Robotics, Volume 13, Issue 1 (January 2024) – 19 articles

In this work, we present an analysis of, as well as driving strategies and design considerations for, a type of omnidirectional mobile robot: the offset-differential robot. This system presents omnidirectionality while using any type of standard wheel, allowing for applications in uneven and rough terrains, as well as cluttered environments. The known fact that these robots, as well as simple differential robots, have an unstable driving zone, has mostly been dealt with by designing driving strategies in the stable zone of internal dynamics. However, driving in the unstable zone may be advantageous when dealing with rough and uneven terrains. This work is based on the full kinematic and dynamic analysis of a robot, including its passive elements, to explain the unexpected behaviors that appear during its motion due to instability. Precise torque calculations taking into account the configuration of the passive elements were performed for better torque control, and design recommendations are included. The stable and unstable behaviors were characterized, and driving strategies were described in order to achieve the desired performance regarding precise positioning and speed. The model and driving strategies were validated through simulations and experimental testing. This work lays the foundation for the design of better control strategies for offset-differential robots. Full article

The control of deformable linear objects (DLOs) such as cables presents a significant challenge for robotic systems due to their unpredictable behavior during manipulation. This paper introduces a novel approach for cable shape control using dual robotic arms on a two–dimensional plane. A discrete point model is utilized for the cable, and a path generation algorithm is developed to define intermediate cable shapes, facilitating the transformation of the cable into the desired profile through a formulated optimization problem. The problem aims to minimize the discrepancy between the cable configuration and the targeted shape to ensure an accurate and stable deformation process. Moreover, a cable dynamic model is developed in which the manipulation approach is validated using this model. Additionally, the approach is tested in a simulation environment in which a framework of two manipulators grasps a cable. The results demonstrate the feasibility and accuracy of the proposed method, offering a promising direction for robotic manipulation of cables. Full article

Learning-based control systems have shown impressive empirical performance on challenging problems in all aspects of robot control and, in particular, in walking robots such as bipeds and quadrupeds. Unfortunately, these methods have a major critical drawback: a reduced lack of guarantees for safety and stability. In recent years, new techniques have emerged to obtain these guarantees thanks to data-driven methods that allow learning certificates together with control strategies. These techniques allow the user to verify the safety of a trained controller while providing supervision during training so that safety and stability requirements can directly influence the training process. This survey presents a comprehensive and up-to-date study of the evolving field of stability certification of neural controllers taking into account such certificates as Lyapunov functions and barrier functions. Although specific attention is paid to legged robots, several promising strategies for learning certificates, not yet applied to walking machines, are also reviewed. Full article

There has been a notable focus on the adoption of jamming-based technologies, which involve increasing the friction between grains, layers, or fibers to achieve variable stiffness capability in soft robots. Additionally, magnetorheological elastomers (MREs) that show magnetic-field-dependent viscoelasticity have great potential as a material for varying stiffness. This study proposes a hybrid method (magnetic jamming of MRE fibers) for enhancing the stiffness of soft robots, combining a jamming-based with a viscosity-based method. First, a fiber jamming structure is developed and integrated into a soft robot, the STIFF-FLOP manipulator, to prove the concept of the magnetic jamming of MRE fibers. Then, based on the proposed method, a variable stiffness device actuated by electro-permanent magnets is developed. The device is integrated into the same manipulator and the electronically controlled magnetic jamming and stiffening of the manipulator is demonstrated. The experimental results show that stiffness gain in bending and compression is achieved with the proposed method. The outcomes of this investigation demonstrate that the proposed hybrid stiffening technique presents a promising avenue for realizing variable and controllable stiffness in soft robots. Full article

Autonomous legged navigation in unstructured environments is still an open problem which requires the ability of an intelligent agent to detect and react to potential obstacles found in its area. These obstacles may range from vehicles, pedestrians, or immovable objects in a structured environment, like in highway or city navigation, to unpredictable static and dynamic obstacles in the case of navigating in an unstructured environment, such as a forest road. The latter scenario is usually more difficult to handle, due to the higher unpredictability. In this paper, we propose a vision dynamics approach to the path planning and navigation problem for a quadruped robot, which navigates in an unstructured environment, more specifically on a forest road. Our vision dynamics approach is based on a recurrent neural network that uses an RGB-D sensor as its source of data, constructing sequences of previous depth sensor observations and predicting future observations over a finite time span. We compare our approach with other state-of-the-art methods in obstacle-driven path planning algorithms and perform ablation studies to analyze the impact of architectural changes to our model components, demonstrating that our approach achieves superior performance in terms of successfully generating collision-free trajectories for the intelligent agent. Full article

