Malik Ghallab
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Malik Ghallab has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Paolo Traverso
Fondazione Bruno Kessler
6 shared publications - Dana Nau
University of Maryland, College Park, MD, USA
4 shared publications Dana Nau
2 shared publicationsSunandita Patra
2 shared publications- Alejandro Estaña
LAAS-CNRS, Université de Toulouse, CNRS, 31400 Toulouse, France
1 shared publication - Amit Kumar
University of Maryland 20742 College Park MD USA
1 shared publication
Latest Publications
- Open Access
Acting and Planning with Hierarchical Operational Models on a Mobile Robot: A Study with RAE+UPOM
Robotic task execution faces challenges due to the inconsistency between symbolic planner models and the rich control structures actually running on the robot. In this paper, we present the first physical deployment of an integrated actor-planner system that shares hierarchical operational models for both acting and planning, interleaving the Reactive Acting Engine (RAE) with an anytime UCT-like Monte Carlo planner (UPOM). We implement RAE+UPOM on a mobile manipulator in a real-world deployment for an object collection task. Our experiments demonstrate robust task execution under action failures and sensor noise, and provide empirical insights into the interleaved acting-and-planning decision making process.
Open AccessActing and Planning with Hierarchical Operational Models on a Mobile Robot: A Study with RAE+UPOM
Robotic task execution faces challenges due to the inconsistency between symbolic planner models and the rich control structures actually running on the robot. In this paper, we present the first physical deployment of an integrated actor-planner system that shares hierarchical operational models for both acting and planning, interleaving the Reactive Acting Engine (RAE) with an anytime UCT-like Monte Carlo planner (UPOM). We implement RAE+UPOM on a mobile manipulator in a real-world deployment for an object collection task. Our experiments demonstrate robust task execution under action failures and sensor noise, and provide empirical insights into the interleaved acting-and-planning decision making process.
- Open Access
Deliberative Acting, Online Planning and Learning with Hierarchical Operational Models
In AI research, synthesizing a plan of action has typically used descriptive models of the actions that abstractly specify what might happen as a result of an action, and are tailored for efficiently computing state transitions. However, executing the planned actions has needed operational models, in which rich computational control structures and closed-loop online decision-making are used to specify how to perform an action in a nondeterministic execution context, react to events and adapt to an unfolding situation. Deliberative actors, which integrate acting and planning, have typically needed to use both of these models together -- which causes problems when attempting to develop the different models, verify their consistency, and smoothly interleave acting and planning. As an alternative, we define and implement an integrated acting and planning system in which both planning and acting use the same operational models. These rely on hierarchical task-oriented refinement methods offering rich control structures. The acting component, called Reactive Acting Engine (RAE), is inspired by the well-known PRS system. At each decision step, RAE can get advice from a planner for a near-optimal choice with respect to a utility function. The anytime planner uses a UCT-like Monte Carlo Tree Search procedure, called UPOM, whose rollouts are simulations of the actor's operational models. We also present learning strategies for use with RAE and UPOM that acquire, from online acting experiences and/or simulated planning results, a mapping from decision contexts to method instances as well as a heuristic function to guide UPOM. We demonstrate the asymptotic convergence of UPOM towards optimal methods in static domains, and show experimentally that UPOM and the learning strategies significantly improve the acting efficiency and robustness.
Open AccessDeliberative Acting, Online Planning and Learning with Hierarchical Operational Models
In AI research, synthesizing a plan of action has typically used descriptive models of the actions that abstractly specify what might happen as a result of an action, and are tailored for efficiently computing state transitions. However, executing the planned actions has needed operational models, in which rich computational control structures and closed-loop online decision-making are used to specify how to perform an action in a nondeterministic execution context, react to events and adapt to an unfolding situation. Deliberative actors, which integrate acting and planning, have typically needed to use both of these models together -- which causes problems when attempting to develop the different models, verify their consistency, and smoothly interleave acting and planning. As an alternative, we define and implement an integrated acting and planning system in which both planning and acting use the same operational models. These rely on hierarchical task-oriented refinement methods offering rich control structures. The acting component, called Reactive Acting Engine (RAE), is inspired by the well-known PRS system. At each decision step, RAE can get advice from a planner for a near-optimal choice with respect to a utility function. The anytime planner uses a UCT-like Monte Carlo Tree Search procedure, called UPOM, whose rollouts are simulations of the actor's operational models. We also present learning strategies for use with RAE and UPOM that acquire, from online acting experiences and/or simulated planning results, a mapping from decision contexts to method instances as well as a heuristic function to guide UPOM. We demonstrate the asymptotic convergence of UPOM towards optimal methods in static domains, and show experimentally that UPOM and the learning strategies significantly improve the acting efficiency and robustness.
