Froduald Kabanza

AIIM Journal 2016 Journal Article

Evaluation of a machine learning capability for a clinical decision support system to enhance antimicrobial stewardship programs

• Mathieu Beaudoin
• Froduald Kabanza
• Vincent Nault
• Louis Valiquette

Objective Antimicrobial stewardship programs have been shown to limit the inappropriate use of antimicrobials. Hospitals are increasingly relying on clinical decision support systems to assist in the demanding prescription reviewing process. In previous work, we have reported on an emerging clinical decision support system for antimicrobial stewardship that can learn new rules supervised by user feedback. In this paper, we report on the evaluation of this system. Methods The evaluated system uses a knowledge base coupled with a supervised learning module that extracts classification rules for inappropriate antimicrobial prescriptions using past recommendations for dose and dosing frequency adjustments, discontinuation of therapy, early switch from intravenous to oral therapy, and redundant antimicrobial spectrum. Over five weeks, the learning module was deployed alongside the baseline system to prospectively evaluate its ability to discover rules that complement the existing knowledge base for identifying inappropriate prescriptions of piperacillin–tazobactam, a frequently used antimicrobial. Results The antimicrobial stewardship pharmacists reviewed 374 prescriptions, of which 209 (56% of 374) were identified as inappropriate leading to 43 recommendations to optimize prescriptions. The baseline system combined with the learning module triggered alerts in 270 prescriptions with a positive predictive value of identifying inappropriate prescriptions of 74%. Of these, 240 reviewed prescriptions were identified by the alerts of the baseline system with a positive predictive value of 82% and 105 reviewed prescriptions were identified by the alerts of the learning module with a positive predictive value of 62%. The combined system triggered alerts for all 43 recommendations, resulting in a rate of actionable alerts of 16% (43 recommendations of 270 reviewed alerts); the baseline system triggered alerts for 38 interventions, resulting in a rate of actionable alerts of 16% (38 of 240 reviewed alerts); and the learning module triggered alerts for 17 interventions, resulting in a rate of actionable alerts of 16% (17 of 105 reviewed alerts). The learning module triggered alerts for every inappropriate prescription missed by the knowledge base of the baseline system (n =5). Conclusions The learning module was able to extract clinically relevant rules for multiple types of antimicrobial alerts. The learned rules were shown to extend the knowledge base of the baseline system by identifying pharmacist interventions that were missed by the baseline system. The learned rules identified inappropriate prescribing practices that were not supported by local experts and were missing from its knowledge base. However, combining the baseline system and the learning module increased the number of false positives.

IJCAI Conference 2015 Conference Paper

Using a Recursive Neural Network to Learn an Agent's Decision Model for Plan Recognition

• Francis Bisson
• Hugo Larochelle
• Froduald Kabanza

Plan recognition, the problem of inferring the goals or plans of an observed agent, is a key element of situation awareness in human-machine and machine-machine interactions for many applications. Some plan recognition algorithms require knowledge about the potential behaviours of the observed agent in the form of a plan library, together with a decision model about how the observed agent uses the plan library to make decisions. It is however difficult to elicit and specify the decision model a priori. In this paper, we present a recursive neural network model that learns such a decision model automatically. We discuss promising experimental results of the approach with comparisons to selected state-of-the-art plan recognition algorithms on three benchmark domains.

IJCAI Conference 2013 Conference Paper

Controlling the Hypothesis Space in Probabilistic Plan Recognition

• Froduald Kabanza
• Julien Filion
• Abder Rezak Benaskeur
• Hengameh Irandoust

The ability to understand the goals and plans of other agents is an important characteristic of intelligent behaviours in many contexts. One of the approaches used to endow agents with this capability is the weighted model counting approach. Given a plan library and a sequence of observations, this approach exhaustively enumerates plan execution models that are consistent with the observed behaviour. The probability that the agent might be pursuing a particular goal is then computed as a proportion of plan execution models satisfying the goal. The approach allows to recognize multiple interleaved plans, but suffers from a combinatorial explosion of plan execution models, which impedes its application to real-world domains. This paper presents a heuristic weighted model counting algorithm that limits the number of generated plan execution models in order to recognize goals quickly by computing their lower and upper bound likelihoods.

