Imitation from Observation (IfO) prompts the robot to imitate tasks from unlabeled videos via reinforcement learning (RL). The performance of the IfO algorithm depends on its ability to extract task-relevant representations since images are informative. Existing IfO algorithms extract image representations by using a simple encoding network or pre-trained network. Due to the lack of action labels, it is challenging to design a supervised task-relevant proxy task to train the simple encoding network. Representations extracted by a pre-trained network such as Resnet are often task-irrelevant. In this article, we propose a new approach for robot IfO via multimodal observations. Different modalities describe the same information from different sides, which can be used to design an unsupervised proxy task. Our approach contains two modules: the unsupervised cross-modal representation (UCMR) module and a self-behavioral cloning (self-BC)-based RL module. The UCMR module learns to extract task-relevant representations via a multimodal unsupervised proxy task. The Self-BC for further offline policy optimization collects successful experiences during the RL training. We evaluate our approach on the real robot pouring water task, quantitative pouring task, and pouring sand task. The robot achieves state-of-the-art performance.

Bilateral teleoperation systems encounter challenges in achieving synchronisation between master and slave robots due to communication time delays. This paper addresses the instability caused by these delays and proposes a solution through advanced control algorithms. Nonlinear optimisation algorithms might only sometimes deliver solutions in the allotted time, particularly when handling complicated, high-dimensional issues or when optimisation iterations are extensive. The study first develops a comprehensive mathematical model encompassing the dynamics and communication intricacies of both master and slave sides in teleoperation. By recognising the limitations of existing proportional-derivative controllers in compensating for communication errors, a sequential quadratic programming-proportional-integral-derivative (SQP-PID) controller is introduced. This controller accumulates and rectifies synchronisation delay errors, ensuring precise control without steady-state deviations. The proposed SQP-PID controller stands out for its ability to handle steady-state errors effectively, offering swift response and maintaining stability. Leveraging the SQP optimisation algorithm, it intelligently tunes the parameters, minimising synchronisation errors. The approach capitalises on the simplicity, performance, and robustness of the SQP-PID controller, providing a promising avenue for enhancing bilateral teleoperation systems’ accuracy and stability, maintaining initial discrepancy with a best fitness value of 0.98 % in varied operating conditions.

Snake robots can move flexibly due to their special bodies and gaits. However, it is difficult to plan their motion in multi-obstacle environments due to their complex models. To solve this problem, this work investigates a reinforcement learning-based motion planning method. To plan feasible paths, together with a modified deep Q-learning algorithm, a Floyd-moving average algorithm is proposed to ensure smoothness and adaptability of paths for snake robots’ passing. An improved path integral algorithm is used to work out gait parameters to control snake robots to move along the planned paths. To speed up the training of parameters, a strategy combining serial training, parallel training, and experience replaying modules is designed. Moreover, we have designed a motion planning framework consists of path planning, path smoothing, and motion planning. Various simulations are conducted to validate the effectiveness of the proposed algorithms.

As the proportion of the elderly population in the USA expands, so will the demand for rehabilitation and social care, which play an important role in maintaining function and mediating motor and cognitive decline in older adults. The use of social robotics and telemedicine are each potential solutions but each have limitations. To address challenges with classical telemedicine for rehabilitation, we propose to use a social robot-augmented telepresence (SRAT), Flo, which was deployed for long-term use in a community-based rehabilitation facility catering to older adults. Our goals were to explore how clinicians and patients would use and respond to the robot during rehab interactions. In this pilot study, three clinicians were recruited and asked to rate usability after receiving training for operating the robot and two of them conducted multiple rehab interactions with their patients using the robot (eleven patients with cognitive impairment and/or motor impairment and 23 rehab sessions delivered via SRAT in total). We report on the experience of both therapists and patients after the interactions.

