As space missions are needed in the future, the assembly volume of the space truss will become larger and larger, and the advancing path of the on-orbit cellular robot to the mission target will become more and more complicated. If the shortest moving path cannot be found in the truss environment, the climbing time of the robot on the truss will be greatly increased. To improve the speed of the cellular robot moving to the target point on the large space truss, this paper designs a cellular robot structure and configuration suitable for climbing on the truss and uses the improved sparrow algorithm to solve the problem of robot motion path planning. By establishing a mathematical model of the space truss, the improved sparrow algorithm is used to find the shortest path between the starting point and the end point in the truss environment. Finally, the data of this algorithm are compared with the data of other algorithms. The data results show that the improved sparrow algorithm is very effective in solving the optimal path of the space truss. The improved sparrow algorithm keeps the same optimal path compared with the standard sparrow algorithm, and the overall reaction time is increased by 51.60%, and the number of effective iterations is increased by about 13.87%.

The rise in the number of automated robotic kitchens accelerated the need for advanced food handling system, emphasizing food analysis including ingredient classification pose recognition and assembling strategy. Selecting the optimal piece from a pile of similarly shaped food items is a challenge to automated meal assembling system. To address this, we present a constructive assembling algorithm, introducing a unique approach for food pose detection–Fast Image to Pose Detection (FI2PD), and a closed-loop packing strategy. Powered by a convolutional neural network (CNN) and a pose retrieval model, FI2PD is adept at constructing a 6D pose from only RGB images. The method employs a coarse-to-fine approach, leveraging the CNN to pinpoint object orientation and position, alongside a pose retrieval process for target selection and 6D pose derivation. Our closed-loop packing strategy, aided by the Item Arrangement Verifier, ensures precise arrangement and system robustness. Additionally, we introduce our FdIngred328 dataset of nine food categories ranging from fake foods to real foods, and the automatically generated data based on synthetic techniques. The performance of our method for object recognition and pose detection has been demonstrated to achieve a success rate of 97.9%. Impressively, the integration of a closed-loop strategy into our meal-assembly process resulted in a notable success rate of 90%, outperforming the results of systems lacking the closed-loop mechanism.

In this study, a novel kinematic modeling method of parallel mechanism is proposed. It can obtain position and posture space simultaneously in a single model. Compared with the traditional method only based on inverse kinematics, the novel method can significantly improve computational performance. The original evaluation metric $\mathfrak{R}$ is proposed to evaluate the performance of the two modeling methods. Three groups of experiments with different calculation times are carried out for the classical PPU-3RUS parallel mechanism, and the new RS-3UPRU parallel mechanism after the effectiveness and wide applicability of the novel modeling method is proved. The calculation time and output rate are recorded, respectively, and then the respective $\mathfrak{R}$ values are obtained by weighting. The results show that the novel modeling method has better performance.

Energy efficiency is inherent for autonomous robotic device. Snakes are well known for their ability to low energy consumption when swimming. However, the swimming know-how is poorly understood. Designing a snake robot inspired by snakes as a tool to find out the swimming energy efficiency crucial point will lead to the development of hyper efficient undulating locomotors. In this article, we introduce a four tendons driven continuum robot made of bio-inspired compliant vertebrae to assess the energy consumption of a planar and a spatial snake motion. The tendon-driven continuum robot constitutes the head–neck part of a locomotor snake robot. A static modeling coupled with an optimization method was implemented to generate bio-inspired motions recorded on snake swimming head. A friction model describing the friction between cables and the disks is investigated and compared to a frictionless model. The proposed prototype is equipped with exteroceptive sensors to record motion and proprioceptive sensors to measure cable forces applied at the tip of the robot. Hence, the work of the forces, thus the energy required to execute a trajectory are computed and analyzed. The energy is introduced as a key criterion to assess the swimming motion of a locomotor snake robot.