AAAI Conference 2011 Conference Paper

Heuristic Planning in Adversarial Dynamic Domains

• Simon Chamberland
• Froduald Kabanza

AAAI Conference 2011 Conference Paper

Provoking Opponents to Facilitate the Recognition of their Intentions

• Francis Bisson
• Froduald Kabanza
• Abder Rezak Benaskeur
• Hengameh Irandoust

TIST Journal 2010 Journal Article

CORALS

• Abder Rezak Benaskeur
• Froduald Kabanza
• Eric Beaudry

Forces involved in modern conflicts may be exposed to a variety of threats, including coordinated raids of advanced ballistic and cruise missiles. To respond to these, a defending force will rely on a set of combat resources. Determining an efficient allocation and coordinated use of these resources, particularly in the case of multiple simultaneous attacks, is a very complex decision-making process in which a huge amount of data must be dealt with under uncertainty and time pressure. This article presents CORALS (COmbat Resource ALlocation Support), a real-time planner developed to support the command team of a naval force defending against multiple simultaneous threats. In response to such multiple threats, CORALS uses a local planner to generate a set of local plans, one for each threat considered apart, and then combines and coordinates them into a single optimized, conflict-free global plan. The coordination is performed through an iterative process of plan merging and conflict detection and resolution, which acts as a plan repair mechanism. Such an incremental plan repair approach also allows adapting previously generated plans to account for dynamic changes in the tactical situation.

IROS Conference 2010 Conference Paper

Motion planning for an omnidirectional robot with steering constraints

• Simon Chamberland
• Eric Beaudry
• Lionel Clavien
• Froduald Kabanza
• François Michaud
• Michel Lauria

Omnidirectional mobile robots, i. e. , robots that can move in any direction without changing their orientation, offer better manoeuvrability in natural environments. Modeling the kinematics of such robots is a challenging problem and different approaches have been investigated. One of the best approaches for a nonholonomic robot is to model the robot's velocity state as the motion around its instantaneous center of rotation (ICR). In this paper, we present a motion planner designed to compute efficient trajectories for such a robot in an environment with obstacles. The action space is modeled in terms of changes of the ICR and the motion around it. Our motion planner is based on a Rapidly-Exploring Random Trees (RRT) algorithm to sample the action space and find a feasible trajectory from an initial configuration to a goal configuration. To generate fluid paths, we introduce an adaptive sampling technique taking into account constraints related to the ICR-based action space.

ICAPS Conference 2010 Conference Paper

Planning for Concurrent Action Executions Under Action Duration Uncertainty Using Dynamically Generated Bayesian Networks

• Eric Beaudry
• Froduald Kabanza
• François Michaud

An interesting class of planning domains, including planning for daily activities of Mars rovers, involves achievement of goals with time constraints and concurrent actions with probabilistic durations. Current probabilistic approaches, which rely on a discrete time model, introduce a blow up in the search state-space when the two factors of action concurrency and action duration uncertainty are combined. Simulation-based and sampling probabilistic planning approaches would cope with this state explosion by avoiding storing all the explored states in memory, but they remain approximate solution approaches. In this paper, we present an alternative approach relying on a continuous time model which avoids the state explosion caused by time stamping in the presence of action concurrency and action duration uncertainty. Time is represented as a continuous random variable. The dependency between state time variables is conveyed by a Bayesian network, which is dynamically generated by a state-based forward-chaining search based on the action descriptions. A generated plan is characterized by a probability of satisfying a goal. The evaluation of this probability is done by making a query the Bayesian network.

ECAI Conference 2010 Conference Paper

Planning with Concurrency under Resources and Time Uncertainty

• Eric Beaudry
• Froduald Kabanza
• François Michaud

Planning with actions concurrency under resources and time uncertainty has been recognized as a challenging and interesting problem. Most current approaches rely on a discrete model to represent resources and time, which contributes to the combinatorial explosion of the search space when dealing with both actions concurrency and resources and time uncertainty. A recent alternative approach uses continuous random variables to represent the uncertainty on time, thus avoiding the state-space explosion caused by the discretization of timestamps. We generalize this approach to consider uncertainty on both resources and time. Our planner is based on a forward chaining search in a state-space where the state representation is characterized by a set of object and numeric state variables. Object state variables are associated with random variables tracking the time at which the state variables' current value has been assigned. The search algorithm dynamically generates a Bayesian network that models the dependency between time and numeric random variables. The planning algorithm queries the Bayesian network to estimate the probability that the resources (numerical state variables) remain in a valid state, the probability of success and the expected cost of the generated plans. Experiments were performed on a transport domain in which we introduced uncertainty on the duration of actions and on the fuel consumption of trucks.

ICAPS Conference 2008 Conference Paper

A Probabilistic Planner for the Combat Power Management Problem

• Abder Rezak Benaskeur
• Froduald Kabanza
• Eric Beaudry
• Mathieu Beaudoin

We present a planner for the Combat Power Management (CPM) problem. In response to multiple simultaneous or sequential threats, the planner generates a set of local plans, one for each target considered apart, and then merges them by searching the space of global plans. The proposed plan merging solution serves also as an iterative plan repair process that resolves negative interferences (subaddivity) and exploits synergistic effects (superaddivity) among activities. The planner was developed as a component of a naval Command and Control system to support the warship command team in defending against Anti-Ship Missile threats. The planner is particularly suited for domains characterized by durative concurrent actions, with both superadditive and subadditive interactions, and probabilistic effects. It is implemented in a generic way, allowing it to address other application domains. We discuss the CPM application domain, describe the planner, and present experimental results.

