Damien Pellier

Damien Pellier, Alexandre Albore, Humbert Fiorino et al.

Real world applications as in industry and robotics need modelling rich and diverse automated planning problems. Their resolution usually requires coordinated and concurrent action execution. In several cases, these problems are naturally decomposed in a hierarchical way and expressed by a Hierarchical Task Network (HTN) formalism. HDDL, a hierarchical extension of the Planning Domain Definition Language (PDDL), unlike PDDL 2.1 does not allow to represent planning problems with numerical and temporal constraints, which are essential for real world applications. We propose to fill the gap between HDDL and these operational needs and to extend HDDL by taking inspiration from PDDL 2.1 in order to express numerical and temporal expressions. This paper opens discussions on the semantics and the syntax needed for a future HDDL 2.1 extension.

Nicolas Cavrel, Damien Pellier, Humbert Fiorino

The Hierarchical Task Network (HTN) formalism is used to express a wide variety of planning problems as task decompositions, and many techniques have been proposed to solve them. However, few works have been done on temporal HTN. This is partly due to the lack of a formal and consensual definition of what a temporal hierarchical planning problem is as well as the difficulty to develop heuristics in this context. In response to these inconveniences, we propose in this paper a new general POCL (Partial Order Causal Link) approach to represent and solve a temporal HTN problem by using existing heuristics developed to solve non temporal problems. We show experimentally that this approach is performant and can outperform the existing ones.

Alexandre Albore, Humbert Fiorino, Damien Pellier

Autonomous Unmanned Underwater Vehicles (UUVs) enable military and civilian covert operations in coastal areas without relying on support vessels or Global Navigation Satellite Systems (GNSS). Such operations are critical when surface access is not possible and stealthy navigation is required in restricted environments such as protected zones or dangerous areas under access ban. GNSS denied navigation is then essential to maintaining concealment as surfacing could expose UUVs to detection. To ensure a precise fleet positioning a constellation of beacons deployed by aerial or surface drones establish a synthetic landmark network that will guide the fleet of UUVs along an optimized path from the continental shelf to the goal on the shore. These beacons either submerged or floating emit acoustic signals for UUV localisation and navigation. A hierarchical planner generates an adaptive route for the drones executing primitive actions while continuously monitoring and replanning as needed to maintain trajectory accuracy.

Ying Siu Liang, Damien Pellier, Humbert Fiorino et al.

The great diversity of end-user tasks ranging from manufacturing environments to personal homes makes pre-programming robots for general purpose applications extremely challenging. In fact, teaching robots new actions from scratch that can be reused for previously unseen tasks remains a difficult challenge and is generally left up to robotics experts. In this work, we present iRoPro, an interactive Robot Programming framework that allows end-users with little to no technical background to teach a robot new reusable actions. We combine Programming by Demonstration and Automated Planning techniques to allow the user to construct the robot's knowledge base by teaching new actions by kinesthetic demonstration. The actions are generalised and reused with a task planner to solve previously unseen problems defined by the user. We implement iRoPro as an end-to-end system on a Baxter Research Robot to simultaneously teach low- and high-level actions by demonstration that the user can customise via a Graphical User Interface to adapt to their specific use case. To evaluate the feasibility of our approach, we first conducted pre-design experiments to better understand the user's adoption of involved concepts and the proposed robot programming process. We compare results with post-design experiments, where we conducted a user study to validate the usability of our approach with real end-users. Overall, we showed that users with different programming levels and educational backgrounds can easily learn and use iRoPro and its robot programming process.

Maxence Grand, Damien Pellier, Humbert Fiorino

Hand-encoding PDDL domains is generally accepted as difficult, tedious and error-prone. The difficulty is even greater when temporal domains have to be encoded. Indeed, actions have a duration and their effects are not instantaneous. In this paper, we present TempAMLSI, an algorithm based on the AMLSI approach able to learn temporal domains. TempAMLSI is based on the classical assumption done in temporal planning that it is possible to convert a non-temporal domain into a temporal domain. TempAMLSI is the first approach able to learn temporal domain with single hard envelope and Cushing's intervals. We show experimentally that TempAMLSI is able to learn accurate temporal domains, i.e., temporal domain that can be used directly to solve new planning problem, with different forms of action concurrency.

Ying Siu Liang, Damien Pellier, Humbert Fiorino et al.

