HATP/EHDA: A Robot Task Planner Anticipating and Eliciting Human Decisions and Actions

Buisan, Guilhem; Favier, Anthony; Mayima, Amandine; Alami, Rachid

doi:10.1109/icra46639.2022.9812227

Cited by 4 publications

(9 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have proposed a generic supervision software dedicated to human-robot collaboration, within a cognitive architecture, which manages the robot high-level decisions. It was used to control the robot in different task contexts: the StackBuildingTask as presented in this paper, the Director Task [18], a tabletop scenario [28], [29], and a directiongiving task [30]. Have we fulfilled the requirements listed in Section III-A?…”

Section: Discussionmentioning

confidence: 99%

JAHRVIS, a Supervision System for Human-Robot Collaboration

Mayima

Clodic²,

Alami³

2022

2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

Self Cite

View full text Add to dashboard Cite

The supervision component is the binder of a robotic architecture. Without it, there is no task, no interaction happening, it conducts the other components of the architecture towards the achievement of a goal, which means, in the context of a collaboration with a human, to bring changes in the physical environment and to update the human partner mental state. However, not so much work focus on this component in charge of the robot decision-making and control, whereas this is the robot puppeteer. Most often, either tasks are simply scripted, or the supervisor is built for a specific task. Thus, we propose JAHRVIS, a Joint Action-based Human-aware supeR-VISor. It aims at being task-independent while implementing a set of key joint action and collaboration mechanisms. With this contribution, we intend to move the deployment of autonomous collaborative robots forward, accompanying this paper with our open-source code.

show abstract

Section: Discussionmentioning

confidence: 99%

JAHRVIS, a Supervision System for Human-Robot Collaboration

Mayima

Clodic²,

Alami³

2022

2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The HATP/EHDA framework [7] comprises a dual HTNbased task specification model. For more details about HTN refer to [30].…”

Section: B the Hatp/ehda Frameworkmentioning

confidence: 99%

“…To estimate the next possible actions that an agent φ ∈ Agents is likely to perform in a state s i ∈ S, we proceed in the same way as in [7]. We refine the agent's agenda tn φ based on its belief val φ i and obtain a refinement as follows ref(tn φ i , val φ i ) = {(a 1 , tn 1 ), ..., (a j , tn j )}.…”

Section: Augmented Problem Specificationsmentioning

confidence: 99%

“…For seamless human-robot collaboration, we believe that it is essential not to restrict human behaviors, and hence, we consider the human as an uncontrollable agent. Recent offline planning frameworks [7], [8] use human task models to estimate and handle uncontrollable human behaviors congruent to the shared task. Doing so allows for planning robot's actions accordingly and generating robot plans that are implicitly coordinated and compliant with every possible human action.…”

Section: Introductionmentioning

confidence: 99%

“…In this work, we propose to extend our prior work HATP/EHDA [7] which stands for Human-Aware Task Planner Emulating Human Decisions and Actions. We first enriched its task specifications to explicitly capture the observability properties of the environment.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Models and Algorithms for Human-Aware Task Planning with Integrated Theory of Mind

Favier,

Shekhar,

Alami

2023

2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

Self Cite

View full text Add to dashboard Cite

It is essential for a collaborative robot to consider the Theory of Mind (ToM) when interacting with humans. Indeed, performing an action in the absence of another agent may create false beliefs like in the well-known Sally & Anne Task [1]. The robot should be able to detect, react to, and even anticipate false beliefs of other agents with a detrimental impact on the task to achieve. Currently, ToM is mainly used to control the task execution and resolve in a reactive way the detrimental false beliefs. Some works introduce ToM at the planning level by considering distinct beliefs, and we are in this context. This work proposes an extension of an existing human-aware task planner and effectively allows the robot to anticipate a false human belief ensuring a smooth collaboration through an implicitly coordinated plan. First, we propose to capture the observability properties of the environment in the state description using two observability types and the notion of co-presence. They allow us to maintain distinct agent beliefs by reasoning directly on what agents can observe through specifically modeled Situation Assessment processes, instead of reasoning of action effects. Then, thanks to the better estimated human beliefs, we can predict if a false belief with adverse impact will occur. If that is the case then, first, the robot's plan can be to communicate minimally and proactively. Second, if this false belief is due to a non-observed robot action, the robot's plan can be to postpone this action until it can be observed by the human, avoiding the creation of the false belief. We implemented our new conceptual approach, discuss its effectiveness qualitatively, and show experimental results on three novel domains.

show abstract

A Knowledge Rich Task Planning Framework for Human-Robot Collaboration

Shekhar,

Favier,

Alami

et al. 2023

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

In this paper, we position ourselves within the context of collaborative planning. Drawing upon our recent research, we introduce a novel, knowledge rich task planning framework that represents and reasons and effectively addresses agents' first-order false beliefs to solving a task planning problem with a shared goal. Our contributions to this work are as follows: First, to enhance the reasoning abilities of an existing framework, an intuitive observability model for situation assessment is addressed, and for that, an improved knowledge modeling is considered. This effectively captures agents' predictable false beliefs and motivates us to exploit the power of off-the-shelf knowledge reasoners. Second, a new planning approach that incorporates this improved encoding. And, to show the effectiveness of our planner and present our initial findings and proof of concept, we conduct a thorough use case analysis.

show abstract

HATP/EHDA: A Robot Task Planner Anticipating and Eliciting Human Decisions and Actions

Cited by 4 publications

References 22 publications

JAHRVIS, a Supervision System for Human-Robot Collaboration

JAHRVIS, a Supervision System for Human-Robot Collaboration

Models and Algorithms for Human-Aware Task Planning with Integrated Theory of Mind

A Knowledge Rich Task Planning Framework for Human-Robot Collaboration

Contact Info

Product

Resources

About