This paper proposes a robust control approach to achieve high-precision trajectory tracking for permanent magnet linear motor (PMLM) system containing uncertainties by describing the dynamic model of PMLM based on the Udwadia-Kalaba equation combined with constraint-following method. First, the system of PMLM is described as a constraint-following system by adding the generalized constraint force to the unconstrained Udwadia-Kalaba equation of PMLM system. Second, the robust constraint-following controller is designed based on the proposed model after uncertainty analysis. Moreover, the proposed controller is verified to guarantee deterministic performance for uncertain systems: uniformly bounded and uniformly ultimately bounded. Third, the numerical simulation and experimental validation demonstrate the effectiveness of proposed controller. Finally, the design approach of constraint-following can be applied to other systems with uncertainties.

Lower limb exoskeletons (LLEs) have demonstrated their potential in delivering quantified repetitive gait training for individuals afflicted with gait impairments. A critical concern in robotic gait training pertains to fostering active patient engagement, and a viable solution entails harnessing the patient’s intrinsic effort to govern the control of LLEs. To address these challenges, this study presents an innovative online gait learning approach with an appropriate control strategy for rehabilitation exoskeletons based on dynamic movement primitives (DMP) and an Assist-As-Needed (AAN) control strategy, denoted as DMP-AAN. Specifically tailored for post-stroke patients, this approach aims to acquire the gait trajectory from the unaffected leg and subsequently generate the reference gait trajectory for the affected leg, leveraging the acquired model and the patient’s personal exertion. Compared to conventional AAN methodologies, the proposed DMP-AAN approach exhibits adaptability to diverse scenarios encompassing varying gait patterns. Experimental validation has been performed using the lower limb rehabilitation exoskeleton HemiGo. The findings highlight the ability to generate suitable control efforts for LLEs with reduced human-robot interactive force, thereby enabling highly patient-controlled gait training sessions to be achieved.

Achieving the high-precision control of cable-driven parallel robots (CDPRs) is complex because of their structural properties. In this paper, a quintessential redundant CDPR is designed as the research subject, and a continuous switching sliding mode controller based on workspace vision is implemented to enhance the accuracy and stability of trajectory tracking. In addition, a virtual prototype of the CDPR with uncertainties is created in the simulation analysis software ADAMS, and co-simulation is performed with the control system designed in Simulink to validate the effectiveness of the proposed control strategy. Furthermore, a CDPR platform is established for trajectory tracking experiments using the visual-based position feedback method. The trajectory tracking performance with the three control schemes is then evaluated. The experimental results show that the continuous switching sliding mode control algorithm can significantly decrease trajectory tracking errors and exhibit superior trajectory tracking performance compared to the other control strategies.

This paper provides the methodology used to simulate and control an icosahedral tensegrity structure augmented with movable masses attached to each bar to provide a means of locomotion. The center of mass of the system can be changed by moving the masses along the length of each of the bars that compose the structure. Moving the masses changes the moments created by gravitational force, allowing for the structure to roll. With this methodology in mind, a controller was created to move the masses to the desired locations to cause such a roll. As shown later in this paper, such a methodology, assuming the movable masses have the required mass, allows for full control of the system using a quasi-static controller created specifically for this system. This system has advantages over traditional tensegrity controllers because it retains its shape and is designed for high-shock scenarios.

In the field of laparoscopic surgery, research is currently focusing on the development of new robotic systems to assist practitioners in complex operations, improving the precision of their medical gestures. In this context, the performance of these robotic platforms can be conditioned by various factors, such as the robot’s accessibility and dexterity in the task workspace. In this paper, we present a new strategy for improving the kinematic and dynamic performance of a 7-degrees of freedom robot-assisted camera-holder system for laparoscopic surgery. This approach involves the simultaneous optimization of the robot base placement and the laparoscope mounting orientation. To do so, a general robot capability representation approach is implemented in an innovative multiobjective optimization algorithm. The obtained results are first evaluated in simulation and then validated experimentally by comparing the robot’s performances implementing both the existing and the optimized solution. The optimization result led to a 2% improvement in the accessibility index and a 14% enhancement in manipulability. Furthermore, the dynamic performance criteria resulted in a substantial 43% reduction in power consumption.

