision models. Here, we adopt a data-driven approach and learn these models from data.Although prior work has studied human trust elicitation and modeling [12,22,36,37], we close the loop between trust modeling and robot decision-making. The trust-POMDP enables the robot to systematically infer and influence the human collaborator's trust, and leverage trust for improved human-robot collaboration and long-term task performance.Consider again the table clearing example (Figure 2). The trust-POMDP strategy first removes the three plastic water bottles to build up trust and only attempts to remove the wine glass afterwards. In contrast, a baseline myopic strategy maximizes short-term task performance and does not account for human trust in choosing the robot actions. It first removes the wine glass, which offers the highest reward, resulting in unnecessary ...

show abstract

Section: Related Workmentioning

confidence: 95%

Trust-Aware Decision Making for Human-Robot Collaboration

Chen

Nikolaidis

Soh

et al. 2020

J. Hum.-Robot Interact.

View full text Add to dashboard Cite

show abstract

“…These broadly fall under two categories: factors based on the automation's task performance, and those based on its honest integrity. As is typical in robotics research [2,14,10,11], our work assumes that integrity-centric bases are given, i.e. our robots are obedient and never deceptive.…”

Section: Trust Characterizationmentioning

confidence: 99%

“…This Bayesian model also processes variable-rate sources of information in a probabilistically sound manner, and can further accommodate an arbitrary belief for prior trust t0. Finally, OPTIMo combines the two main approaches used by existing trust models, namely by applying causal reasoning to update the robot's trustworthiness based on its task performance [7,10], and analyzing evidential factors to quantify each user's actual degree of trust [2,14]. …”

Section: Human-robot Trust Modelmentioning

confidence: 99%

OPTIMo

Dudek

2015

Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction

View full text Add to dashboard Cite

We present OPTIMo: an Online Probabilistic Trust Inference Model for quantifying the degree of trust that a human supervisor has in an autonomous robot "worker". Represented as a Dynamic Bayesian Network, OPTIMo infers beliefs over the human's moment-to-moment latent trust states, based on the history of observed interaction experiences. A separate model instance is trained on each user's experiences, leading to an interpretable and personalized characterization of that operator's behaviors and attitudes. Using datasets collected from an interaction study with a large group of roboticists, we empirically assess OPTIMo's performance under a broad range of configurations. These evaluation results highlight OPTIMo's advances in both prediction accuracy and responsiveness over several existing trust models. This accurate and near real-time humanrobot trust measure makes possible the development of autonomous robots that can adapt their behaviors dynamically, to actively seek greater trust and greater efficiency within future human-robot collaborations.

show abstract

“…Over the years, the importance of taking into account agents' limited sensing and communication capabilities has become paramount [3], [4]. Recent innovations in the field include, among others, time varying methodologies [5], dynamic approaches [6], and adaptive management of agents' trust [7]. Note that most of the existing literature focuses on continuous space coverage, while in several practical situations it might be required to cover just a discrete set of points of interest (PoI).…”

Section: Introductionmentioning

confidence: 99%

Distributed and proximity-constrained C-means for discrete coverage control

Oliva

Gasparri

Fagiolini

et al. 2017

2017 IEEE 56th Annual Conference on Decision and Control (CDC)

View full text Add to dashboard Cite

In this paper we present a novel distributed coverage control framework for a network of mobile agents, in charge of covering a finite set of points of interest (PoI), such as people in danger, geographically dispersed equipment or environmental landmarks. The proposed algorithm is inspired by C-Means, an unsupervised learning algorithm originally proposed for non-exclusive clustering and for identification of cluster centroids from a set of observations. To cope with the agents' limited sensing range and avoid infeasible coverage solutions, traditional C-Means needs to be enhanced with proximity constraints, ensuring that each agent takes into account only neighboring PoIs. The proposed coverage control framework provides useful information concerning the ranking or importance of the different PoIs to the agents, which can be exploited in further application-dependent data fusion processes, patrolling, or disaster relief applications.

show abstract

Adaptive Inter-Robot Trust for Robust Multi-Robot Sensor Coverage

Cited by 20 publications

References 15 publications

Trust-Aware Decision Making for Human-Robot Collaboration

Trust-Aware Decision Making for Human-Robot Collaboration

OPTIMo

Distributed and proximity-constrained C-means for discrete coverage control

Contact Info

Product

Resources

About