Balanced Information Gathering and Goal-Oriented Actions in Shared Autonomy

Brooks, Connor; Szafir, Daniel

doi:10.1109/hri.2019.8673192

Cited by 24 publications

(18 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the current trend in robotics literature (e.g., [1,2,3,4]), we believe that it is implausible to learn the human's behavior by only passively observing his/her states and actions. Indeed, the human's trajectory may not encode sufficient information about the human.…”

Section: Introductionmentioning

confidence: 88%

“…Problem 1: Consider a HRI, in which the robot and the human are moving to two different goal locations. Suppose that the robot model is as in (1), and the robot uses the receding predictive control given in (2) to determine the next action. Suppose that the human's model is as in (3), and the human decides the next action via optimization problem (4).…”

Section: Problem Statementmentioning

confidence: 99%

“…The function P d (u H |x H , x R ; β) describes the probability distribution of the human's action if the human chooses the action according to the the goal and safety objective functions. Assuming that the robot can observe the human's state, one 1 We understand that there might be some differences between people. However, this paper does not aim to deal with the differences.…”

Section: A Human Action Predictionmentioning

confidence: 99%

See 2 more Smart Citations

Toward Safe and Efficient Human-Robot Interaction via Behavior-Driven Danger Signaling

Hosseinzadeh,

Sinopoli,

Bobick

2021

Preprint

View full text Add to dashboard Cite

This paper introduces the notion of danger awareness in the context of Human-Robot Interaction (HRI), which decodes whether a human is aware of the existence of the robot, and illuminates whether the human is willing to engage in enforcing the safety. This paper also proposes a method to quantify this notion as a single binary variable, so-called danger awareness coefficient. By analyzing the effect of this coefficient on the human's actions, an online Bayesian learning method is proposed to update the belief about the value of the coefficient. It is shown that based upon the danger awareness coefficient and the proposed learning method, the robot can build a predictive human model to anticipate the human's future actions. In order to create a communication channel between the human and the robot, to enrich the observations and get informative data about the human, and to improve the efficiency of the robot, the robot is equipped with a danger signaling system. A predictive planning scheme, coupled with the predictive human model, is also proposed to provide an efficient and Probabilistically safe plan for the robot. The effectiveness of the proposed scheme is demonstrated through simulation studies on an interaction between a self-driving car and a pedestrian.

show abstract

Section: Introductionmentioning

confidence: 88%

Section: Problem Statementmentioning

confidence: 99%

Section: A Human Action Predictionmentioning

confidence: 99%

See 1 more Smart Citation

Toward Safe and Efficient Human-Robot Interaction via Behavior-Driven Danger Signaling

Hosseinzadeh,

Sinopoli,

Bobick

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…But if 𝜆 is too high, then 𝑅 could disregard their objective, and choose actions that are maximally informative, but also suboptimal or dangerous ( [10] discuss this in greater detail). Determining how best to address this trade-off between exploring informative actions, and exploiting rewarding actions, is a topic of recent and ongoing research [3,4].…”

Section: Active Information Gathering In Stackelberg Gamesmentioning

confidence: 99%

Active Altruism Learning and Information Sufficiency for Autonomous Driving

Geary,

Gouk,

Ramamoorthy

2021

Preprint

View full text Add to dashboard Cite

Safe interaction between vehicles requires the ability to choose actions that reveal the preferences of the other vehicles. Since exploratory actions often do not directly contribute to their objective, an interactive vehicle must also able to identify when it is appropriate to perform them. In this work we demonstrate how Active Learning methods can be used to incentivise an autonomous vehicle (AV) to choose actions that reveal information about the altruistic inclinations of another vehicle. We identify a property, Information Sufficiency, that a reward function should have in order to keep exploration from unnecessarily interfering with the pursuit of an objective. We empirically demonstrate that reward functions that do not have Information Sufficiency are prone to inadequate exploration, which can result in sub-optimal behaviour. We propose a reward definition that has Information Sufficiency, and show that it facilitates an AV choosing exploratory actions to estimate altruistic tendency, whilst also compensating for the possibility of conflicting beliefs between vehicles.

show abstract

“…Although shared control has been shown to improve efficiency, human teleoperators often display a hesitancy to use these systems [10], [11]. We believe that one potential reason for this hesitancy is a lack of understanding of the assistive controller's intent.…”

Section: Introductionmentioning

confidence: 99%

Visualization of Intended Assistance for Acceptance of Shared Control

Brooks¹,

Szafir²

2020

Preprint

Self Cite

View full text Add to dashboard Cite

In shared control, advances in autonomous robotics are applied to help empower a human user in operating a robotic system. While these systems have been shown to improve efficiency and operation success, users are not always accepting of the new control paradigm produced by working with an assistive controller. This mismatch between performance and acceptance can prevent users from taking advantage of the benefits of shared control systems for robotic operation. To address this mismatch, we develop multiple types of visualizations for improving both the legibility and perceived predictability of assistive controllers, then conduct a user study to evaluate the impact that these visualizations have on user acceptance of shared control systems. Our results demonstrate that shared control visualizations must be designed carefully to be effective, with users requiring visualizations that improve both legibility and predictability of the assistive controller in order to voluntarily relinquish control.

show abstract

Balanced Information Gathering and Goal-Oriented Actions in Shared Autonomy

Cited by 24 publications

References 20 publications

Toward Safe and Efficient Human-Robot Interaction via Behavior-Driven Danger Signaling

Toward Safe and Efficient Human-Robot Interaction via Behavior-Driven Danger Signaling

Active Altruism Learning and Information Sufficiency for Autonomous Driving

Visualization of Intended Assistance for Acceptance of Shared Control

Contact Info

Product

Resources

About