In brain–machine interface (BMI) systems, the performance of trained Convolutional Neural Networks (CNNs) is significantly influenced by the quality of the training data. Another issue is the training time of CNNs. This paper introduces a novel approach by combining transfer learning and a Genetic Algorithm (GA) to optimize the training data of CNNs. Transfer learning is implemented across different subjects, and the data chosen by GA aim to improve CNN performance. In addition, the GA-selected data shed light on the similarity in brain activity between subjects. Two datasets are used: (1) the publicly available BCI Competition IV, in which the subjects performed motor imagery (MI) tasks, and (2) the dataset created by healthy subjects of our laboratory performing motor movement (MO) tasks. The experimental results indicate that the brain data selected by the GA improve the recognition accuracy of the target CNN (TCNN) using pre-trained base CNN (BCNN). The improvement in accuracy is 11% and 4% for the BCI Competition IV and our laboratory datasets, respectively. In addition, the GA-selected training data reduce the CNN training time. The performance of the trained CNN, utilizing transfer learning, is tested for real-time control of a robot manipulator. Full article

This paper presents a planar four-bar approximate motion synthesis technique that uses only pole locations. Synthesis for rigid-body guidance determines the linkage dimensions that guide a body in a desired manner. The desired motion is specified with task positions including a location and orientation angle. Approximation motion synthesis is necessary when an exact match to the task positions cannot be obtained. A linkage that achieves the task positions as closely as possible becomes desired. Structural error refers to the deviations between the task positions and the linkage’s generated positions. A challenge in approximate motion synthesis is that structural error involves metrics that include location and orientation. A best-fit solution is not evident because the structural error is based on an objective function that combines the location and orientation. Such solutions lack bi-invariance because a change in reference for the motion changes the values of the metric. This work uses only displacement poles, described solely by their coordinates, as they sufficiently characterize the relative task positions. The optimization seeks to minimize the distance between the poles of the task positions and the poles of the generated positions. The use of poles results in a bi-invariant statement of the problem. Full article

Machine learning (ML) is a branch of artificial intelligence that has been developing at a dynamic pace in recent years. ML is also linked with Big Data, which are huge datasets that need special tools and approaches to process them. ML algorithms make use of data to learn how to perform specific tasks or make appropriate decisions. This paper presents a comprehensive survey of recent ML approaches that have been applied to the task of mobile robot control, and they are divided into the following: supervised learning, unsupervised learning, and reinforcement learning. The distinction of ML methods applied to wheeled mobile robots and to walking robots is also presented in the paper. The strengths and weaknesses of the compared methods are formulated, and future prospects are proposed. The results of the carried out literature review enable one to state the ML methods that have been applied to different tasks, such as the following: position estimation, environment mapping, SLAM, terrain classification, obstacle avoidance, path following, learning to walk, and multirobot coordination. The survey allowed us to associate the most commonly used ML algorithms with mobile robotic tasks. There still exist many open questions and challenges such as the following: complex ML algorithms and limited computational resources on board a mobile robot; decision making and motion control in real time; the adaptability of the algorithms to changing environments; the acquisition of large volumes of valuable data; and the assurance of safety and reliability of a robot’s operation. The development of ML algorithms for nature-inspired walking robots also seems to be a challenging research issue as there exists a very limited amount of such solutions in the recent literature. Full article

This study aims to provide a comprehensive critical review of the existing body of evidence pertaining to gait rehabilitation. It also seeks to introduce a systematic approach for the development of innovative design solutions in this domain. The field of gait rehabilitation has witnessed a surge in the development of novel robotic devices. This trend has emerged in response to limitations observed in most commercial solutions, particularly regarding their high costs. Consequently, there is a growing need to explore more cost-effective alternatives and create opportunities for greater accessibility. Within the realm of cost-effective options, linkage-based gait trainers have emerged as viable alternatives, prompting a thorough examination of this category, which is carried out in this work. Notably, there is a wide heterogeneity in research approaches and presentation methods. This divergence has prompted discourse regarding the standardization of key elements relevant to the proposals of new linkage-based devices. As a result, this study proposes a comprehensive and standardized design process and offers a brief illustration of the application of this design process through the presentation of a potential new design. Full article

Robotic surgery involves significant task switching between tool control and camera control, which can be a source of distraction and error. This study evaluated the performance of a voice-enabled autonomous camera control system compared to a human-operated camera for the da Vinci surgical robot. Twenty subjects performed a series of tasks that required them to instruct the camera to move to specific locations to complete the tasks. The subjects performed the tasks (1) using an automated camera system that could be tailored based on keywords; and (2) directing a human camera operator using voice commands. The data were analyzed using task completion measures and the NASA Task Load Index (TLX) human performance metrics. The human-operated camera control method was able to outperform an automated algorithm in terms of task completion (6.96 vs. 7.71 correct insertions; p-value = 0.044). However, subjective feedback suggests that a voice-enabled autonomous camera control system is comparable to a human-operated camera control system. Based on the subjects’ feedback, thirteen out of the twenty subjects preferred the voice-enabled autonomous camera control system including the surgeon. This study is a step towards a more natural language interface for surgical robotics as these systems become better partners during surgery. Full article

