An Adaptive Imitation Learning Framework for Robotic Complex Contact-Rich Insertion Tasks

Complex contact-rich insertion is a ubiquitous robotic manipulation skill and usually involves nonlinear and low-clearance insertion trajectories as well as varying force requirements. A hybrid trajectory and force learning framework can be utilized to generate high-quality trajectories by imitation learning and find suitable force control policies efficiently by reinforcement learning. However, with the mentioned approach, many human demonstrations are necessary to learn several tasks even when those tasks require topologically similar trajectories. Therefore, to reduce human repetitive teaching efforts for new tasks, we present an adaptive imitation framework for robot manipulation. The main contribution of this work is the development of a framework that introduces dynamic movement primitives into a hybrid trajectory and force learning framework to learn a specific class of complex contact-rich insertion tasks based on the trajectory profile of a single task instance belonging to the task class. Through experimental evaluations, we validate that the proposed framework is sample efficient, safer, and generalizes better at learning complex contact-rich insertion tasks on both simulation environments and on real hardware.

4d CT to assess spinal instability in developmental anomaly of posterior arch of atlas

Four-dimensional (4D) CT uniquely allows cinematic visualization of the entirety of joint motion throughout dynamic movement, which can reveal subtle or transient internal joint derangements not evident on static images. As developmental anomalies of the posterior arch can predispose to cervical spinal instability and neurological morbidity, precise assessment of spinal movement during motion is of clinical relevance. We describe the use of 4D-CT in a subject with partial absence of posterior C1 arch. This, to our knowledge, is the first such report. In at-risk individuals, 4D-CT has the potential to enable an assessment of spinal instability with a higher level of clarity and, in this sense, its more routine implementation may be a future direction.

Zoomorphic Mobile Robot Development for Vertical Movement Based on the Geometrical Family Caterpillar

Research in robotics is one of the promising areas in mobile robot development, which is planned to be implemented in extreme dangerous conditions of areas explored by humans. This article aims at developing and improving a prototype of zoomorphic mobile robots that are designed to repeat the existing biological objects in nature. The authors performed a detailed analysis on the structure and dynamics of the geometrical family caterpillar movement, which is passed on a practical design implemented to perform the dynamic movement on uneven vertical surfaces. Based on the obtained analysis, the design and kinematic scheme of the movement is developed. Also, the structural control scheme via the Internet technologies that allow carrying out remote control is presented in this paper, considering the dangerous mobile robot work zones. To test the recommended solutions, the authors developed detailed 3D printed models of the mobile robot constructions for the implemented hardware. The model of the mobile robot is constructed, and the control system with examples of the user program code implementations is performed. Several experiments were performed, which showed the efficiency of the achieved mobile robot for solving problems of vertical movement on uneven metal surfaces. Moreover, the obtained slow motion of the designed robot proves that the simulated robot behaves similarly to the natural behavior of caterpillar movement.

Motion generation for walking exoskeleton robot using multiple dynamic movement primitives sequences combined with reinforcement learning

In order to assist patients with lower limb disabilities in normal walking, a new trajectory learning scheme of limb exoskeleton robot based on dynamic movement primitives (DMP) combined with reinforcement learning (RL) was proposed. The developed exoskeleton robot has six degrees of freedom (DOFs). The hip and knee of each artificial leg can provide two electric-powered DOFs for flexion/extension. And two passive-installed DOFs of the ankle were used to achieve the motion of inversion/eversion and plantarflexion/dorsiflexion. The five-point segmented gait planning strategy is proposed to generate gait trajectories. The gait Zero Moment Point stability margin is used as a parameter to construct a stability criteria to ensure the stability of human-exoskeleton system. Based on the segmented gait trajectory planning formation strategy, the multiple-DMP sequences were proposed to model the generation trajectories. Meanwhile, in order to eliminate the effect of uncertainties in joint space, the RL was adopted to learn the trajectories. The experiment demonstrated that the proposed scheme can effectively remove interferences and uncertainties.

