Intelligent Service Robotics最新文献

This paper proposes a flexible vibrotactile actuator based on a dielectric elastomer which is fabricated by mixing a PDMS-Ecoflex elastomer and PC (propylene carbonate) solution. The proposed flexible vibrotactile actuator is composed of a top electrode, an adhesive tape, the PDMS-Ecoflex-PC-based elastomer, and a bottom electrode. The applied electric field between two parallel electrodes (top and bottom electrodes) creates an electrostatic force in the actuator, resulting in the actuator being compressed. The performance of the vibrotactile actuator based on dielectric elastomers is affected by the mechanical and dielectric properties of the dielectric elastomer. So, in this paper, we experimentally optimize the design of the haptic actuator and then quantitatively evaluate the actuator. For evaluation, the six samples of PDMS-Ecoflex-PC elastomers having different mixing ratios are prepared and their material properties are investigated by experiments. We fabricate the haptic actuators based on PDMS-Ecoflex-PC elastomers and then measure the haptic behaviors of the proposed actuator as a function of the applied voltage amplitude and frequency. Furthermore, we inquire the response time of the proposed actuator. Maximum vibrational force of the optimized sample is about 0.556 N at 140 Hz which is strong enough to stimulate human finger, and the response time is 21 ms which is fast enough to obtain the touch feedback in real time. From the results, we show that the proposed vibrotactile actuator creates a variety of haptic sensations in real time.

The integration of sensor data is crucial in the field of robotics to take full advantage of the various sensors employed. One critical aspect of this integration is determining the extrinsic calibration parameters, such as the relative transformation, between each sensor. The use of data fusion between complementary sensors, such as radar and LiDAR, can provide significant benefits, particularly in harsh environments where accurate depth data is required. However, noise included in radar sensor data can make the estimation of extrinsic calibration challenging. To address this issue, we present a novel framework for the extrinsic calibration of radar and LiDAR sensors, utilizing CycleGAN as a method of image-to-image translation. Our proposed method employs translating radar bird-eye-view images into LiDAR-style images to estimate the 3-DOF extrinsic parameters. The use of image registration techniques, as well as deskewing based on sensor odometry and B-spline interpolation, is employed to address the rolling shutter effect commonly present in spinning sensors. Our method demonstrates a notable improvement in extrinsic calibration compared to filter-based methods using the MulRan dataset.

In this paper, a control method is proposed for the flocking of multi-agent systems in the presence of obstacles. One of the main contributions of this work is the introduction of a safety distance parameter that ensures agents do not enter this safety distance during the flocking process. To achieve this, a fuzzy logic-based gradient of the potential function is designed. Furthermore, it is demonstrated that no consensus term is necessary in the control signal when all agents are informed about the desired path. Additionally, stability analysis is conducted for the proposed algorithm in free space, which allows the extraction of the ultimate bound of the tracking error. Finally, the effectiveness of the proposed algorithm is demonstrated through simulations conducted in free space, space with obstacles, and in the presence of measurement noise. The results obtained from these simulations are compared with the existing methods in the literature.

In this work, Coyote optimization algorithm (COA) is used for inverse kinematics optimization of a 7 degrees-of-freedom Kuka robot. The Denavit–Hartenberg (D–H) Convention approach is used to compute the forward kinematics of the robotic arm. The fitness functions based on sum of squares of distance and torque are employed to compute the optimized inverse kinematics solution using the COA. A comparative analysis has been conducted with other optimization algorithms including genetic algorithm (GA), particle swarm optimization (PSO) and Grey wolf optimization (GWO), artificial bee colony (ABC) optimization, and whale optimization algorithm (WOA) to evaluate the performance of the proposed approach. The experimental results show that the COA leads to least computation error of (3.59 times 10^{-7}) and computation time of 1.405 s as compared to GA, PSO, GWO, ABC, and WOA algorithms. Further, jerk being control input has a major impact on the efficiency of robotic arm. COA is employed to obtain the optimal joint parameters, such as joint velocity, joint acceleration, and joint jerk, respectively. This leads to a minimum jerk trajectory which contributes to the smooth movement of Kuka arm. The simulation of Kuka robotic arm for pick and place operations is performed in CoppeliaSim, which further justifies its usage for real-time applications.

Abstract

The accessible environment and locomotion performance of a robot are governed by the scale of the robot. The operating time and speed can be increased as the scale of the robot increases. However, the size of the robot does limit the accessible environment: the robot cannot pass through a space smaller than its size. Therefore, to explore an environment containing gaps, holes, and crevices, a small-scale robot is required. In this paper, we propose a sub-10 cm, sub-100 g scale jumping–crawling robot. The proposed robot consists of crawling, jumping, and self-righting mechanisms. The combination of crawling and jumping allowed the robot to overcome obstacles of various sizes. To reduce the weight and size of the robot, we employed a smart composite microstructures (SCM) design method and utilized a shape memory alloy (SMA) actuator. All the mechanisms and electronic components were compactly integrated into a single robot. The robot can crawl with the maximum speed of 3.94 cm/s (0.4 BL/s), and jump 19 cm which is 2.2 times its body height.