ECAI Conference 2008 Conference Paper

Automatic Animation Generation of a Teleoperated Robot Arm

• Khaled Belghith
• Benjamin Auder
• Froduald Kabanza
• Philipe Bellefeuille
• Leo Hartman

In this paper we describe the Automatic Task Demonstration Generator (ATDG), a system implemented into a software prototype for teaching the operation of a robot manipulator deployed on the International Space Station (ISS). The ATDG combines the use of path planning and camera planning to take into account the complexity of the manipulator, the limited direct view of the ISS exterior, and the unpredictability of lighting conditions in the workspace. The path-planning algorithm not only avoids obstacles in the workspace as is normal for a path-planner, but in addition takes into account the position of corridors for safe operations and the placement of cameras on the ISS. The camera planner is then invoked to find the right arrangement of cameras to follow the manipulator on its trajectory. This allows the on-the-fly production of useful and pedagogical task demonstrations to help the student carry out tasks involving the manipulation of the robot on the ISS. Even if the system has been developed for robotic manipulations, it could be used for any application involving the filming of unpredictable complex scenes.

ICAPS Conference 2008 Conference Paper

Planning 3D Task Demonstrations of a Teleoperated Space Robot Arm

• Froduald Kabanza
• Khaled Belghith
• Philipe Bellefeuille
• Benjamin Auder
• Leo Hartman

We present an automated planning application for generating 3D tasks demonstrations involving a teleoperated robot arm on the the International Space Station (ISS). A typical task demonstration involves moving the robot arm from one configuration to another. Our objective is to automatically plan the position of virtual cameras to film the arm in a manner that conveys the best awareness of the robot trajectory to the user. Given a new task, or given changes to a task previously planned, our system automatically and efficiently generates 3D demonstrations of the task without the intervention of a computer graphics programmer. For a given task, the robot trajectory is generated using a path planner. Then we consider the filming of the trajectory as a sequence of shots satisfying some temporally extended goal conveying constraints on the desirable positioning of virtual cameras. Then a temporal-logic based planning system (TLPlan) is used to generate a 3D movie satisfying the goal. One motivation for this application is to eventually use it to support ground operators in planning mission tasks for the ISS. Another motivation is to eventually use automatically generated demonstrations in a 3D training simulator to provide feedback to student astronauts learning to manipulate the robot arm. Although motivated by the ISS application, the key ideas underlying our system are potentially useful for automatically filming other kinds of complex animated scenes.

IROS Conference 2008 Conference Paper

Reactive planning as a motivational source in a behavior-based architecture

• Eric Beaudry
• Dominic Létourneau
• Froduald Kabanza
• François Michaud

Behavior-based architectures use behaviors as building blocks for decision-making and action execution processes. Behaviors are distributed and evaluated in parallel for the control of the robot, taking real-time inputs from sensory data and sending real-time commands to effectors. No centralized components exist in these architectures, each module carrying out its own strategy independently, making an overall behavior emerge from the interaction between the concurrently executed modules and the environment. In this paper, we discuss the use of a reactive hierarchical task network (HTN) planner in a behavior-based robot architecture. The planner in this architecture is not a central component on which everything else relies on, but acts as one of the motivational modules recommending tasks to be executed and influencing the selection and configuration of behaviors. The planning module allows the behavior-based architecture to deal with tasks with priorities, flexible time constraints and on-line planning using a simple but very effective reactive planning strategy. We demonstrate our approach in the context of making a robot attend a conference.

ICRA Conference 2006 Conference Paper

Anytime Dynamic Path-planning with Flexible Probabilistic Roadmaps

• Khaled Belghith
• Froduald Kabanza
• Leo Hartman
• Roger Nkambou

Probabilistic roadmaps (PRM) have been demonstrated to be very promising for planning paths for robots with high degrees of freedom in complex 3D workspaces. In this paper we describe a PRM path-planning method presenting three novel features that are useful in various real-world applications. First, it handles zones in the robot workspace with different degrees of desirability. Given the random quality of paths that are calculated by traditional PRM approaches, this provides a mean to specify a sampling strategy that controls the search process to generate better paths by simply annotating regions in the free workspace with degrees of desirability. Second, our approach can efficiently re-compute paths in dynamic environments where obstacles and zones can change shape or move concurrently with the robot. Third, it can incrementally improve the quality of a generated path, so that a suboptimal solution is available when required for immediate action, but get improved as more planning time is affordable

AIIM Journal 2006 Journal Article

Implementing tutoring strategies into a patient simulator for clinical reasoning learning

