Explore the vast range of titles available.

As technology-enhanced children's learning has gained wide attention, programmable robots have been gradually introduced in early childhood education. Hence, it would be valuable to understand how young children perceive robot programming learning. Draw-a-picture technique is an ideal method to elicit ideas, thoughts, and feelings for children with limited literacy, and epistemic network analysis (ENA) is a novel analytical method to analyze children's conceptions through the visualized network model. Therefore, this study employed a draw-a-picture technique and ENA to explore 189 5-6-year-old young children's conceptions of robot programming learning and probe whether their conceptions differ by gender and learning achievements. Results revealed that most children believed that with robot programming kits, they could engage in programming activities with peers in any location and held positive emotions and attitudes. In addition, young children's conceptions of robot programming learning differ notably by gender and learning achievements. Based on the current findings, several suggestions were proposed, which could set a reference for future robot programming teaching in early childhood education.

In the digital age, robotics education has gained much attention for cultivating learners’ design thinking, creative thinking, critical thinking, and cooperative abilities. In particular, critical thinking as one of the key competencies in Education for Sustainable Development (ESD) can stimulate imagination and creation. It is of great value to explore critical thinking cultivation in robot programming learning. Therefore, this study applied different teaching tools to take the content of “making a manipulator through programming and construction” in a robotics course as an experimental context to examine the promotion of learners’ critical thinking. Before the experiment, a pre-test was conducted to measure students’ critical thinking ability. Then, all students were divided randomly into two groups: one as an experimental group with the teaching tool of Construction–Criticism–Migration (CCM) instructional design, and the other as a control group with the traditional teaching tool of demonstrate–practice instructional design. After a 6-week experiment, the measurement of critical thinking was applied as a post-test. SPSS was used to conduct an independent sample t test and one-way ANOVA to explore whether students’ critical thinking ability had improved and whether differences were found between the experimental group and the control group after the 6-week experiment. The results showed that the experimental group students’ critical thinking ability significantly improved, whereas no significant difference was found before and after the experiment for the control group. A significant difference existed between the two groups. This study provides an example of a new instructional design teaching tool for the teaching of robot programming and can provide valuable suggestions for instructors in middle schools.

Locally weighted as well as Gaussian mixtures learning algorithms are suitable strategies for trajectory learning and skill acquisition, in the context of programming by demonstration. Input streams other than visual information, as used in most applications up to date, reveal themselves as quite useful in trajectory learning experiments where visual sources are not available. For the first time, force/torque feedback through a haptic device has been used for teaching a teleoperated robot to empty a rigid container. The memory-based LWPLS and the non-memory-based LWPR algorithms [1,2,3], as well as both the batch and the incremental versions of GMM/GMR [4,5] were implemented, their comparison leading to very similar results, with the same pattern as regards to both the involved robot joints and the different initial experimental conditions. Tests where the teacher was instructed to follow a strategy compared to others where he was not lead to useful conclusions that permit devising the new research stages, where the taught motion will be refined by autonomous robot rehearsal through reinforcement learning.

Human-robot collaboration as a multidisciplinary research topic is still pursuing the robots’ enhanced intelligence to be more human-compatible and fit the dynamic and stochastic characteristics of human. However, the uncertainties brought by the human partner challenge the task-planning and decision-making of the robot. When aiming at industrial tasks like collaborative assembly, dynamics on temporal dimension and stochasticities on the order of procedures need to be further considered. In this work, we bring a new perspective and solution based on reinforcement learning, where the problem is regarded as training an agent towards tasks in dynamic and stochastic environments. Concretely, an adapted training approach based on the deep Q learning method is proposed. This method regards both the robot and the human as the agents in the interactive training environment for deep reinforcement learning. With the consideration of task-level industrial human-robot collaboration, the training logic and the agent-environment interaction have been proposed. For the human-robot collaborative assembly tasks in the case study, it is illustrated that our method could drive the robot represented by one agent to collaborate with the human partner even the human performs randomly on the task procedures.

Around the world, programming education is actively promoted by such factors as economic and technical requirements. The use of a robot in programming education could help students understand computer-science concepts more easily. In this study we designed a course in programming a robot for elementary school students and investigated its effectiveness by implementing it in actual classes. We further examined the effects of students’ prior skills and of gender on the outcomes. In addition, we reviewed the applicable teaching and learning strategies in the field of robotics programming. Our course in programming a robot was implemented for 155 Korean elementary school students in the fifth and sixth grades. The course was conducted for 11 weeks. Our results show that teaching programming by using a robot significantly improved computational thinking and creativity. Computational thinking, however, was not significantly improved in the group that initially showed high scores. Further, creativity was improved more in girls than in boys, and the mean difference was statistically significant, but the difference in computational thinking was not. The implication of this study is that the best approach is to design a course in programming a robot and apply it in actual classrooms in order to discuss teaching and learning strategies according to students’ prior skills and their gender.

