Search

Aplicat embargament des de la data de defensa fins el dia 31/12/2019, Premi Extraordinari de Doctorat, promoció 2018-2019. Àmbit d’Enginyeria Industrial, This thesis addresses the combination of task and motion planning which deals with different types of robotic manipulation problems. Manipulation problems are referred to as mobile manipulation, collaborative multiple mobile robots tasks, and even higher dimensional tasks (like bi-manual robots or mobile manipulators). Task and motion planning problems needs to obtain a geometrically feasible manipulation plan through symbolic and geometric search space. The combination of task and motion planning levels has emerged as a challenging issue as the failure leads robots to dead-end tasks due to geometric constraints. In addition, task planning is combined with physics-based motion planning and information to cope with manipulation tasks in which interactions between robots and objects are required, or also a low-cost feasible plan in terms of power is looked for. Moreover, combining task and motion planning frameworks is enriched by introducing manipulation knowledge. It facilitates the planning process and aids to provide the way of executing symbolic actions. Combining task and motion planning can be considered under uncertain information and with human-interaction. Uncertainty can be viewed in the initial state of the robot world or the result of symbolic actions. To deal with such issues, contingent-based task and motion planning is proposed using a perception system and human knowledge. Also, robots can ask human for those tasks which are difficult or infeasible for the purpose of collaboration. An implementation framework to combine different types of task and motion planning is presented. All the required modules and tools are also illustrated. As some task planning algorithms are implemented in Prolog or C++ languages and our geometric reasoner is developed in C++, the flow of information between different languages is explained., Aquesta tesis es centra en les eines de planificació combinada a nivell de tasca i a nivell de moviments per abordar diferents problemes de manipulació robòtica. Els problemes considerats són de navegació de robots mòbil enmig de obstacles no fixes, tasques de manipulació cooperativa entre varis robots mòbils, i tasques de manipulació de dimensió més elevada com les portades a terme amb robots bi-braç o manipuladors mòbils. La planificació combinada de tasques i de moviments ha de cercar un pla de manipulació que sigui geomètricament realitzable, a través de d'un espai de cerca simbòlic i geomètric. La combinació dels nivells de planificació de tasca i de moviments ha sorgit com un repte ja que les fallades degudes a les restriccions geomètriques poden portar a tasques sense solució. Addicionalment, la planificació a nivell de tasca es combina amb informació de la física de l'entorn i amb mètodes de planificació basats en la física, per abordar tasques de manipulació en les que la interacció entre el robot i els objectes és necessària, o també si es busca un pla realitzable i amb un baix cost en termes de potència. A més, el marc proposat per al combinació de la planificació a nivell de tasca i a nivell de moviments es millora mitjançant l'ús de coneixement, que facilita el procés de planificació i ajuda a trobar la forma d'executar accions simbòliques. La combinació de nivells de planificació també es pot considerar en casos d'informació incompleta i en la interacció humà-robot. La incertesa es considera en l'estat inicial i en el resultat de les accions simbòliques. Per abordar aquest problema, es proposa la planificació basada en contingències usant un sistema de percepció i el coneixement de l'operari humà. Igualment, els robots poden demanar col·laboració a l'operari humà per a que realitzi aquelles accions que són difícils o no realitzables pel robot. Es presenta també un marc d'implementació per a la combinació de nivells de planificació usant diferents mètod, Award-winning, Postprint (published version)

