1,720,987 research outputs found
Cognitive Task Planning for Smart Industrial Robots
Full text linkThis research work presents a novel Cognitive Task Planning framework for Smart Industrial Robots. The framework makes an industrial mobile manipulator robot Cognitive by applying Semantic Web Technologies. It also introduces a novel Navigation Among Movable Obstacles algorithm for robots navigating and manipulating inside a firm.
The objective of Industrie 4.0 is the creation of Smart Factories: modular firms provided with cyber-physical systems able to strong customize products under the condition of highly flexible mass-production. Such systems should real-time communicate and cooperate with each other and with humans via the Internet of Things. They should intelligently adapt to the changing surroundings and autonomously navigate inside a firm while moving obstacles that occlude free paths, even if seen for the first time. At the end, in order to accomplish all these tasks while being efficient, they should learn from their actions and from that of other agents.
Most of existing industrial mobile robots navigate along pre-generated trajectories. They follow ectrified wires embedded in the ground or lines painted on th efloor. When there is no expectation of environment changes and cycle times are critical, this planning is functional. When workspaces and tasks change frequently, it is better to plan dynamically: robots should autonomously navigate without relying on modifications of their environments. Consider the human behavior: humans reason about the environment and consider the possibility of moving obstacles if a certain goal cannot be reached or if moving objects may significantly shorten the path to it. This problem is named Navigation Among Movable Obstacles and is mostly known in rescue robotics. This work transposes the problem on an industrial scenario and tries to deal with its two challenges: the high dimensionality of the state space and the treatment of uncertainty.
The proposed NAMO algorithm aims to focus exploration on less explored areas. For this reason it extends the Kinodynamic Motion Planning by Interior-Exterior Cell Exploration algorithm. The extension does not impose obstacles avoidance: it assigns an importance to each cell by combining the efforts necessary to reach it and that needed to free it from obstacles. The obtained algorithm is scalable because of its independence from the size of the map and from the number, shape, and pose of obstacles. It does not impose restrictions on actions to be performed: the robot can both push and grasp every object. Currently, the algorithm assumes full world knowledge but the environment is reconfigurable and the algorithm can be easily extended in order to solve NAMO problems in unknown environments. The algorithm handles sensor feedbacks and corrects uncertainties.
Usually Robotics separates Motion Planning and Manipulation problems. NAMO forces their combined processing by introducing the need of manipulating multiple objects, often unknown, while navigating. Adopting standard precomputed grasps is not sufficient to deal with the big amount of existing different objects. A Semantic Knowledge Framework is proposed in support of the proposed algorithm by giving robots the ability to learn to manipulate objects and disseminate the information gained during the fulfillment of tasks. The Framework is composed by an Ontology and an Engine. The Ontology extends the IEEE Standard Ontologies for Robotics and Automation and contains descriptions of learned manipulation tasks and detected objects. It is accessible from any robot connected to the Cloud. It can be considered a data store for the efficient and reliable execution of repetitive tasks; and a Web-based repository for the exchange of information between robots and for the speed up of the learning phase. No other manipulation ontology exists respecting the IEEE Standard and, regardless the standard, the proposed ontology differs from the existing ones because of the type of features saved and the efficient way in which they can be accessed: through a super fast Cascade Hashing algorithm. The Engine lets compute and store the manipulation actions when not present in the Ontology. It is based on Reinforcement Learning techniques that avoid massive trainings on large-scale databases and favors human-robot interactions.
The overall system is flexible and easily adaptable to different robots operating in different industrial environments. It is characterized by a modular structure where each software block is completely reusable. Every block is based on the open-source Robot Operating System. Not all industrial robot controllers are designed to be ROS-compliant. This thesis presents the method adopted during this research in order to Open Industrial Robot Controllers and create a ROS-Industrial interface for them
A Sampling-Based Tree Planner for Navigation Among Movable Obstacles
No full textThis paper proposes a planner that solves Navigation Among Movable Obstacles problems giving robots the ability to reason about the environment and choose when manipulating obstacles. It finds a path from a robot start configuration S to a goal configuration G taking into consideration the possibility of moving objects if G cannot be reached or if moving objects may significantly shorten the path. The planner combines the A*-Search and the exploration strategy of the Kinodynamic Motion Planning by Interior-Exterior Cell Exploration algorithm. It is locally optimal and independent from the size of the map and from the number, shape, and position of obstacles. It assumes full world knowledge but it can be easily extended in order to explore unknown environments
Temporal Task and Motion Planning with Metric Time for Multiple Object Navigation
No full textIntegrating metric time into Task And Motion Planning (TAMP) is challenging, especially with simultaneous object motion. Existing work focuses on classical and numeric TAMP, not considering deadlines, motions overlapping in time, and other temporal constraints. In this paper, we fill this gap by formalizing Temporal Task and Motion Planning (TTAMP) for multi-object navigation. We propose a novel interleaved planning technique for this problem, which leverages incremental Satisfiability Modulo Theory to ensure efficient reasoning on deadlines and action duration coupled with a motion planner supporting simultaneous object motion. Geometric data on encountered obstacles prunes unreachable symbolic regions, while temporal bounds limit the geometric search space. For multiple moving objects, our algorithm contextualizes the conflicts learned from the motion planner on overlapping actions so that entire classes of temporal plans are pruned from the search space of the task planner, ensuring the eventual termination of the interplay. We provide a comprehensive benchmark suite and demonstrate the effectiveness of our solver in leveraging these scenarios