• Froduald Kabanza
• Guy Bisson
• Annabelle Charneau
• Taek-Sueng Jang

Objective This paper describes an approach for developing intelligent tutoring systems (ITS) for teaching clinical reasoning. Materials and methods Our approach to ITS for clinical reasoning uses a novel hybrid knowledge representation for the pedagogic model, combining finite state machines to model different phases in the diagnostic process, production rules to model triggering conditions for feedback in different phases, temporal logic to express triggering conditions based upon past states of the student's problem solving trace, and finite state machines to model feedback dialogues between the student and TeachMed. The expert model is represented by an influence diagram capturing the relationship between evidence and hypotheses related to a clinical case. Results This approach is implemented into TeachMed, a patient simulator we are developing to support clinical reasoning learning for a problem-based learning medical curriculum at our institution; we demonstrate some scenarios of tutoring feedback generated using this approach. Conclusion Each of the knowledge representation formalisms that we use has already been proven successful in different applications of artificial intelligence and software engineering, but their integration into a coherent pedagogic model as we propose is unique. The examples we discuss illustrate the effectiveness of this approach, making it promising for the development of complex ITS, not only for clinical reasoning learning, but potentially for other domains as well.

IJCAI Conference 2005 Conference Paper

Path-Planning for Autonomous Training on Robot Manipulators in Space

• Froduald Kabanza
• Roger Nkambou
• Khaled

This paper describes the integration of robot path-planning and spatial task modeling into a software system that teaches the operation of a robot manipulator deployed on International Space Station (ISS). The system addresses the complexity of the manipulator, the limited direct view of the ISS exterior and the unpredictability of lighting conditions in the workspace. Robot path planning is used not for controlling the manipulator, but for automatically checking errors of a student learning to operate the manipulator and for automatically producing illustrations of good and bad motions in training.

ICAPS Conference 2005 Conference Paper

Search Control in Planning for Temporally Extended Goals

• Froduald Kabanza
• Sylvie Thiébaux

Current techniques for reasoning about search control knowledge in AI planning, such as those used in TLPlan, TALPlanner, or SHOP2, assume that search control knowledge is conditioned upon and interpreted with respect to a fixed set of goal states. Therefore, these techniques can deal with reachability goals but do not apply to temporally extended goals, such as goals of achieving a condition whenever a certain fact becomes true. Temporally extended goals convey several intermediate reachability goals to be achieved at different point of execution, sometimes with cyclic executions; that is, the notion of goal state becomes dynamic. In this paper, we describe a method for reasoning about search control knowledge in the presence of temporally extended goals. Given such a goal, we generate an equivalent Buchi automaton---an automaton recognising the language of the executions satisfying the goal---and interpret control knowledge over this automaton and the world state trajectories generated by a forward search planner. This method is implemented and experimented with as an extension of the TLPlan planner, which incidentally becomes capable of handling cyclic goals.

UAI Conference 2002 Conference Paper

Anytime State-Based Solution Methods for Decision Processes with non-Markovian Rewards

• Sylvie Thiébaux
• Froduald Kabanza
• John K. Slaney

A popular approach to solving a decision process with non-Markovian rewards (NMRDP) is to exploit a compact representation of the reward function to automatically translate the NMRDP into an equivalent Markov decision process (MDP) amenable to our favorite MDP solution method. The contribution of this paper is a representation of non-Markovian reward functions and a translation into MDP aimed at making the best possible use of state-based anytime algorithms as the solution method. By explicitly constructing and exploring only parts of the state space, these algorithms are able to trade computation time for policy quality, and have proven quite effective in dealing with large MDPs. Our representation extends future linear temporal logic (FLTL) to express rewards. Our translation has the effect of embedding model-checking in the solution method. It results in an MDP of the minimal size achievable without stepping outside the anytime framework, and consequently in better policies by the deadline.

AIJ Journal 2000 Journal Article

Using temporal logics to express search control knowledge for planning

• Fahiem Bacchus
• Froduald Kabanza

Over the years increasingly sophisticated planning algorithms have been developed. These have made for more efficient planners, but unfortunately these planners still suffer from combinatorial complexity even in simple domains. Theoretical results demonstrate that planning is in the worst case intractable. Nevertheless, planning in particular domains can often be made tractable by utilizing additional domain structure. In fact, it has long been acknowledged that domain-independent planners need domain-dependent information to help them plan effectively. In this work we present an approach for representing and utilizing domain-specific control knowledge. In particular, we show how domain-dependent search control knowledge can be represented in a temporal logic, and then utilized to effectively control a forward-chaining planner. There are a number of advantages to our approach, including a declarative semantics for the search control knowledge; a high degree of modularity (new search control knowledge can be added without affecting previous control knowledge); and an independence of this knowledge from the details of the planning algorithm. We have implemented our ideas in the TLplan system, and have been able to demonstrate its remarkable effectiveness in a wide range of planning domains.