Human and robot behavior modeling for probabilistic cognition of an autonomous service robot

Schmidt-Rohr, Sven R.; Lösch, Martin; Dillmann, Rdiger

doi:10.1109/roman.2008.4600738

Cited by 8 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To effectively model behaviours for HSRs such as robowaiters, Schmidt-Rohr et al [12] applied Reinforcement Learning (RL) for modelling robot behaviours by understanding human activity through speech and posture. Yet, the focus of this work was to only model correct waiter behaviour, without any adaptation.…”

Section: A Humanoid Service Robotsmentioning

confidence: 99%

Learning Socially Appropriate Robo-waiter Behaviours through Real-time User Feedback

McQuillin

Churamani

Güneş

2022

2022 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI)

View full text Add to dashboard Cite

Current Humanoid Service Robot (HSR) behaviours mainly rely on static models that cannot adapt dynamically to meet individual customer attitudes and preferences. In this work, we focus on empowering HSRs with adaptive feedback mechanisms driven by either implicit reward, by estimating facial affect, or explicit reward, by incorporating verbal responses of the human 'customer'. To achieve this, we first create a custom dataset, annotated using crowd-sourced labels, to learn appropriate approach (positioning and movement) behaviours for a Robowaiter. This dataset is used to pre-train a Reinforcement Learning (RL) agent to learn behaviours deemed socially appropriate for the robo-waiter. This model is later extended to include separate implicit and explicit reward mechanisms to allow for interactive learning and adaptation from user social feedback. We present a within-subjects Human-Robot Interaction (HRI) study with 21 participants implementing interactions between the robowaiter and human customers implementing the above-mentioned model variations. Our results show that both explicit and implicit adaptation mechanisms enabled the adaptive robo-waiter to be rated as more enjoyable and sociable, and its positioning relative to the participants as more appropriate compared to using the pre-trained model or a randomised control implementation.

show abstract

Section: A Humanoid Service Robotsmentioning

confidence: 99%

Learning Socially Appropriate Robo-waiter Behaviours through Real-time User Feedback

McQuillin

Churamani

Güneş

2022

2022 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI)

View full text Add to dashboard Cite

show abstract

“…When it comes to robotic applications the task becomes even more challenging since the amount of onboard sensing devices is limited, while the understanding of human activities mostly boils down to finding good representations of the sensed primitives [38]. The partial observability of the scene primitives and the uncertainty of human actions gave thrust to the development of strategies that express the perception uncertainties, the stochastic human behavior and the typical mission objectives with explicit Partially Observable Markov Decision Process (POMDP) models [44]. Authors in [18] proposed a knowledge driven method for automatically generating activity analysis and recognition based on POMDP models and context sensitive prompting systems.…”

Section: Behavior Understanding From Daily Activities Monitoringmentioning

confidence: 99%

Understanding of Human Behavior with a Robotic Agent Through Daily Activity Analysis

Kostavelis

Vasileiadis

Skartados

et al. 2019

Int J of Soc Robotics

View full text Add to dashboard Cite

Personal assistive robots to be realized in the near future should have the ability to seamlessly coexist with humans in unconstrained environments, with the robot's capability to understand and interpret the human behavior during human-robot cohabitation significantly contributing towards this end. Still, the understanding of human behavior through a robot is a challenging task as it necessitates a comprehensive representation of the high-level structure of the human's behavior from the robot's low-level sensory input. The paper at hand tackles this problem by demonstrating a robotic agent capable of apprehending human daily activities through a method, the Interaction Unit analysis, that enables activities' decomposition into a sequence of units, each one associated with a behavioral factor. The modelling of human behavior is addressed with a Dynamic Bayesian Network that operates on top of the Interaction Unit, offering quantification of the behavioral factors and the formulation of the human's behavioral model. In addition, lightweight human action and object manipulation monitoring strategies have been developed, based on RGB-D and laser sensors, tailored for onboard robot operation. As a proof of concept, we used our robot to evaluate the ability of the method to differentiate among the examined human activities, as well as to assess the capability of behavior modeling of people with Mild Cognitive Impairment. Moreover, we deployed our robot in 12 real

show abstract

“…In addition to previously mentioned works on modeling HRI and generating behaviors [4,5,10,21,22,6,20], kinodynamic planning with RRT can also be used to solve search problems with dynamic constraints [12]. However, as with most planning algorithms, this requires specifying a desired goal state that may not be reachable.…”

Section: Related Workmentioning

confidence: 99%

“…If so, can the tools of control theory generate useful policies? Previous work on modeling HRI scenarios and generating appropriate behaviors include creating belief models of the robot and human [4,5], probabilistic anticipatory action selection [10], collaborative agent planning [21], motion planning for navigation to maximize human comfort [22], fluent-turn taking using timed petri-nets [6], utilizing POMDPs for modeling cognition of an autonomous service robot [20], and many others. For all scenarios the robot's cognitive model of the world and the human was necessary to generate appropriate actions to address the task at hand.…”

Section: Introductionmentioning

confidence: 99%

Exploring Model Predictive Control to Generate Optimal Control Policies for HRI Dynamical Systems

Jorgensen,

Campbell,

Llado

et al. 2017

Preprint

View full text Add to dashboard Cite

We model Human-Robot-Interaction (HRI) scenarios as linear dynamical systems and use Model Predictive Control (MPC) with mixed integer constraints to generate humanaware control policies. We motivate the approach by presenting two scenarios. The first involves an assistive robot that aims to maximize productivity while minimizing the human's workload, and the second involves a listening humanoid robot that manages its eye contact behavior to maximize "connection" and minimize social "awkwardness" with the human during the interaction. Our simulation results show that the robot generates useful behaviors as it finds control policies to minimize the specified cost function. Further, we implement the second scenario on a humanoid robot and test the eye contact scenario with 48 human participants to demonstrate and evaluate the desired controller behavior. The humanoid generated 25% more eye contact when it was told to maximize connection over when it was told to maximize awkwardness. However, despite showing the desired behavior, there was no statistical difference between the participant's perceived connection with the humanoid.

show abstract

Human and robot behavior modeling for probabilistic cognition of an autonomous service robot

Cited by 8 publications

References 7 publications

Learning Socially Appropriate Robo-waiter Behaviours through Real-time User Feedback

Learning Socially Appropriate Robo-waiter Behaviours through Real-time User Feedback

Understanding of Human Behavior with a Robotic Agent Through Daily Activity Analysis

Exploring Model Predictive Control to Generate Optimal Control Policies for HRI Dynamical Systems

Contact Info

Product

Resources

About