This paper presents the design of a new lightweight, full-size bipedal robot developed in the Humanoid Robotics Laboratory at Nazarbayev University. The robot, equipped with 12 degrees of freedom (DOFs), stands at 1.1 m tall and weighs only 15 kg (excluding the battery). Through the implementation of a simple mechanical design and the utilization of off-the-shelf components, the overall prototype cost remained under USD 5000. The incorporation of high-performance in-house-developed servomotors enables the robot’s actuation system to generate up to 2400 W of mechanical power, resulting in a power-to-weight ratio of 160 W/kg. The details of the mechanical and electrical design are presented alongside the formalization of the forward kinematic model using the successive screw displacement method and the solution of the inverse kinematics. Tests conducted in both a simulation environment and on the real prototype demonstrate that the robot is capable of accurately following the reference joint trajectories to execute a quasi-static gait, achieving an average power consumption of 496 W. Full article

Robot manipulation in a physically constrained environment requires compliant manipulation. Compliant manipulation is a manipulation skill to adjust hand motion based on the force imposed by the environment. Recently, reinforcement learning (RL) has been applied to solve household operations involving compliant manipulation. However, previous RL methods have primarily focused on designing a policy for a specific operation that limits their applicability and requires separate training for every new operation. We propose a constraint-aware policy that is applicable to various unseen manipulations by grouping several manipulations together based on the type of physical constraint involved. The type of physical constraint determines the characteristic of the imposed force direction; thus, a generalized policy is trained in the environment and reward designed on the basis of this characteristic. This paper focuses on two types of physical constraints: prismatic and revolute joints. Experiments demonstrated that the same policy could successfully execute various compliant manipulation operations, both in the simulation and reality. We believe this study is the first step toward realizing a generalized household robot. Full article

This paper addresses a systematic method for odometry calibration of a differential-drive mobile robot moving on arbitrary paths in the presence of slippage and an algorithm encoding it which is well fit for online applications. It exploits the redundancy of sensors commonly available on ground mobile robots, such as encoders, gyroscopes, and IMU, to promptly detect slippage phenomena during the calibration process and effectively address their impact on odometry. The proposed technique has been validated through exhaustive numerical simulations and compared with other available odometry calibration methods. The simulation results confirm that the proposed methodology mitigates the impact of poor calibration, conducted without considering possible slipping phenomena, on reaching a target position, reducing the error by up to a maximum of 35 times. This restores the robot’s performance to a calibration condition close to that of a slip-free scenario, confirming the effectiveness of the approach and its robustness against slippage phenomena. Full article

Mobile robots have become increasingly important across various sectors and are now essential in agriculture due to their ability to navigate effectively and precisely in crop fields. Navigation involves the integration of several technologies, including robotics, control theory, computer vision, and artificial intelligence, among others. Challenges in robot navigation, particularly in agriculture, include mapping, localization, path planning, obstacle detection, and guiding control. Accurate mapping, localization, and obstacle detection are crucial for efficient navigation, while guiding the robotic system is essential to execute tasks accurately and for the safety of crops and the robot itself. Therefore, this study introduces a Guiding Manager for autonomous mobile robots specialized for laser-based weeding tools in agriculture. The focus is on the robot’s tracking, which combines a lateral controller, a spiral controller, and a linear speed controller to adjust to the different types of trajectories that are commonly followed in agricultural environments, such as straight lines and curves. The controllers have demonstrated their usefulness in different real work environments at different nominal speeds, validated on a tracked mobile platform with a width of about 1.48 m, in complex and varying field conditions including loose soil, stones, and humidity. The lateral controller presented an average absolute lateral error of approximately 0.076 m and an angular error of about 0.0418 rad, while the spiral controller presented an average absolute lateral error of about 0.12 m and an angular error of about 0.0103 rad, with a horizontal accuracy of about ±0.015 m and an angular accuracy of about ±0.009 rad, demonstrating its effectiveness in real farm tests. Full article

