Explore the vast range of titles available.

Obstacle avoidance for Dynamic Movement Primitives (DMPs) is still a challenging problem. In our previous work, we proposed a framework for obstacle avoidance based on superquadric potential functions to represent volumes. In this work, we extend our previous work to include the velocity of the system in the definition of the potential. Our formulations guarantee smoother behavior with respect to state-of-the-art point-like methods. Moreover, our new formulation allows obtaining a smoother behavior in proximity of the obstacle than when using a static (i.e. velocity independent) potential. We validate our framework for obstacle avoidance in a simulated multi-robot scenario and with different real robots: a pick-and-place task for an industrial manipulator and a surgical robot to show scalability; and navigation with a mobile robot in a dynamic environment.

This paper focuses on optimising pick-and-place tasks performed by a dual-arm collaborative robot in a specific shoe manufacturing industry environment. The robot must identify the pieces of a shoe placed on a tray, pick them up, and place them in a shoe mold for further processing. The shoe pieces arrive on the tray in random positions and angles and can be picked up in a different order. Optimising these tasks could increase the assembly speed of each unit and improve shoe production. To achieve this goal, a mathematical model based on binary integer linear programming (BILP) has been developed. This model determines the optimal sequence for picking and placing the shoe pieces in the mold, thus minimising the time required for picking and decision-making. The effectiveness of this approach has been tested using two 3-piece unit shoe models: one for training and another for validation. These models encompass a total of 500 trays. An analysis of the results reveals that BILP offers advantages for task motion planning in complex environments with multiple trajectories and the potential for collisions between arms. The model’s generalizability to shoes with n assembly pieces further confirms its robustness for various piece counts.

The field of robotics has been rapidly developing in recent years, and the work related to training robotic agents with reinforcement learning has been a major focus of research. This survey reviews the application of reinforcement learning for pick-and-place operations, a task that a logistics robot can be trained to complete without support from a robotics engineer. To introduce this topic, we first review the fundamentals of reinforcement learning and various methods of policy optimization, such as value iteration and policy search. Next, factors which have an impact on the pick-and-place task, such as reward shaping, imitation learning, pose estimation, and simulation environment are examined. Following the review of the fundamentals and key factors for reinforcement learning, we present an extensive review of all methods implemented by researchers in the field to date. The strengths and weaknesses of each method from literature are discussed, and details about the contribution of each manuscript to the field are reviewed. The concluding critical discussion of the available literature, and the summary of open problems indicates that experiment validation, model generalization, and grasp pose selection are topics that require additional research.

With the rapid development of robotics, robots gradually replace people to complete various tasks. Grasping is one of the most common tasks in industry and daily life. In addition to typical pick-and-place task, grasping a tool is the basis for performing other tasks, such as grabbing the key to open the door, grabbing a hammer to nail, etc. The robotic grippers are the manipulator in which the robot completes the grasp. Their performance characteristics have a significant impact on work efficiency because they are the parts interacting with the grasping objects directly. Therefore, this paper researches on robotic gripper and its related technology from the following aspects. First of all, the current robotic gripper type is analyzed in detail. Second, the research status of the most promising robotic gripper is reviewed widely. Third, the critical technology of robotic gripper is studied deeply. Finally, the analysis of robotic gripper development trend is performed prospectively.

Energy efficiency is a challenging and relevant research field in modern manufacturing industries, where robotic systems play an essential role in the automation of several industrial operations. In this paper, we present an approach for the energy-efficiency optimization of a 3-DOF parallel robot. The proposed strategy leverages the task placement, the execution time, and the length of the robot lower arms to minimize the energy consumption for the execution of a predefined high-speed pick-and-place operation. To evaluate the actuators energy consumption, the kinematic, dynamic and electro-mechanic mathematical models, as well as an equivalent multibody model, of the parallel robot are implemented. The results of extensive numerical simulations show that the proposed strategy provides notable improvements in the energy efficiency of the parallel robot, with respect to alternative approaches. Starting from a pick-and-place task with optimal task placement with a consumption of 38.2 J (with a cycle time of 0.4 s), the energy expenditure can be reduced to 3.75 J (with a cycle time of 1.86 s), with a reduction percentage of 90.2%, by additionally optimizing the execution time, and the length of the robot lower arms. These results lead to a reduction from 5733 J/min (for 150 cycles/min) to 121 J/min (for 32 cycles/min), allowing to choose the best trade-off between robot productivity and consumed energy.