This paper is concerned with the problem of collision-free path planning for manipulators in multi-obstacle scenarios. Aiming at overcoming the deficiencies of existing algorithms in excessive time consumption and poor expansion quality, a path planning algorithm named Fast Bi-directional Rapidly-exploring Random Tree (FBi-RRT) with novel heuristic node expansion is proposed, which includes a selective-expansion strategy and a vertical-exploration strategy. The selective-expansion strategy is designed to guide the selection of the nearest-neighbor node to avoid the repeated expansion failure, thereby shortening the overall planning time. Also, the vertical-exploration strategy is developed to regulate the expansion direction of the collision nodes to escape from the obstacle space with less blindness, thus improving the expansion quality and further reducing time cost. Compared with previous planning algorithms, FBi-RRT can generate a feasible path for manipulators in a drastically shorter time. To validate the effectiveness of the proposed heuristic node expansion, FBi-RRT is conducted on a 6-DOF manipulator and tested in five scenarios. The experimental results demonstrate that FBi-RRT outperforms the existing methods in time consumption and expansion quality.

Expert drivers possess the ability to execute high sideslip angle maneuvers, commonly known as drifting, during racing to navigate sharp corners and execute rapid turns. However, existing model-based controllers encounter challenges in handling the highly nonlinear dynamics associated with drifting along general paths. While reinforcement learning-based methods alleviate the reliance on explicit vehicle models, training a policy directly for autonomous drifting remains difficult due to multiple objectives. In this paper, we propose a control framework for autonomous drifting in the general case, based on curriculum reinforcement learning. The framework empowers the vehicle to follow paths with varying curvature at high speeds, while executing drifting maneuvers during sharp corners. Specifically, we consider the vehicle’s dynamics to decompose the overall task and employ curriculum learning to break down the training process into three stages of increasing complexity. Additionally, to enhance the generalization ability of the learned policies, we introduce randomization into sensor observation noise, actuator action noise, and physical parameters. The proposed framework is validated using the CARLA simulator, encompassing various vehicle types and parameters. Experimental results demonstrate the effectiveness and efficiency of our framework in achieving autonomous drifting along general paths. The code is available at https://github.com/BIT-KaiYu/drifting.

Continuum robot has become a research hotspot due to its excellent dexterity, flexibility and applicability to constrained environments. However, the effective, secure and accurate path planning for the continuum robot remains a challenging issue, for that it is difficult to choose a suitable inverse kinematics solution due to its redundancy in the confined environment. This paper presents a collision-free path planning method based on the improved artificial potential field (APF) for the cable-driven continuum robot, in which the beetle antennae search algorithm is adopted to deal with the optimal problem of APF without the necessary for velocity kinematics. In addition, the local optimum problem of traditional APF is solved by the randomness of the antennae’s direction vector which can make the algorithm easily jump out of local minima. The simulation and experimental results verify the efficiency of the proposed path planning method.

The flexible flat cable (FFC) assembly task is a prime challenge in electronic manufacturing. Its characteristics of being prone to deformation under external force, tiny assembly tolerance, and fragility impede the application of robotic assembly in this field. To achieve reliable and stable robotic automation assembly of FFC, an efficient assembly skill acquisition strategy is presented by combining a parallel robot skill learning algorithm with adaptive impedance control. The parallel robot skill learning algorithm is proposed to enhance the efficiency of FFC assembly skill acquisition, which reduces the risk of damaging FFC and tackles the uncertain influence resulting from deformation during the assembly process. Moreover, FFC assembly is also a complex contact-rich manipulation task. An adaptive impedance controller is designed to implement force tracking during the assembly process without precise environment information, and the stability is also analyzed based on the Lyapunov function. Experiments of FFC assembly are conducted to illustrate the efficiency of the proposed method. The experimental results demonstrate that the proposed method is robust and efficient.

