Time-informed task planning in multi-agent collaboration

Maniadakis, Michail; Hourdakis, Emmanouil; Trahanias, Panos

doi:10.1016/j.cogsys.2016.09.004

Cited by 10 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the DP setup can be rather straightforwardly implemented since it does not assume sophisticated or difficult to obtain prior knowledge. For example, it has been very easy to employ DP for the coordination of two similar (Maniadakis et al, 2016b ), or heterogeneous robots (Maniadakis et al, 2016a ) in different application domains.…”

Section: Resultsmentioning

confidence: 99%

“…To address the issues mentioned above, we have recently introduced the Daisy Planner (DP) (Maniadakis et al, 2016a , b ), a new scheme of time-informed planning, which relies on the daisy representation of tasks and adopts time-inclusive multi-criteria ranking of alternative plans. DP operates under the assumption of pursuing immediate, locally optimal assignment of tasks to agents.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The fluent coordination of multi-agent activities plays a crucial role in the joint accomplishment of goals. We have recently introduced (Maniadakis et al, 2016a , b ), a time-informed planner that attributes tasks to agents in a step-by-step manner, accomplishing the effective coordination of multiple agents (see also, Isaacson et al, 2019 ). The planner assumes the daisy-like representation of the composite behavior and is thus termed Daisy Planner (DP).…”

Section: Time-informed Multi-agent Interaction Implementationmentioning

confidence: 99%

“…In particular, each non-busy agent is assigned a new task in a way that maximizes agent's utility for the team, given the current, short-term view of team performance. Full implementation and assessment details of DP have been presented in Maniadakis et al ( 2016a , b ), and are not repeated here and re not listed here for the clarity of presentation.…”

Section: Time-informed Multi-agent Interaction Implementationmentioning

confidence: 99%

“…These regard (i) the representation and memorization of past experiences on a temporally rich domain to facilitate time-informed reasoning in forthcoming sessions, (ii) the perception of the temporal features of evolving real-world procedures to support action coordination with other agents in the environment, and (iii) the planning of actions to facilitate timely accomplishment of goals given the temporal constraints and the dynamic unfolding of multi-agent collaboration. Targeting the implementation of time-aware robotic cognitive systems, we have developed computational modules addressing complementary cognitive skills along the past, present and future disciplines mentioned above (Maniadakis et al, 2016b , 2017 ; Sigalas et al, 2017a , b ; Hourdakis and Trahanias, 2018 ).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Time-Aware Multi-Agent Symbiosis

et al. 2020

Self Cite

View full text Add to dashboard Cite

Contemporary research in human-machine symbiosis has mainly concentrated on enhancing relevant sensory, perceptual, and motor capacities, assuming short-term and nearly momentary interaction sessions. Still, human-machine confluence encompasses an inherent temporal dimension that is typically overlooked. The present work shifts the focus on the temporal and long-lasting aspects of symbiotic human-robot interaction (sHRI). We explore the integration of three time-aware modules, each one focusing on a diverse part of the sHRI timeline. Specifically, the Episodic Memory considers past experiences, the Generative Time Models estimate the progress of ongoing activities, and the Daisy Planner devices plans for the timely accomplishment of goals. The integrated system is employed to coordinate the activities of a multi-agent team. Accordingly, the proposed system (i) predicts human preferences based on past experience, (ii) estimates performance profile and task completion time, by monitoring human activity, and (iii) dynamically adapts multi-agent activity plans to changes in expectation and Human-Robot Interaction (HRI) performance. The system is deployed and extensively assessed in real-world and simulated environments. The obtained results suggest that building upon the unfolding and the temporal properties of team tasks can significantly enhance the fluency of sHRI.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Time-informed Multi-agent Interaction Implementationmentioning

confidence: 99%

Section: Time-informed Multi-agent Interaction Implementationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Time-Aware Multi-Agent Symbiosis

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

Learning Spatio-temporal Characteristics of Human Motions Through Observation

Koskinopoulou

Maniadakis

Trahanias

2018

Advances in Service and Industrial Robotics

View full text Add to dashboard Cite

Help-Estimator: Robot Requests for Help from Humans by Estimating a Person’s Subjective Time

Kimoto

Yasumatsu

Imai

2021

Int J of Soc Robotics

View full text Add to dashboard Cite

In human-robot cooperation, it is effective for a robot to ask a human partner for help to reduce the time required for a task. However, the person might not be able to help the robot if she or he is engaged in something else. In this study, we focused on the person's subjective estimation of the time for a task and investigated its effect on the likelihood of agreeing to help the robot. For this purpose, we developed a Help-Estimator system that decides whether the robot should request help by considering the required time for both the person and the robot to finish their tasks. We conducted an experiment to evaluate such help requests that incorporate the human's subjective time estimation for a task. We found that appropriate timing for requesting help, as estimated from the person's viewpoint, increases the likelihood of the person helping the robot and improves the person's impression of the robot as a partner.

show abstract

Time-informed task planning in multi-agent collaboration

Cited by 10 publications

References 12 publications

Time-Aware Multi-Agent Symbiosis

Time-Aware Multi-Agent Symbiosis

Learning Spatio-temporal Characteristics of Human Motions Through Observation

Help-Estimator: Robot Requests for Help from Humans by Estimating a Person’s Subjective Time

Contact Info

Product

Resources

About