- 1 October 2021
- Published by Elsevier in Artificial Intelligence
- Vol. 299, 103523
Deliberative acting, planning and learning with hierarchical operational models
- 1 October 2021
- Published by Elsevier in Artificial Intelligence
- Vol. 299, 103523
Deliberative acting, planning and learning with hierarchical operational models
- Open Access
Integrating Acting, Planning and Learning in Hierarchical Operational Models
We present new planning and learning algorithms for RAE, the Refinement Acting Engine. RAE uses hierarchical operational models to perform tasks in dynamically changing environments. Our planning procedure, UPOM, does a UCT-like search in the space of operational models in order to find a near-optimal method to use for the task and context at hand. Our learning strategies acquire, from online acting experiences and/or simulated planning results, a mapping from decision contexts to method instances as well as a heuristic function to guide UPOM. Our experimental results show that UPOM and our learning strategies significantly improve RAE's performance in four test domains using two different metrics: efficiency and success ratio.
Open AccessIntegrating Acting, Planning and Learning in Hierarchical Operational Models
We present new planning and learning algorithms for RAE, the Refinement Acting Engine. RAE uses hierarchical operational models to perform tasks in dynamically changing environments. Our planning procedure, UPOM, does a UCT-like search in the space of operational models in order to find a near-optimal method to use for the task and context at hand. Our learning strategies acquire, from online acting experiences and/or simulated planning results, a mapping from decision contexts to method instances as well as a heuristic function to guide UPOM. Our experimental results show that UPOM and our learning strategies significantly improve RAE's performance in four test domains using two different metrics: efficiency and success ratio.
- Open Access
- 3 September 2019
- Published by Springer Nature in AI Perspectives
- Vol. 1 (1) , 1-7
Responsible AI: requirements and challenges
- 3 September 2019
- Published by Springer Nature in AI Perspectives
- Vol. 1 (1) , 1-7
Open AccessResponsible AI: requirements and challenges
- Open Access
Investigating the Formation of Structural Elements in Proteins Using Local Sequence-Dependent Information and a Heuristic Search Algorithm
Structural elements inserted in proteins are essential to define folding/unfolding mechanisms and partner recognition events governing signaling processes in living organisms. Here, we present an original approach to model the folding mechanism of these structural elements. Our approach is based on the exploitation of local, sequence-dependent structural information encoded in a database of three-residue fragments extracted from a large set of high-resolution experimentally determined protein structures. The computation of conformational transitions leading to the formation of the structural elements is formulated as a discrete path search problem using this database. To solve this problem, we propose a heuristically-guided depth-first search algorithm. The domain-dependent heuristic function aims at minimizing the length of the path in terms of angular distances, while maximizing the local density of the intermediate states, which is related to their probability of existence. We have applied the strategy to two small synthetic polypeptides mimicking two common structural motifs in proteins. The folding mechanisms extracted are very similar to those obtained when using traditional, computationally expensive approaches. These results show that the proposed approach, thanks to its simplicity and computational efficiency, is a promising research direction.
Open AccessInvestigating the Formation of Structural Elements in Proteins Using Local Sequence-Dependent Information and a Heuristic Search Algorithm
Structural elements inserted in proteins are essential to define folding/unfolding mechanisms and partner recognition events governing signaling processes in living organisms. Here, we present an original approach to model the folding mechanism of these structural elements. Our approach is based on the exploitation of local, sequence-dependent structural information encoded in a database of three-residue fragments extracted from a large set of high-resolution experimentally determined protein structures. The computation of conformational transitions leading to the formation of the structural elements is formulated as a discrete path search problem using this database. To solve this problem, we propose a heuristically-guided depth-first search algorithm. The domain-dependent heuristic function aims at minimizing the length of the path in terms of angular distances, while maximizing the local density of the intermediate states, which is related to their probability of existence. We have applied the strategy to two small synthetic polypeptides mimicking two common structural motifs in proteins. The folding mechanisms extracted are very similar to those obtained when using traditional, computationally expensive approaches. These results show that the proposed approach, thanks to its simplicity and computational efficiency, is a promising research direction.
- Top Cited Papers
- 1 March 2014
- Published by Elsevier in Artificial Intelligence
- Vol. 208, 1-17
The actorʼs view of automated planning and acting: A position paper
- 1 March 2014
- Published by Elsevier in Artificial Intelligence
- Vol. 208, 1-17
Top Cited PapersThe actorʼs view of automated planning and acting: A position paper
- 8 October 2010
- Published by Springer Nature in Autonomous Robots
- Vol. 30 (2) , 157-177
Learning the behavior model of a robot
- 8 October 2010
- Published by Springer Nature in Autonomous Robots
- Vol. 30 (2) , 157-177
Learning the behavior model of a robot
- Open Access
- 1 January 2010
- Published by AEPress, s.r.o. in General Physiology and Biophysics
- Vol. 29 (1) , 85-94
Prophylactic role of curcumin against cyclosporine-induced nephrotoxicity: Histological and immunohistological study
Prophylactic role of curcumin against cyclosporine-induced nephrotoxicity: Histological and immunohistological study
- 1 January 2010
- Published by AEPress, s.r.o. in General Physiology and Biophysics
- Vol. 29 (1) , 85-94
Open AccessProphylactic role of curcumin against cyclosporine-induced nephrotoxicity: Histological and immunohistological study
Prophylactic role of curcumin against cyclosporine-induced nephrotoxicity: Histological and immunohistological study