The study of robotics has become a popular course among many educational programs, especially as a technical elective. A significant part of this course involves having the students learn how to program the movement of a robotic arm by controlling the velocity of its individual joint motors, a topic referred to as joint programming. They must learn how to develop algorithms to move the end effector of the arm by controlling the instantaneous velocity or some similar aspect, of each joint motor. To support this learning activity, physical or virtual robotic arms are typically employed. Visual observation of the movement of the arm provides feedback to the correctness of the student’s joint programming algorithms. A problem arises with supporting the student in learning how to move the robotic arm with precise velocity along some path, a subtopic of joint programming referred to as differential movements. To develop this knowledge, the student must produce and test differential movement algorithms and have the capability to verify its correctness. Regardless of the type of arm used, physical or virtual, the human eye cannot notice the difference between a correct or incorrect movement of the end effector as this will involve noticing small differences in velocities. This study found that by simulating the process of spray painting on a virtual canvas, the correctness of a differential movement algorithm may be accessed by observing the resulting paint on the canvas as opposed to observing the movement of the arm. A model of a set of spray-painting equipment and a canvas was added to an existing virtual robotic arm educational tool and used in an Introduction to Robotics class offered at Florida Gulf Coast University in Spring 2019 and Spring 2020. The class offered in Spring 2019 used the virtual arm but without the spray-painting feature while the class offered in Spring 2020 used the new spray-painting feature that was added to the virtual arm. Exam results show that 59.4% of the students that used the new feature scored at least an 85% on the corresponding differential movements exam question compared to only 5.6% of the class that did not use the added spray-painting feature. The differential movement exam question simply asked the student to produce a differential movements algorithm to move the arm with a specified velocity alone a straight line.

The objective of this paper is to propose a framework for a robot to learn multiple Sensory-Motor Contingencies from human demonstrations and reproduce them. Sensory-Motor Contingencies are a concept that describes intelligent behavior of animals and humans in relation to their environment. They have been used to design control and planning algorithms for robots capable of interacting and adapting autonomously. However, enabling a robot to autonomously develop Sensory-Motor Contingencies is challenging due to the complexity of action and perception signals. This framework leverages tools from Learning from Demonstrations to have the robot memorize various sensory phases and corresponding motor actions through an attention mechanism. This generates a metric in the perception space, used by the robot to determine which sensory-motor memory is contingent to the current context. The robot generalizes the memorized actions to adapt them to the present perception. This process creates a discrete lattice of continuous Sensory-Motor Contingencies that can control a robot in loco-manipulation tasks. Experiments on a 7-dof collaborative robotic arm with a gripper, and on a mobile manipulator demonstrate the functionality and versatility of the framework.

Autonomous mobile robots (AMRs) are increasingly used in modern intralogistics systems as complexity and performance requirements become more stringent. One way to increase performance is to improve the operation and cooperation of multiple robots in their shared environment. The paper addresses these problems with a method for off-line route planning and on-line route execution. In the proposed approach, pre-computation of routes for frequent pick-up and drop-off locations limits the movements of AMRs to avoid conflict situations between them. The paper proposes a reinforcement learning approach where an agent builds the routes on a given layout while being rewarded according to different criteria based on the desired characteristics of the system. The results show that the proposed approach performs better in terms of throughput and reliability than the commonly used shortest-path-based approach for a large number of AMRs operating in the system. The use of the proposed approach is recommended when the need for high throughput requires the operation of a relatively large number of AMRs in relation to the size of the space in which the robots operate.

This paper proposes a robust model predictive control (MPC) strategy for the trajectory tracking control of a four-mecanum-wheeled omni-directional mobile robot (FM-OMR) under various constraints. The method proposed in this paper can solve various constraints while implementing trajectory tracking of the FM-OMR. Firstly, a kinematics model with constraint relationship of the FM-OMR is established. On the basis of the kinematics model, the kinematics trajectory tracking error model of the FM-OMR is further formulated. Then, it is transformed into a constrained quadratic programming(QP) problem by the method of MPC. In addition, aiming at the speed deficiencies of conventional neural networks in QP solving, a delayed neural network (DNN) is applied to solve the optimal solution of the QP problem, and compared with the Lagrange programming neural network (LPNN) to show the rapidity of the DNN. Finally, two simulation cases considering bounded random disturbance are provided to verify the robustness and effectiveness of the proposed method. Theoretical analysis and simulation results show that the control strategy is effective and feasible.

Robotics is increasingly entering the field of education. The tools, methods, and approaches of robotics contribute to the development of all areas of STEAM education, both individually and interdisciplinary. The present work aims to highlight the robots that are most effective in STEAM education and to classify robots used in education in terms of their frequency of use, features, flexibility, manufacturer, sensors, software, programming language, connection, recommended age, usefulness in education, and their cost. It turned out that there are packages for building robots, pre-assembled robots, and social robots. Their form can be animal, human, car, etc., and they have various properties; for example, they can move and fly. Moreover, most of the robots proposed for education use block-based programming; for example, the Scratch language. Common features of robots are that the robot follows a path, reacts to sounds, and recognizes obstacles, with various sensors; for example, vision. Finally, it turned out to be necessary to design an activity guide for each lesson, which will be accompanied by instructions and specific steps for teachers and students.