Abstract

Rehabilitation of the upper and lower limbs is crucial for patients recovering from strokes, surgeries, or injuries. Traditional rehabilitation often takes place in hospitals under the guidance of a therapist, which can delay treatment due to various constraints. This paper proposes a soft robotic device designed to aid in the flexion and extension of both the elbow and knee. The device utilizes pneumatic artificial muscles, constructed from an elastomeric bladder with a threaded mesh exterior, as its actuating mechanism. It operates in two distinct modes: a continuous passive mode, where continuous, repetitive flexion, and extension of limbs are carried out, and an active intent-based assisted mode, which detects a patient's movement intention via surface electromyography (sEMG) and subsequently aids in the movement execution. To test the effectiveness of the device, sEMG electrodes were placed on upper and lower limbs of six healthy male subjects, range of motion, and muscle activity were recorded with and without the device. Also NASA task load index (NASA-TLX) was calculated for the usability of the device. The results indicate the required muscle activity and range of motions for both upper and lower limb rehabilitation are effectively generated in both the modes.

Abstract

Soft surgical robots represent a groundbreaking innovation in the field of medical technology. These robots utilize soft, deformable materials to navigate and interact with delicate structures inside the human body, such as organs and blood vessels, with enhanced safety. They have the potential to transform healthcare by expanding the capabilities of minimally invasive surgeries, targeted drug delivery, and precise diagnostics. They can also reduce patient discomfort, recovery times, and the risk of complications, infections, and accidental injuries. The key to the functionality of soft surgical robots lies in their actuation mechanisms. Various actuation methods have been developed, including pneumatic, magnetic, tendon-driven, smart materials (like shape memory alloys, dielectric elastomer actuators, and ionic polymer–metal composites), and hybrid combinations of these mechanisms. Each actuator type offers unique advantages and challenges, making the selection of the right actuation solution a complex task. This review paper aims to provide a comprehensive understanding of these soft actuation mechanisms and their applications in surgical robotics. It delves into the current state of the art in various applications, from endoscopes and catheters to cardiac support devices, bioinspired inchworm robots, and more. While significant progress has been made in the field of soft actuators for surgical robotics, this paper identifies several challenges that must still be overcome to effectively apply these innovations in real-life surgical procedures on human patients.

Material handling loco-manipulation is heavily present in humanitarian assistance and disaster relief (HADR) efforts. Consider a scenario requiring human expertise to transcend the physical location of the human body; an approach—harnessing the innately long-range and precise abilities of robotic Avatar technologies—was successfully applied to material handling and loco-manipulation tasks, proving that humanoids may play an integral role in future disaster relief. Typically, first responders, such as firefighters and/or paramedics, must carry, push, pull, and handle objects, facilitating the transportation of goods. Hence, researchers have sought to enable full-sized humanoid robots to perform such essential material handling tasks. This work aims to tackle current limitations in humanoid object interaction capabilities, specifically with common objects such as carts, wheelbarrows, etc. Furthermore, this article compiles many methods to ensure stable gait during cart loco-manipulation. The examined objects range from simple carts (such as rolling and utility carts) to challenging carts (such as wheelbarrows). Thus, the authors present a comprehensive approach to address some of the most convoluted material handling and loco-manipulation challenges in the field of humanoid robotics. Finally, promising results are showcased when ART (Avatar Robotics Telepresence) and humanoid embodiment are applied in the context of loco-manipulation and material handling.

Abstract

Robot-assisted navigation is a perfect example of a class of applications requiring flexible control approaches. When the human is reliable, the robot should concede space to their initiative. When the human makes inappropriate choices the robot controller should kick-in guiding them towards safer paths. Shared authority control is a way to achieve this behaviour by deciding online how much of the authority should be given to the human and how much should be retained by the robot. An open problem is how to evaluate the appropriateness of the human’s choices. One possible way is to consider the deviation from an ideal path computed by the robot. This choice is certainly safe and efficient, but it emphasises the importance of the robot’s decision and relegates the human to a secondary role. In this paper, we propose a different paradigm: a human’s behaviour is correct if, at every time, it bears a close resemblance to what other humans do in similar situations. This idea is implemented through the combination of machine learning and adaptive control. The map of the environment is decomposed into a grid. In each cell, we classify the possible motions that the human executes. We use a neural network classifier to classify the current motion, and the probability score is used as a hyperparameter in the control to vary the amount of intervention. The experiments collected for the paper show the feasibility of the idea. A qualitative evaluation, done by surveying the users after they have tested the robot, shows that the participants preferred our control method over a state-of-the-art visco-elastic control.

Deploying socially assistive robots (SARs) at home, such as robotic companion pets, can be useful for tracking behavioral and health-related changes in humans during lifestyle fluctuations over time, like those experienced during CoVID-19. However, a fundamental problem required when deploying autonomous agents such as SARs in people’s everyday living spaces is understanding how users interact with those robots when not observed by researchers. One way to address that is to utilize novel modeling methods based on the robot’s sensor data, combined with newer types of interaction evaluation such as ecological momentary assessment (EMA), to recognize behavior modalities. This paper presents such a study of human-specific behavior classification based on data collected through EMA and sensors attached onboard a SAR, which was deployed in user homes. Classification was conducted using generative replay models, which attempt to use encoding/decoding methods to emulate how human dreaming is thought to create perturbations of the same experience in order to learn more efficiently from less data. Both multi-class and binary classification were explored for comparison, using several types of generative replay (variational autoencoders, generative adversarial networks, semi-supervised GANs). The highest-performing binary model showed approximately 79% accuracy (AUC 0.83), though multi-class classification across all modalities only attained 33% accuracy (AUC 0.62, F1 0.25), despite various attempts to improve it. The paper here highlights the strengths and weaknesses of using generative replay for modeling during human–robot interaction in the real world and also suggests a number of research paths for future improvement.