Background Parkinson’s disease (PD) is a slowly progressive neurodegenerative disease. There are mixed reports on success of physiotherapy in patients with PD. Our objective was to investigate the functional improvements, motivation aspects and clinical effectiveness when using immersive 3D virtual reality versus non-immersive 2D exergaming. Methods We designed a randomized parallel study with 97 patients, but only 20 eligible participants were randomized in 2 groups; the one using 3D Oculus Rift CV1 and the other using a laptop. Both groups participated in the 10-session 3 weeks training with a pick and place task in the virtual world requiring precise hand movement to manipulate the virtual cubes. The kinematics of the hand was traced with Leap motion controller, motivation effect was assessed with modified Intrinsic Motivation Inventory and clinical effectiveness was evaluated with Box & Blocks Test (BBT) and shortened Unified Parkinson’s disease rating scale (UPDRS) before and after the training. Mack-Skilling non-parametrical statistical test was used to identify statistically significant differences ( p  < 0.05) and Cohen’s U3 test to find the effect sizes. Results Participants in the 3D group demonstrated statistically significant and substantially better performance in average time of manipulation (group x time, p  = 0.009), number of successfully placed cubes (group x time, p  = 0.028), average tremor (group x time, p  = 0.002) and UPDRS for upper limb (U3 = 0.35). The LCD and 3D groups substantially improved their BBT score with training (U3 = 0.7, U3 = 0.6, respectively). However, there were no statistically significant differences in clinical tests between the groups (group x time, p  = 0.2189, p  = 0.2850, respectively). In addition the LCD group significantly decreased the pressure/tension (U3 = 0.3), the 3D did not show changes (U3 = 0.5) and the differences between the groups were statistically different ( p  = 0.037). The 3D group demonstrated important increase in effort (U3 = 0.75) and perceived competences (U3 = 0.9). Conclusions The outcomes of the study demonstrated that the immersive 3D technology may bring increased interests/enjoyment score resulting in faster and more efficient functional performance. But the 2D technology demonstrated lower pressure/tension score providing similar clinical progress. A study with much larger sample size may also confirm the clinical effectiveness of the approaches. Trial registration The small scale randomized pilot study has been registered at ClinicalTrials.gov Identifier: NCT03515746 , 4 May 2018

Robot pick-and-place for unknown objects is still a very challenging research topic. This paper proposes a multi-modal learning method for robot one-shot imitation of pick-and-place tasks. This method aims to enhance the generality of industrial robots while reducing the amount of data and training costs the one-shot imitation method relies on. The method first categorizes human demonstration videos into different tasks, and these tasks are classified into six types to symbolize as many types of pick-and-place tasks as possible. Second, the method generates multi-modal prompts and finally predicts the action of the robot and completes the symbolic pick-and-place task in industrial production. A carefully curated dataset is created to complement the method. The dataset consists of human demonstration videos and instance images focused on real-world scenes and industrial tasks, which fosters adaptable and efficient learning. Experimental results demonstrate favorable success rates and loss results both in simulation environments and real-world experiments, confirming its effectiveness and practicality.

Understanding the impact of gravity on daily upper-limb movements is crucial for comprehending upper-limb impairments. This study investigates the relationship between gravitational force and upper-limb mobility by analyzing hand trajectories from 24 healthy subjects performing nine pick-and-place tasks, captured using a motion capture system. The results reveal significant differences in motor behavior in terms of planning, smoothness, efficiency, and accuracy when movements are performed against or with gravity. Analysis showed that upward movements ( g − ) resembled transversal ones ( g 0 ) but differed significantly from downward movements ( g + ). Corrective movements in g + began later than in g − and g 0 , indicating different motor planning models. Velocity profiles highlighted smoother movements in g − and g 0 compared to g + . Smoothness was lower in g + , indicating less coordinated movements. Efficiency showed significant variability with no specific trends due to subjective task duration among subjects. This study highlights the importance of considering gravitational effects when evaluating upper-limb movements, especially for individuals with neurological impairments. Planning metrics, including Percent Time to Peak Velocity and Percent Time to Peak Standard Deviation, showed significant differences between g − and g 0 compared to g + , supporting Fitts’ law on the trade-off between speed and accuracy. Two novel indications were also introduced: the Target Position Error and the Minimum Required Tunnel. These new indicators provided insights into hand-eye coordination and movement variability. The findings suggest that motor planning, smoothness, and efficiency are significantly influenced by gravity, emphasizing the need for differentiated approaches in assessing and rehabilitating upper-limb impairments. Future research should explore these metrics in impaired populations to develop targeted rehabilitation strategies.

Semi-autonomous telerobotic systems allow both humans and robots to exploit their strengths while enabling personalized execution of a remote task. For soft robots with kinematic structures dissimilar to those of human operators, it is unknown how the allocation of control between the human and the robot changes the performance. This work presents a set of interaction paradigms between a human and a remote soft-growing robot manipulator, with demonstrations in both real and simulated scenarios. The soft robot can grow and retract by eversion and inversion of its tubular body, a property we exploit in the interaction paradigms. We implemented and tested six different human-robot interaction paradigms, with full teleoperation at one extreme and gradually adding autonomy to various aspects of the task execution. All paradigms are demonstrated by two experts and two naive operators. Results show that humans and the soft robot manipulator can effectively split their control along different degrees of freedom while acting simultaneously to accomplish a task. In the simple pick-and-place task studied in this work, performance improves as the control is gradually given to the robot’s autonomy, especially when the robot can correct certain human errors. However, human engagement is maximized when the control over a task is at least partially shared. Finally, when the human operator is assisted by haptic guidance, which is computed based on soft robot tip position errors, we observed that the improvement in performance is dependent on the expertise of the human operator.

In this paper, we present an intelligent and flexible framework for autonomous pick-and-place tasks in previously unknown scenarios. It includes modules for object recognition, environment modeling, motion planning and collision avoidance, as well as sophisticated error handling and a task supervisor. The framework combines state-of-the-art algorithms and was validated during the first phase of the European Robotics Challenge in which it obtained first place in a field of 39 international contestants. We discuss our results and the potential application of our framework to real industrial tasks. Furthermore, we validate our approach with an application on a real harvesting manipulator. To inspire other teams participating in the challenge and as a tool for new researchers in the field, we release it as open source.