One of the problems that service robotics deals with is to bring mobile manipulators to work in semi-structured human scenarios, which requires an efficient and flexible way to execute every-day tasks, like serve a cup in a cluttered environment. Usually, for those tasks, the combination of symbolic and geometric levels of planning is necessary, as well as the integration of perception models with knowledge to guide both planning levels, resulting in a sequence of actions or skills which, according to the current knowledge of the world, may be executed. This paper proposes a planning and execution framework, called SkillMaN, for robotic manipulation tasks, which is equipped with a module with experiential knowledge (learned from its experience or given by the user) on how to execute a set of skills, like pick-up, put-down or open a drawer, using workflows as well as robot trajectories. The framework also contains an execution assistant with geometric tools and reasoning capabilities to manage how to actually execute the sequence of motions to perform a manipulation task (which are forwarded to the executor module), as well as the capacity to store the relevant information to the experiential knowledge for further usage, and the capacity to interpret the actual perceived situation (in case the preconditions of an action do not hold) and to feed back the updated state to the planner to resume from there, allowing the robot to adapt to non-expected situations. To evaluate the viability of the proposed framework, an experiment has been proposed involving different skills performed with various types of objects in different scene contexts, Peer Reviewed, Preprint

Manipulation planning under incomplete information is a highly challenging task for mobile manipulators. Uncertainty can be resolved by robot perception modules or using human knowledge in the execution process. Human operators can also collaborate with robots for the execution of some difficult actions or as helpers in sharing the task knowledge. In this scope, a contingent-based task and motion planning is proposed taking into account robot uncertainty and human–robot interactions, resulting a tree-shaped set of geometrically feasible plans. Different sorts of geometric reasoning processes are embedded inside the planner to cope with task constraints like detecting occluding objects when a robot needs to grasp an object. The proposal has been evaluated with different challenging scenarios in simulation and a real environment., Postprint (published version)

This is a post-peer-review, pre-copyedit version of an article published in ROBOT - Iberian Robotics Conference. The final authenticated version is available online at: http://dx.doi.org/10.1007/978-3-030-35990-4_31”., Autonomous indoor robots are supposed to accomplish tasks, like serve a cup, which involve manipulation actions, where task and motion planning levels are coupled. In both planning levels and execution phase, several source of failures can occur. In this paper, an interpretation ontology covering several sources of failures in automated planning and also during the execution phases is introduced with the purpose of working the planning more informed and the execution prepared for recovery. The proposed failure interpretation ontological module covers: (1) geometric failures, that may appear when e.g. the robot can not reach to grasp/place an object, there is no free-collision path or there is no feasible Inverse Kinematic (IK) solution. (2) hardware related failures that may appear when e.g. the robot in a real environment requires to be re-calibrated (gripper or arm), or it is sent to a non-reachable configuration. (3) software agent related failures, that may appear when e.g. the robot has software components that fail like when an algorithm is not able to extract the proper features. The paper describes the concepts and the implementation of failure interpretation ontology in several foundations like DUL and SUMO, and presents an example showing different situations in planning demonstrating the range of information the framework can provide for autonomous robots, Peer Reviewed, Postprint (author's final draft)

Autonomous indoor service robots are supposed to accomplish tasks, like serve a cup, which involve manipulation actions. Particularly, for complex manipulation tasks which are subject to geometric constraints, spatial information and a rich semantic knowledge about objects, types, and functionality are required, together with the way in which these objects can be manipulated. In this line, this paper presents an ontological-based reasoning framework called Perception and Manipulation Knowledge (PMK) that includes: (1) the modeling of the environment in a standardized way to provide common vocabularies for information exchange in human-robot or robot-robot collaboration, (2) a sensory module to perceive the objects in the environment and assert the ontological knowledge, (3) an evaluation-based analysis of the situation of the objects in the environment, in order to enhance the planning of manipulation tasks. The paper describes the concepts and the implementation of PMK, and presents an example demonstrating the range of information the framework can provide for autonomous robots., Peer Reviewed, Postprint (published version)