Programming robots for general purpose applications is extremely challenging due to the great diversity of end-user tasks ranging from manufacturing environments to personal homes. Recent work has focused on enabling end-users to program robots using Programming by Demonstration. However, teaching robots new actions from scratch that can be reused for unseen tasks remains a difficult challenge and is generally left up to robotic experts. We propose iRoPro, an interactive Robot Programming framework that allows end-users to teach robots new actions from scratch and reuse them with a task planner. In this work we provide a system implementation on a two-armed Baxter robot that (i) allows simultaneous teaching of low- and high-level actions by demonstration, (ii) includes a user interface for action creation with condition inference and modification, and (iii) allows creating and solving previously unseen problems using a task planner for the robot to execute in real-time. We evaluate the generalisation power of the system on six benchmark tasks and show how taught actions can be easily reused for complex tasks. We further demonstrate its usability with a user study (N=21), where users completed eight tasks to teach the robot new actions that are reused with a task planner. The study demonstrates that users with any programming level and educational background can easily learn and use the system.

Damien Pellier, Humbert Fiorino

In this short paper, we outline nine classical benchmarks submitted to the first hierarchical planning track of the International Planning competition in 2020. All of these benchmarks are based on the HDDL language. The choice of the benchmarks was based on a questionnaire sent to the HTN community. They are the following: Barman, Childsnack, Rover, Satellite, Blocksworld, Depots, Gripper, and Hiking. In the rest of the paper we give a short description of these benchmarks. All are totally ordered.

Damien Pellier, Humbert Fiorino

In this paper, we outline the implementation of the TFD (Totally Ordered Fast Downward) and the PFD (Partially ordered Fast Downward) hierarchical planners that participated in the first HTN IPC competition in 2020. These two planners are based on forward-chaining task decomposition coupled with a compact grounding of actions, methods, tasks and HTN problems.

Maxence Grand, Humbert Fiorino, Damien Pellier

This paper presents new approach based on grammar induction called AMLSI Action Model Learning with State machine Interactions. The AMLSI approach does not require a training dataset of plan traces to work. AMLSI proceeds by trial and error: it queries the system to learn with randomly generated action sequences, and it observes the state transitions of the system, then AMLSI returns a PDDL domain corresponding to the system. A key issue for domain learning is the ability to plan with the learned domains. It often happens that a small learning error leads to a domain that is unusable for planning. Unlike other algorithms, we show that AMLSI is able to lift this lock by learning domains from partial and noisy observations with sufficient accuracy to allow planners to solve new problems.

Omar Mohammed, Gerard Bailly, Damien Pellier

How can we learn, transfer and extract handwriting styles using deep neural networks? This paper explores these questions using a deep conditioned autoencoder on the IRON-OFF handwriting data-set. We perform three experiments that systematically explore the quality of our style extraction procedure. First, We compare our model to handwriting benchmarks using multidimensional performance metrics. Second, we explore the quality of style transfer, i.e. how the model performs on new, unseen writers. In both experiments, we improve the metrics of state of the art methods by a large margin. Lastly, we analyze the latent space of our model, and we see that it separates consistently writing styles.

Abdeldjalil Ramoul, Damien Pellier, Humbert Fiorino et al.

Many planning techniques have been developed to allow autonomous systems to act and make decisions based on their perceptions of the environment. Among these techniques, HTN ({\it Hierarchical Task Network}) planning is one of the most used in practice. Unlike classical approaches of planning. HTN operates by decomposing task into sub-tasks until each of these sub-tasks can be achieved an action. This hierarchical representation provide a richer representation of planning problems and allows to better guide the plan search and provides more knowledge to the underlying algorithms. In this paper, we propose a new approach of HTN planning in which, as in conventional planning, we instantiate all planning operators before starting the search process. This approach has proven its effectiveness in classical planning and is necessary for the development of effective heuristics and encoding planning problems in other formalism such as CSP or SAT. The instantiation is actually used by most modern planners but has never been applied in an HTN based planning framework. We present in this article a generic instantiation algorithm which implements many simplification techniques to reduce the process complexity inspired from those used in classical planning. Finally we present some results obtained from an experimentation on a range of problems used in the international planning competitions with a modified version of SHOP planner using fully instantiated problems.

Damien Pellier, Carole Adam, Wafa Johal et al.

In this paper, we present CAIO, a Cognitive and Affective Interaction-Oriented architecture for social human-robot interactions (HRI), allowing robots to reason on mental states (including emotions), and to act physically, emotionally and verbally. We also present a short scenario and implementation on a Nao robot.

Ankuj Arora, Humbert Fiorino, Damien Pellier et al.

