A Quality Diversity Approach to Automatically Generating Human-Robot Interaction Scenarios in Shared Autonomy

Fontaine, Matthew C.; Nikolaidis, Stefanos

doi:10.15607/rss.2021.xvii.036

Cited by 22 publications

(14 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jain and Argall [16] proposed combining multiple predictions by assuming each is independent conditioned on the goal, which we use. Structural challenges to effective shared autonomy have also been identifed in Fontaine and Nikolaidis [10].…”

Section: A Assisted Teleoperationmentioning

confidence: 99%

Gaze Complements Control Input for Goal Prediction During Assisted Teleoperation

Aronson¹,

Admoni²

2022

Robotics: Science and Systems XVIII

View full text Add to dashboard Cite

Shared control systems can make complex robot teleoperation tasks easier for users. These systems predict the user's goal, determine the motion required for the robot to reach that goal, and combine that motion with the user's input. Goal prediction is generally based on the user's control input (e.g., the joystick signal). In this paper, we show that this prediction method is especially effective when users follow standard noisily optimal behavior models. In tasks with input constraints like modal control, however, this effectiveness no longer holds, so additional sources for goal prediction can improve assistance. We implement a novel shared control system that combines natural eye gaze with joystick input to predict people's goals online, and we evaluate our system in a real-world, COVID-safe user study. We fnd that modal control reduces the effciency of assistance according to our model, and when gaze provides a prediction earlier in the task, the system's performance improves. However, gaze on its own is unreliable and assistance using only gaze performs poorly. We conclude that control input and natural gaze serve different and complementary roles in goal prediction, and using them together leads to improved assistance. * * sum a with the user command u directly: a exec = a + u.

show abstract

Section: A Assisted Teleoperationmentioning

confidence: 99%

Gaze Complements Control Input for Goal Prediction During Assisted Teleoperation

Aronson¹,

Admoni²

2022

Robotics: Science and Systems XVIII

View full text Add to dashboard Cite

show abstract

“…Quality diversity optimization is a rapidly growing branch of stochastic optimization with applications in generative design [32,27,26], automatic scenario generation in robotics [21,20,19], reinforcement learning [60,62,57,75], damage recovery in robotics [14], and procedural content generation [30,24,78,15,48,73,68,67]. Our paper introduces a new quality diversity algorithm, CMA-MAE, that bridges the gap between single-objective optimization and quality diversity optimization.…”

Section: Limitations and Future Workmentioning

confidence: 99%

Covariance Matrix Adaptation MAP-Annealing

Fontaine¹,

Nikolaidis²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Single-objective optimization algorithms search for the single highest-quality solution with respect to an objective. In contrast, quality diversity (QD) optimization algorithms, such as Covariance Matrix Adaptation MAP-Elites (CMA-ME), search for a collection of solutions that are both high-quality with respect to an objective and diverse with respect to specified measure functions. We propose a new quality diversity algorithm, Covariance Matrix Adaptation MAP-Annealing (CMA-MAE), which bridges the gap between single-objective optimization and QD optimization. We prove that CMA-MAE smoothly blends between the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) single-objective optimizer and CMA-ME by gradually annealing a discount function with a scalar learning rate. We show that CMA-MAE has better performance than the current state-of-the-art QD algorithms on several benchmark domains and that its performance is empirically invariant to the archive resolution and robust to the discount function learning rate.Preprint. Under review.

show abstract

“…As both the objective and measure functions are part of the problem definition, a user can apply QD to different domains by reducing their problem to a quality diversity problem. As a result, QD algorithms have been applied to procedural content generation [40], robotics [13,33], aerodynamic shape design [11], and scenario generation in human-robot interaction [41,42].…”

Section: Quality Diversity Algorithmsmentioning

confidence: 99%

Deep Surrogate Assisted MAP-Elites for Automated Hearthstone Deckbuilding

Zhang¹,

Fontaine²,

Hoover³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We study the problem of efficiently generating high-quality and diverse content in games. Previous work on automated deckbuilding in Hearthstone shows that the quality diversity algorithm MAP-Elites can generate a collection of high-performing decks with diverse strategic gameplay. However, MAP-Elites requires a large number of expensive evaluations to discover the diverse collection of decks. We propose assisting MAP-Elites with a deep surrogate model trained online to predict game outcomes with respect to candidate decks. MAP-Elites discovers a diverse dataset to improve the surrogate model accuracy, while the surrogate model helps guide MAP-Elites towards promising new content. In a Hearthstone deckbuilding case study, we show that our approach improves the sample efficiency of MAP-Elites and outperforms a model trained offline with random decks, as well as a linear surrogate model baseline, setting a new state-of-the-art for quality diversity approaches in the application domain of automated Hearthstone deckbuilding.

show abstract

A Quality Diversity Approach to Automatically Generating Human-Robot Interaction Scenarios in Shared Autonomy

Cited by 22 publications

References 67 publications

Gaze Complements Control Input for Goal Prediction During Assisted Teleoperation

Gaze Complements Control Input for Goal Prediction During Assisted Teleoperation

Covariance Matrix Adaptation MAP-Annealing

Deep Surrogate Assisted MAP-Elites for Automated Hearthstone Deckbuilding

Contact Info

Product

Resources

About