Prostate cancer is the second most common malignancy in American men. High-dose-rate brachytherapy is a popular treatment technique in which a large, localized radiation dose is used to kill cancer. Utilization of curvilinear catheter implantation inside the prostate gland to provide access channels to host the radiation source has shown superiority in terms of improved dosimetric constraints compared to straight needles. To this aim, we have introduced an active needle to curve inside the prostate conformal to the patient’s specific anatomical relationship for improved dose distribution to the prostate and reduced toxicity to the organs at risk. This work presents closed-loop control of our tendon-driven active needle in water medium and air using the position feedback of the tip obtained in real time from an ultrasound (US) or an electromagnetic (EM) tracking sensor, respectively. The active needle consists of a compliant flexure section to realize bending in two directions via actuation of two internal tendons. Tracking errors using US and EM trackers are estimated and compared. Results show that the bending angle of the active needle could be controlled using position feedback of the US or the EM tracking system with a bending angle error of less than 1.00 degree when delay is disregarded. It is concluded that the actuation system and controller, presented in this work, are able to realize a desired bending angle at the active needle tip with reasonable accuracy paving the path for tip tracking and manipulation control evaluations in a prostate brachytherapy.

An improved Monte-Carlo algorithm is proposed to address the problem of an unclear workspace boundary in a multi-robot coordinated lifting system. The spatial configuration of a multi-robot coordinated lifting system with rolling base is analyzed, and the kinematics and static workspace of the system are established. To solve the workspace boundary, first, the error introduced by the layers is reduced using an intra-layer thinning method. Second, each layer is divided simultaneously based on rows and columns, and the initial boundary points are extracted by searching for the best value. Third, random three-dimensional points are added in the neighborhood, and pseudo-boundary points are removed using three-dimensional local spherical coordinates to achieve a high-precision solution for the workspace boundary. Finally, the workspace volume is used to analyze the influence of structural parameters on the workspace boundary. The results show that the lifting system has limited carrying capacity and a data reference for selecting the structural parameters by analyzing the factors that affect the workspace. Findings provide a basis for further studies on the structural configuration and optimization of the lifting system.

Motivated by practical applications of inspection and maintenance, we have developed a wall-climbing robot with passive compliant mechanisms that can autonomously adapt to curved surfaces. At first, this paper presents two failure modes of the traditional wall-climbing robot on the variable curvature wall surface and further introduces the designed passive compliant wall-climbing robot in detail. Then, the motion mechanism of the passive compliant wall-climbing robot on the curved surface is analyzed from stable adsorption conditions, parameter design process, and force analysis. At last, a series of experiments have been carried out on load capability and curved surface adaptability based on a developed principle prototype. The experimental results indicated that the wall-climbing robot with passive compliant mechanisms can effectively promote both adsorption stability and adaptability to variable curvatures.

Aimed at the challenges of wide-angle mobile robot visual perception for diverse field applications, we present the spherical robot visual system that uses a 360° field of view (FOV) for realizing real-time object detection. The spherical robot image acquisition system model is developed with optimal parameters, including camera spacing, camera axis angle, and the distance of the target image plane. Two 180$^{\circ}$-wide panoramic FOVs, front and rear view, are formed using four on-board cameras. The speed of the SURF algorithm is increased for feature extraction and matching. For seamless fusion of the images, an improved fade-in and fade-out algorithm is used, which not only improves the seam quality but also improves object detection performance. The speed of the dynamic image stitching is significantly enhanced by using a cache-based sequential image fusion method. On top of the acquired panoramic wide FOVs, the YOLO algorithm is used for real-time object detection. The panoramic visual system for the spherical robot is then tested in real time, which outputs panoramic views of the scene at an average frame rate of 21.69 fps and panoramic views with object detection at an average of 15.39 fps.