For social robots to be brought more into widespread use in the fields of companionship, care taking and domestic help, they must be capable of demonstrating social intelligence. In order to be acceptable, they must exhibit socio-communicative skills. Classic approaches to program HRI from observed human-human interactions fails to capture the subtlety of multimodal interactions as well as the key structural differences between robots and humans. The former arises due to a difficulty in quantifying and coding multimodal behaviours, while the latter due to a difference of the degrees of liberty between a robot and a human. However, the notion of reverse engineering from multimodal HRI traces to learn the underlying behavioral blueprint of the robot given multimodal traces seems an option worth exploring. With this spirit, the entire HRI can be seen as a sequence of exchanges of speech acts between the robot and human, each act treated as an action, bearing in mind that the entire sequence is goal-driven. Thus, this entire interaction can be treated as a sequence of actions propelling the interaction from its initial to goal state, also known as a plan in the domain of AI planning. In the same domain, this action sequence that stems from plan execution can be represented as a trace. AI techniques, such as machine learning, can be used to learn behavioral models (also known as symbolic action models in AI), intended to be reusable for AI planning, from the aforementioned multimodal traces. This article reviews recent machine learning techniques for learning planning action models which can be applied to the field of HRI with the intent of rendering robots as socio-communicative.

Damien Pellier, Mickaël Vanneufville, Humbert Fiorino et al.

Devising intelligent robots or agents that interact with humans is a major challenge for artificial intelligence. In such contexts, agents must constantly adapt their decisions according to human activities and modify their goals. In this paper, we tackle this problem by introducing a novel planning approach, called Moving Goal Planning (MGP), to adapt plans to goal evolutions. This planning algorithm draws inspiration from Moving Target Search (MTS) algorithms. In order to limit the number of search iterations and to improve its efficiency, MGP delays as much as possible triggering new searches when the goal changes over time. To this purpose, MGP uses two strategies: Open Check (OC) that checks if the new goal is still in the current search tree and Plan Follow (PF) that estimates whether executing actions of the current plan brings MGP closer to the new goal. Moreover, MGP uses a parsimonious strategy to update incrementally the search tree at each new search that reduces the number of calls to the heuristic function and speeds up the search. Finally, we show evaluation results that demonstrate the effectiveness of our approach.

Damien Pellier, Bruno Bouzy, Marc Métivier

In the context of real-time planning, this paper investigates the contributions of two enhancements for selecting actions. First, the agenda-driven planning enhancement ranks relevant atomic goals and solves them incrementally in a best-first manner. Second, the committed jump enhancement commits a sequence of actions to be executed at the following time steps. To assess these two enhancements, we developed a real-time planning algorithm in which action selection can be driven by a goal-agenda, and committed jumps can be done. Experimental results, performed on classical planning problems, show that agenda-planning and committed jumps are clear advantages in the real-time context. Used simultaneously, they enable the planner to be several orders of magnitude faster and solution plans to be shorter.

Damien Pellier, Bruno Bouzy, Marc Métivier

In this paper, we introduce a new heuristic search algorithm based on mean values for real-time planning, called MHSP. It consists in associating the principles of UCT, a bandit-based algorithm which gave very good results in computer games, and especially in Computer Go, with heuristic search in order to obtain a real-time planner in the context of classical planning. MHSP is evaluated on different planning problems and compared to existing algorithms performing on-line search and learning. Besides, our results highlight the capacity of MHSP to return plans in a real-time manner which tend to an optimal plan over the time which is faster and of better quality compared to existing algorithms in the literature.

Sandra Castellanos-Paez, Damien Pellier, Humbert Fiorino et al.

Planning has achieved significant progress in recent years. Among the various approaches to scale up plan synthesis, the use of macro-actions has been widely explored. As a first stage towards the development of a solution to learn on-line macro-actions, we propose an algorithm to identify useful macro-actions based on data mining techniques. The integration in the planning search of these learned macro-actions shows significant improvements over six classical planning benchmarks.

Ying Siu Liang, Damien Pellier, Humbert Fiorino et al.

The increasing presence of robots in industries has not gone unnoticed. Large industrial players have incorporated them into their production lines, but smaller companies hesitate due to high initial costs and the lack of programming expertise. In this work we introduce a framework that combines two disciplines, Programming by Demonstration and Automated Planning, to allow users without any programming knowledge to program a robot. The user teaches the robot atomic actions together with their semantic meaning and represents them in terms of preconditions and effects. Using these atomic actions the robot can generate action sequences autonomously to reach any goal given by the user. We evaluated the usability of our framework in terms of user experiments with a Baxter Research Robot and showed that it is well-adapted to users without any programming experience.