The book covers a variety of topics in Information and Communications Technology (ICT) and their impact on innovation and business. The authors discuss various innovations, business and industrial motivations, and impact on humans and the interplay between those factors in terms of finance, demand, and competition. Topics discussed include the convergence of Machine to Machine (M2M), Internet of Things (IoT), Social, and Big Data. They also discuss AI and its integration into technologies from machine learning, predictive analytics, security software, to intelligent agents, and many more. Contributions come from academics and professionals around the world. Covers the most recent practices in ICT related topics pertaining to technological growth, innovation, and business; Presents a survey on the most recent technological areas revolutionizing how humans communicate and interact; Features four sections: IoT, Wireless Ad Hoc & Sensor Networks, Fog Computing, and Big Data Analytics., (Chapter) The recent advancements in robotic systems set new challenges for robotic simulation software, particularly for planning. It requires the realistic behavior of the robots and the objects in the simulation environment by incorporating their dynamics. Furthermore, it requires the capability of reasoning about the action effects. To cope with these challenges, this study proposes an open-source simulation tool for knowledge-oriented physics-based motion planning by extending The Kautham Project, a C++ based open-source simulation tool for motion planning. The proposed simulation tool provides a flexible way to incorporate the physics, knowledge and reasoning in planning process. Moreover, it provides ROS-based interface to handle the manipulation actions (such as push/pull) and an easy way to communicate with the real robots, Peer Reviewed, Postprint (author's final draft)

This is an Accepted Manuscript of an article published by Taylor & Francis in Journal of experimental and theoretical artificial intelligence, published online: 30 Nov 2018 available online: https://www.tandfonline.com/doi/abs/10.1080/0952813X.2018.1544280, Robotic systems composed of several mobile robots moving in human environments pose several problems at perception, planning and control levels. In these environments, there may be obstacles obstructing the paths, which robots can remove by pushing or pulling them. At planning level, therefore, an efficient combination of task and motion planning is required. Even more if we assume a cooperative system in which robots can collaborate with each other by e.g. pushing together a heavy obstacle or by one robot clearing the way to another one. In this paper, we cope with this problem by proposing ¿-TMP, a smart combination of an heuristic task planner based on the Fast Forward method, a physics-based motion planner, and reasoning processes over the ontologies that code the knowledge on the problem. The significance of the proposal relies on how geometric and physics information is used within the computation of the heuristics in order to guide the symbolic search, i.e. how an artificial intelligence planning method is combined with low-level motion planning to achieve a feasible sequence of actions (composed of collision-free motions plus physically-feasible push/pull actions). The proposal has been validated with several simulated scenarios (using up to five robots that need to collaborate with each other to reach the goal state), showing how the method is able to solve challenging situations and also find an efficient solution in terms of power., Peer Reviewed, Postprint (author's final draft)

Planning efficiently at task and motion levels allows the setting of new challenges for robotic manipulation problems, like for instance constrained table-top problems for bi-manual robots. In this scope, the appropriate combination of task and motion planning levels plays an important role. Accordingly, a heuristic-based task and motion planning approach is proposed, in which the computation of the heuristic addresses a geometrically relaxed problem, i.e., it only reasons upon objects placements, grasp poses, and inverse kinematics solutions. Motion paths are evaluated lazily, i.e., only after an action has been selected by the heuristic. This reduces the number of calls to the motion planner, while backtracking is reduced because the heuristic captures most of the geometric constraints. The approach has been validated in simulation and on a real robot, with different classes of table-top manipulation problems. Empirical comparison with recent approaches solving similar problems is also reported, showing that the proposed approach results in significant improvement both in terms of planing time and success rate., Peer Reviewed, Postprint (author's final draft)

Assembly recipes can elegantly be represented in description logic theories. With such a recipe, the robot can figure out the next assembly step through logical inference. However, before performing an action, the robot needs to ensure various spatial constraints are met, such as that the parts to be put together are reachable, non occluded, etc. Such inferences are very complicated to support in logic theories, but specialized algorithms exist that efficiently compute qualitative spatial relations such as whether an object is reachable. In this work, we combine a logic-based planner for assembly tasks with geometric reasoning capabilities to enable robots to perform their tasks under spatial constraints. The geometric reasoner is integrated into the logic-based reasoning through decision procedures attached to symbols in the ontology., Peer Reviewed, Postprint (author's final draft)