Study of Ballast Track Dynamic Behavior Evaluation Comparative Analysis According to the On-Site Laying of Rectangular-Parallelepiped Fiber Reinforcement Sack

The roadbed reinforcement method using cuboidal fiber reinforcement is an eco-friendly method that compensates for the shortcomings of various existing roadbed reinforcement technologies. A rectangular parallelepiped fiber reinforcement was installed in section oo of the existing line where fine-grained gravel, floating sleepers, and sleeper cracks occurred. The basic physical property test of the upper subgrade was conducted, and the vertical displacement and acceleration of rails and sleepers were compared and analyzed according to the train operation of the reinforced and non-reinforced sections. A comparative analysis of the vertical displacement and acceleration according to train operation after laying the rectangular parallelepiped fiber reinforcement demonstrated that the vertical displacement and acceleration were reduced by up to 84% and 80%, respectively. The dynamic movement of the rail was reduced owing to the reinforcing effect of the rectangular parallelepiped reinforcement, thereby improving the roadbed bearing capacity and stability.

Escape Path Obstacle-Based Mobility Model (EPOM) for Campus Delay-Tolerant Network

In Delay-Tolerant Networks (DTNs), humans are the main carriers of mobile devices, signifying that human mobility can be exploited by extracting nodes’ interests, social behavior, and spatiotemporal features for the performance evaluation of DTNs protocols. This paper presents a new mobility model that describes students’ daily activities in a campus environment. Unlike the conventional random walk models, which use a free space environment, our model includes a collision-avoidance technique that generates an escape path upon encountering obstacles of different shapes and sizes that obstruct pedestrian movement. We evaluate the model’s usefulness by comparing the distributions of its synthetic traces with realistic traces in terms of spatial, temporal, and connectivity features of human mobility. Similarly, we analyze the concept of dynamic movement clusters observed on the location-based trajectories of the studied real traces. The model synthetically generates traces with the distribution of the intercluster travel distance, intracluster travel distance, direction of movement, contact duration, intercontact time, and pause time similar to the distribution of real traces.

Anatomical Injection Guidelines for Glabellar Frown Lines Based on Ultrasonographic Evaluation

When botulinum neurotoxin (BoNT) is injected to treat glabellar frown lines, the corrugator supercilia muscle (CSM) and procerus muscles are the main targets. Although there have been many studies on the treatment of glabellar frown lines, no study has confirmed the dynamic movement under ultrasonography (US). This study examined and evaluated dynamic muscle movements under US, thereby providing more effective BoNT injection guidelines for glabellar frowning. Glabellar frowning was categorized as either Type A or B. Type A is the general frowning pattern in which vertical wrinkles are made by contracting the CSM and procerus muscles (81%, n = 13). On US images, the procerus muscle thickens and the bilateral CSMs contract. Type B is an upward frowning pattern demonstrating upward elevation of vertical wrinkles due to hyperactive contraction of the frontalis muscle during frowning (19%, n = 3). On US images, the hypoechoic frontalis muscle thickens, forming horizontal forehead lines. After BoNT injection into the CSM and frontalis muscle but not the procerus muscle, Type B patterns showed improvements in the vertical crease and horizontal forehead line. Both types showed improvement in glabellar frown lines after conventional injection, but the horizontal forehead line did not improve in Type B. Type B wrinkles improved after additional injections into the frontalis muscle. This study provided novel anatomical findings related to the injection of glabellar frown lines with BoNT. Preliminary analysis and optimized procedures using US will enable more effective and safer injections.

A Novel Balance Control Strategy Based on Enhanced Stability Pyramid Index and Dynamic Movement Primitives for a Lower Limb Human-Exoskeleton System

The lower limb exoskeleton is playing an increasing role in enabling individuals with spinal cord injury (SCI) to stand upright, walk, turn, and so on. Hence, it is essential to maintain the balance of the human-exoskeleton system during movements. However, the balance of the human-exoskeleton system is challenging to maintain. There are no effective balance control strategies because most of them can only be used in a specific movement like walking or standing. Hence, the primary aim of the current study is to propose a balance control strategy to improve the balance of the human-exoskeleton system in dynamic movements. This study proposes a new safety index named Enhanced Stability Pyramid Index (ESPI), and a new balance control strategy is based on the ESPI and the Dynamic Movement Primitives (DMPs). To incorporate dynamic information of the system, the ESPI employs eXtrapolated Center of Mass (XCoM) instead of the center of mass (CoM). Meanwhile, Time-to-Contact (TTC), the urgency of safety, is used as an automatic weight assignment factor of ESPI instead of the traditional manual one. Then, the balance control strategy utilizing DMPs to generate the gait trajectory according to the scalar and vector values of the ESPI is proposed. Finally, the walking simulation in Gazebo and the experiments of the human-exoskeleton system verify the effectiveness of the index and balance control strategy.