Damien Pellier, lias. Belaidi

In this paper, we introduce a generic and fresh model for distributed planning called "Distributed Planning Through Graph Merging" ({\sf DPGM}). This model unifies the different steps of the distributed planning process into a single step. Our approach is based on a planning graph structure for the agent reasoning and a CSP mechanism for the individual plan extraction and the coordination. We assume that no agent can reach the global goal alone. Therefore the agents must cooperate, {\it i.e.,} take in into account potential positive interactions between their activities to reach their common shared goal. The originality of our model consists in considering as soon as possible, {\it i.e.,} in the individual planning process, the positive and the negative interactions between agents activities in order to reduce the search cost of a global coordinated solution plan.

Damien Pellier, Humbert Fiorino

This paper introduces a multirobot cooperation approach to solve the "pursuit evasion" problem for mobile robots that have omnidirectional vision sensors. The main characteristic of this approach is to implement a real cooperation between robots based on knowledge sharing and makes them work as a team. A complete algorithm for computing a motion strategy of robots is also presented. This algorithm is based on searching critical points in the environment. Finally, the deliberation protocol which distributes the exploration task among the team and takes the best possible outcome from the robots resources is presented.

Damien Pellier, Humbert Fiorino

The purpose of the paper is to introduce a new approach of planning called Assumption-Based Planning. This approach is a very interesting way to devise a planner based on a multi-agent system in which the production of a global shared plan is obtained by conjecture/refutation cycles. Contrary to classical approaches, our contribution relies on the agents reasoning that leads to the production of a plan from planning domains. To take into account complex environments and the partial agents knowledge, we propose to consider the planning problem as a defeasible reasoning where the agents exchange proposals and counter-proposals and are able to reason about uncertainty. The argumentation dialogue between agents must not be viewed as a negotiation process but as an investigation process in order to build a plan. In this paper, we focus on the mechanisms that allow an agent to produce `reasonable' proposals according to its knowledge.

Bruno Bouzy, Marc Métivier, Damien Pellier

Playing repeated matrix games (RMG) while maximizing the cumulative returns is a basic method to evaluate multi-agent learning (MAL) algorithms. Previous work has shown that $UCB$, $M3$, $S$ or $Exp3$ algorithms have good behaviours on average in RMG. Besides, hedging algorithms have been shown to be effective on prediction problems. An hedging algorithm is made up with a top-level algorithm and a set of basic algorithms. To make its decision, an hedging algorithm uses its top-level algorithm to choose a basic algorithm, and the chosen algorithm makes the decision. This paper experimentally shows that well-selected hedging algorithms are better on average than all previous MAL algorithms on the task of playing RMG against various players. $S$ is a very good top-level algorithm, and $UCB$ and $M3$ are very good basic algorithms. Furthermore, two-level hedging algorithms are more effective than one-level hedging algorithms, and three levels are not better than two levels.

Ankuj Arora, Humbert Fiorino, Damien Pellier et al.

In the field of Automated Planning and Scheduling (APS), intelligent agents by virtue require an action model (blueprints of actions whose interleaved executions effectuates transitions of the system state) in order to plan and solve real world problems. It is, however, becoming increasingly cumbersome to codify this model, and is more efficient to learn it from observed plan execution sequences (training data). While the underlying objective is to subsequently plan from this learnt model, most approaches fall short as anything less than a flawless reconstruction of the underlying model renders it unusable in certain domains. This work presents a novel approach using long short-term memory (LSTM) techniques for the acquisition of the underlying action model. We use the sequence labelling capabilities of LSTMs to isolate from an exhaustive model set a model identical to the one responsible for producing the training data. This isolation capability renders our approach as an effective one.

Omar Mohammed, Gerard Bailly, Damien Pellier

Evaluating the style of handwriting generation is a challenging problem, since it is not well defined. It is a key component in order to develop in developing systems with more personalized experiences with humans. In this paper, we propose baseline benchmarks, in order to set anchors to estimate the relative quality of different handwriting style methods. This will be done using deep learning techniques, which have shown remarkable results in different machine learning tasks, learning classification, regression, and most relevant to our work, generating temporal sequences. We discuss the challenges associated with evaluating our methods, which is related to evaluation of generative models in general. We then propose evaluation metrics, which we find relevant to this problem, and we discuss how we evaluate the evaluation metrics. In this study, we use IRON-OFF dataset. To the best of our knowledge, there is no work done before in generating handwriting (either in terms of methodology or the performance metrics), our in exploring styles using this dataset.

Sandra Castellanos-Paez, Damien Pellier, Humbert Fiorino et al.

Planning has achieved significant progress in recent years. Among the various approaches to scale up plan synthesis, the use of macro-actions has been widely explored. As a first stage towards the development of a solution to learn on-line macro-actions, we propose an algorithm to identify useful macro-actions based on data mining techniques. The integration in the planning search of these learned macro-actions shows significant improvements over four classical planning benchmarks.