The strategies of multi-autonomous cooperative robots in a football game can be solved in multiple ways. Still, the most common is the “Skills, Tactics and Plays (STP)” architecture, developed so that robots could easily cooperate based on a group of predefined plays, called the playbook. The development of the new strategy algorithm presented in this paper, used by the RoboCup Middle Size League LAR@MSL team, had a completely different approach from most other teams for multiple reasons. Contrary to the typical STP architecture, this strategy, called the Probability-Based Strategy (PBS), uses only skills and decides the outcome of the tactics and plays in real-time based on the probability of arbitrary values given to the possible actions in each situation. The action probability values also affect the robot’s positioning in a way that optimizes the overall probability of scoring a goal. It uses a centralized decision-making strategy rather than the robot’s self-control. The robot is still fully autonomous in the skills assigned to it and uses a communication system with the main computer to synchronize all robots. Also, calibration or any strategy improvements are independent of the robots themselves. The robots’ performance affects the results but does not interfere with the strategy outcome. Moreover, the strategy outcome depends primarily on the opponent team and the probability calibration for each action. The strategy presented has been fully implemented on the team and tested in multiple scenarios, such as simulators, a controlled environment, against humans in a simulator, and in the RoboCup competition. Full article

Collaborative robotics represents a modern and efficient framework in which machines can safely interact with humans. Coupled with artificial intelligence (AI) systems, collaborative robots can solve problems that require a certain degree of intelligence not only in industry but also in the entertainment and educational fields. Board games like chess or checkers are a good example. When playing these games, a robotic system has to recognize the board and pieces and estimate their position in the robot reference frame, decide autonomously which is the best move to make (respecting the game rules), and physically execute it. In this paper, an intelligent and collaborative robotic system is presented to play Italian checkers. The system is able to acquire the game state using a camera, select the best move among all the possible ones through a decision-making algorithm, and physically manipulate the game pieces on the board, performing pick-and-place operations. Minimum-time trajectories are optimized online for each pick-and-place operation of the robot so as to make the game more fluent and interactive while meeting the kinematic constraints of the manipulator. The developed system is tested in a real-world setup using a Franka Emika arm with seven degrees of freedom. The experimental results demonstrate the feasibility and performance of the proposed approach. Full article

We explore multi-log grasping using reinforcement learning and virtual visual servoing for automated forwarding in a simulated environment. Automation of forest processes is a major challenge, and many techniques regarding robot control pose different challenges due to the unstructured and harsh outdoor environment. Grasping multiple logs involves various problems of dynamics and path planning, where understanding the interaction between the grapple, logs, terrain, and obstacles requires visual information. To address these challenges, we separate image segmentation from crane control and utilise a virtual camera to provide an image stream from reconstructed 3D data. We use Cartesian control to simplify domain transfer to real-world applications. Because log piles are static, visual servoing using a 3D reconstruction of the pile and its surroundings is equivalent to using real camera data until the point of grasping. This relaxes the limits on computational resources and time for the challenge of image segmentation, and allows for data collection in situations where the log piles are not occluded. The disadvantage is the lack of information during grasping. We demonstrate that this problem is manageable and present an agent that is 95% successful in picking one or several logs from challenging piles of 2–5 logs. Full article

In order to attain precise and robust transformation estimation in simultaneous localization and mapping (SLAM) tasks, the integration of multiple sensors has demonstrated effectiveness and significant potential in robotics applications. Our work emerges as a rapid tightly coupled LIDAR-inertial-visual SLAM system, comprising three tightly coupled components: the LIO module, the VIO module, and the loop closure detection module. The LIO module directly constructs raw scanning point increments into a point cloud map for matching. The VIO component performs image alignment by aligning the observed points and the loop closure detection module imparts real-time cumulative error correction through factor graph optimization using the iSAM2 optimizer. The three components are integrated via an error state iterative Kalman filter (ESIKF). To alleviate computational efforts in loop closure detection, a coarse-to-fine point cloud matching approach is employed, leverging Quatro for deriving a priori state for keyframe point clouds and NanoGICP for detailed transformation computation. Experimental evaluations conducted on both open and private datasets substantiate the superior performance of the proposed method compared to similar approaches. The results indicate the adaptability of this method to various challenging situations. Full article

Predicting the trajectory of other road users, especially vulnerable road users (VRUs), is an important aspect of safety and planning efficiency for autonomous vehicles. With recent advances in Deep-Learning-based approaches in this field, physics- and classical Machine-Learning-based methods cannot exhibit competitive results compared to the former. Hence, this paper provides an extensive review of recent Deep-Learning-based methods in trajectory prediction for VRUs and autonomous driving in general. We review the state and context representations and architectural insights of selected methods, divided into categories according to their primary prediction scheme. Additionally, we summarize reported results on popular datasets for all methods presented in this review. The results show that conditional variational autoencoders achieve the best overall results on both pedestrian and autonomous driving datasets. Finally, we outline possible future research directions for the field of trajectory prediction in autonomous driving. Full article