A Planning Domain Definition Language Generator, Interpreter, and Knowledge Base for Efficient Automated Planning
No full textThe Planning Domain Definition Language (PDDL) successfully encodes classical planning tasks by easily describing objects, actions, and states in many planning domains. PDDL also describes domains, but they include only predefined sets of actions that can solve problems in a finite set of states. Indeed, the PDDL structure disables the processing of single predicates and operators. As a consequence, they cannot be arbitrarily composed to model new domains. To overcome these limitations, we propose a domain-independent, general-purpose knowledge design and task planning system based on the combination of a PDDL generator and interpreter and a Knowledge Base. The former builds planning data structures, where every object is a PDDL token independent of its original domain. It also allows merging these objects to formulate new PDDL domains and problems, ensuring consistency and validity of generated definitions. Their resolution is based on a powerful object-based reasoning instead of an inefficient lexical-based one. The latter contains the necessary relationships and representations to allow data storing and reusability. Their combination enables the storage, interpretation, and reuse of planning data, resulting in integration between the planning process and description logic reasoning. The overall system guarantees a flexible adaptation of the computed planning domains to changing environmental conditions, agent capabilities, and assigned tasks, promoting effective sharing and reuse of domain knowledge across different systems and applications
A Learning from Demonstration Framework for Manipulation Tasks
Full text linkThis paper presents a Robot Learning from Demonstration (RLfD) framework for teaching manipulation tasks in an industrial environment: the system is able to learn a task performed by a human demonstrator and reproduce it through a manipulator robot. An RGB-D sensor acquires the scene (human in action); a skeleton tracking algorithm extracts the useful information from the images acquired (positions and orientations of skeleton joints); and this information is given as input to the motion re-targeting system that remaps the skeleton joints into the manipulator ones. After the remapping, a model for the robot motion controller is retrieved by applying first a Gaussian Mixture Model (GMM) and then a Gaussian Mixture Regression (GMR) on the collected data. Two types of controller are modeled: a position controller and a velocity one. The former was presented in [10] inclusive of simulation tests, and here it has been upgraded extended the proves to a real robot. The latter is proposed for the first time in this work and tested both in simulation and with the real robot. Experiments were performed using a Comau Smart5 SiX manipulator robot and let to show a comparison between the two controllers starting from natural human demonstrations
An Integrated System to approach the Programming of Humanoid Robotics
Full text linkThis paper describes a set of laboratory experiences focused on humanoid robots offered at the University of Padua. Instructors developed an integrated system through which students can work with robots. The aim is to improve the educational experience introducing a new learning tool, namely a humanoid robot, and the Robots Operating System (ROS) in a constructivist framework. This approach to robotics teaching lets students exploiting up-to-date robotic technologies and to deal with multidisciplinary problems, applying a scientic approach. By using humanoid robots, students are able to compare human movements
to robot motion. The comparison brings out human/robot similarities, pushing students to solve complex motion problems in a more natural way while discovering robot limitations. In this paper, the learning objectives of the project, and the tools used by the students are presented. A set of evaluation results are provided in order to validate the authors'
purpose. Finally, a discussion about designed experiences and possible future improvements is reported, hoping to encourage further spread of educational robotics in schools at all levels
Using robotics to train students for Industry 4.0
Full text linkThis paper presents the master course on Autonomous Robotics that we offer at the School of Engineering of the University of Padova (Italy). Its novelty is the assignment of a lab project carefully designed to train students on autonomous and industrial robotics in the framework of Industry 4.0: the "Industry 4.0 Robotics Challenge". Students have to program both a manipulator and a mobile robot, together with a 3D vision system, in order to collaborate in the fulfillment of a pick-place-transport industrial task. We adopt a constructionist approach: project-based learning and team-based learning are applied to robotics and Industry 4.0. The project is organized as a challenge to motivate students to propose innovative ideas. A survey on students' satisfaction is reported at the end of the paper. We made the description of both the hardware and software setup, together with tutorials and wikis, publicly available to let other robotics instructors replicate our proposal and make it a point of reference for teaching robotics in the frame of Industry 4.0
Teaching humanoid robotics by means of human teleoperation through RGB-D sensors
Full text linkThis paper presents a graduate course project on humanoid robotics offered by the University of Padova. The target is to safely lift an object by teleoperating a small humanoid. Students have to map human limbs into robot joints, guarantee the robot stability during the motion, and teleoperate the robot to perform the correct movement. We introduce the following innovative aspects with respect to classical robotic classes: i) the use of humanoid robots as teaching tools; ii) the simplification of the stable locomotion problem by exploiting the potential of teleoperation; iii) the adoption of a Project-Based Learning constructivist approach as teaching methodology. The learning objectives of both course and project are introduced and compared with the students’ background. Design and constraints students have to deal with are reported, together with the amount of time they and their instructors dedicated to solve tasks. A set of evaluation results are provided in order to validate the authors’ purpose, including the students’ personal feedback. A discussion about possible future improvements is reported, hoping to encourage further spread of educational robotics in schools at all levels
- …
