Shared Autonomy Systems with Stochastic Operator Models

Klaška, David; Kučera, Antonín; Musil, Vít; Řehák, Vojtěch

doi:10.24963/ijcai.2022/640

Cited by 6 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, past work has shown that when making decisions in groups, individuals adapt their own confidence estimates to align with others' [13], raising the possibility that metacognitive processes may be altered when collaborating with humans vs. machines. In addition, an illusion of confidence may play a role in collaborations involving delegation, where human operators can choose to delegate tasks to automated agents [38] and may choose to do so more often if higher confidence is attributed to a potential collaborator. The results of Experiment 5 are especially relevant in this respect, as they suggest that attributions of confidence affect advice taking in a scenario akin to AI support and assistance.…”

Section: Discussionmentioning

confidence: 99%

Illusions of Confidence in Artificial Systems

Colombatto,

Fleming

2023

Preprint

View full text Add to dashboard Cite

To effectively communicate and collaborate with others, we must monitor not only other people’s cognitive states (e.g., what someone thinks or believes), but also their metacognitive states (e.g., how confident they are in their beliefs). Confidence is however rarely communicated explicitly: instead, we often perceive others’ confidence via implicit signals such as speech prosody or movement dynamics. Recent advances in artificial intelligence (AI) have broadened the scope of these metacognitive inferences: artificial agents often perform similarly to humans yet rarely explicitly signal their confidence in their beliefs, raising the question as to how humans attribute confidence to AI. Here we report five pre-registered experiments in which participants observed human and artificial agents make perceptual choices, and reported how confident they thought the observed agent was in each choice. Overall, attributions of confidence were sensitive to observed variables such as task difficulty, accuracy, and response time. Strikingly, participants attributed higher confidence to AI agents compared to other humans, even though their behaviour was identical. An illusion of greater confidence in artificial agents’ decisions generalised across different behavioural profiles (Experiment 2), agent descriptions (Experiment 3), and choice domains (Experiment 4). Attributions of confidence also influenced advice-taking behaviour, as participants were more willing to accept the advice of artificial systems compared to matched humans (Experiment 5). Overall, our results uncover a systematic illusion of confidence in AI decisions, and highlight the importance of metacognition in guiding human-machine interactions.

show abstract

Section: Discussionmentioning

confidence: 99%

Illusions of Confidence in Artificial Systems

Colombatto,

Fleming

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Changes to the autonomy level can occur at any time throughout a task or mission. These changes can be initiated by the robot (robot-initiative) ( Costen et al, 2022 ; Mahmud et al, 2023 ), the human supervisor (human-initiative), or from either the supervisor or the robot (mixed-initiative) ( Chiou et al, 2021 ). While our experiments and demonstration in this manuscript focus on a human-initiative system, robot competency assessment for autonomy adjustment can be applied to mixed-initiative and robot-initiative systems as well.…”

Section: Background and Related Workmentioning

confidence: 99%

Event-triggered robot self-assessment to aid in autonomy adjustment

Conlon,

Ahmed,

Szafir

2024

Front. Robot. AI

View full text Add to dashboard Cite

Introduction: Human–robot teams are being called upon to accomplish increasingly complex tasks. During execution, the robot may operate at different levels of autonomy (LOAs), ranging from full robotic autonomy to full human control. For any number of reasons, such as changes in the robot’s surroundings due to the complexities of operating in dynamic and uncertain environments, degradation and damage to the robot platform, or changes in tasking, adjusting the LOA during operations may be necessary to achieve desired mission outcomes. Thus, a critical challenge is understanding when and how the autonomy should be adjusted.Methods: We frame this problem with respect to the robot’s capabilities and limitations, known as robot competency. With this framing, a robot could be granted a level of autonomy in line with its ability to operate with a high degree of competence. First, we propose a Model Quality Assessment metric, which indicates how (un)expected an autonomous robot’s observations are compared to its model predictions. Next, we present an Event-Triggered Generalized Outcome Assessment (ET-GOA) algorithm that uses changes in the Model Quality Assessment above a threshold to selectively execute and report a high-level assessment of the robot’s competency. We validated the Model Quality Assessment metric and the ET-GOA algorithm in both simulated and live robot navigation scenarios.Results: Our experiments found that the Model Quality Assessment was able to respond to unexpected observations. Additionally, our validation of the full ET-GOA algorithm explored how the computational cost and accuracy of the algorithm was impacted across several Model Quality triggering thresholds and with differing amounts of state perturbations.Discussion: Our experimental results combined with a human-in-the-loop demonstration show that Event-Triggered Generalized Outcome Assessment algorithm can facilitate informed autonomy-adjustment decisions based on a robot’s task competency.

show abstract

“…Markov chains are established models for stochastic processes. Discrete-time Markov chains have been used to model environmental hazards (Tihanyi et al, 2021), resource constraints (de Nijs et al, 2018), disease spread (Gómez et al, 2010), and human task performance (Costen et al, 2022). However, many real world processes operate in continuous time.…”

Section: Modelling Stochastic Processes With Markov Chainsmentioning

confidence: 99%

Right Place, Right Time: Proactive Multi-Robot Task Allocation Under Spatiotemporal Uncertainty

Street,

Lacerda,

Mühlig

et al. 2024

jair

View full text Add to dashboard Cite

For many multi-robot problems, tasks are announced during execution, where task announcement times and locations are uncertain. To synthesise multi-robot behaviour that is robust to early announcements and unexpected delays, multi-robot task allocation methods must explicitly model the stochastic processes that govern task announcement. In this paper, we model task announcement using continuous-time Markov chains which predict when and where tasks will be announced. We then present a task allocation framework which uses the continuous-time Markov chains to allocate tasks proactively, such that robots are near or at the task location upon its announcement. Our method seeks to minimise the expected total waiting duration for each task, i.e. the duration between task announcement and a robot beginning to service the task. Our framework can be applied to any multi-robot task allocation problem where robots complete spatiotemporal tasks which are announced stochastically. We demonstrate the efficacy of our approach in simulation, where we outperform baselines which do not allocate tasks proactively, or do not fully exploit our task announcement models.

show abstract

Shared Autonomy Systems with Stochastic Operator Models

Cited by 6 publications

References 3 publications

Illusions of Confidence in Artificial Systems

Illusions of Confidence in Artificial Systems

Event-triggered robot self-assessment to aid in autonomy adjustment

Right Place, Right Time: Proactive Multi-Robot Task Allocation Under Spatiotemporal Uncertainty

Contact Info

Product

Resources

About