Performing tasks in agriculture, such as fruit monitoring or harvesting, requires perceiving the objects’ spatial position. RGB-D cameras are limited under open-field environments due to lightning interferences. So, in this study, we state to answer the research question: “How can we use and control monocular sensors to perceive objects’ position in the 3D task space?” Towards this aim, we approached histogram filters (Bayesian discrete filters) to estimate the position of tomatoes in the tomato plant through the algorithm MonoVisual3DFilter. Two kernel filters were studied: the square kernel and the Gaussian kernel. The implemented algorithm was essayed in simulation, with and without Gaussian noise and random noise, and in a testbed at laboratory conditions. The algorithm reported a mean absolute error lower than 10 mm in simulation and 20 mm in the testbed at laboratory conditions with an assessing distance of about 0.5 m. So, the results are viable for real environments and should be improved at closer distances.

Bayesian inference provides a probabilistic reasoning process for drawing conclusions based on imprecise and uncertain data that has been successful in many applications within robotics and information processing, but is most often considered in terms of data analysis rather than synthesis of behaviours. This paper presents the use of Bayesian inference as a means by which to perform Boolean operations in a logic programme while incorporating and propagating uncertainty information through logic operations by inference. Boolean logic operations are implemented in a Bayesian network of Bernoulli random variables with tensor-based discrete distributions to enable probabilistic hybrid logic programming of a robot. This enables Bayesian inference operations to coexist with Boolean logic in a unified system while retaining the ability to capture uncertainty by means of discrete probability distributions. Using a discrete Bayesian network with both Boolean and Bayesian elements, the proposed methodology is applied to navigate a mobile robot using hybrid Bayesian and Boolean operations to illustrate how this new approach improves robotic performance by inclusion of uncertainty without increasing the number of logic elements required. As any logical system could be programmed in this manner to integrate uncertainty into decision-making, this methodology can benefit a wide range of applications that use discrete or probabilistic logic.

The loading and unloading operations of smart logistic application robots depend largely on their perception system. However, there is a paucity of study on the evaluation of Lidar maps and their SLAM algorithms in complex environment navigation system. In the proposed work, the Lidar information is finetuned using binary occupancy grid approach and implemented Improved Self-Adaptive Learning Particle Swarm Optimization (ISALPSO) algorithm for path prediction. The approach makes use of 2D Lidar mapping to determine the most efficient route for a mobile robot in logistical applications. The Hector SLAM method is used in the Robot Operating System (ROS) platform to implement mobile robot real-time location and map building, which is subsequently transformed into a binary occupancy grid. To show the path navigation findings of the proposed methodologies, a navigational model has been created in the MATLAB 2D virtual environment using 2D Lidar mapping point data. The ISALPSO algorithm adapts its parameters inertia weight, acceleration coefficients, learning coefficients, mutation factor, and swarm size, based on the performance of the generated path. In comparison to the other five PSO variants, the ISALPSO algorithm has a considerably shorter path, a quick convergence rate, and requires less time to compute the distance between the locations of transporting and unloading environments, based on the simulation results that was generated and its validation using a 2D Lidar environment. The efficiency and effectiveness of path planning for mobile robots in logistic applications are validated using Quanser hardware interfaced with 2D Lidar and operated in environment 3 using proposed algorithm for production of optimal path.

Currently, most wheel-legged robots need to complete the switching of the wheel-and-leg modal in a stationary state, and the existing algorithms of statically switching the wheel-leg modal cannot meet the control requirements of multimodal switching dynamically for robots. In this paper, to achieve efficient switching of the wheel-and-leg modal for a quadruped robot, the novel transformable mechanism is designed. Then, a multimodal coordination operation control framework based on multiple algorithms is presented, incorporating the minimum foot force distribution method (algorithm No.1), the minimum joint torque distribution method (algorithm No.2), and the method of combining the single rigid body dynamic model with quadratic programming (algorithm No.3). In the process of switching wheel-leg modal dynamically, the existing algorithm No.3 is prone to produce the wrong optimal force due to the change of the whole-body rotational inertia. Therefore, an improved algorithm No.1 and algorithm No.2 are proposed, which do not consider the change in the body’s inertia. The control effects of the three algorithms are compared and analyzed by simulation. The results show that algorithm No.3 can maintain a small error in attitude angle and speed tracking regardless of whether the robot is under multilegged support or omnidirectional walking compared to the other two algorithms. However, proposed algorithms No.1 and No.2 can more accurately track the target speed when the robot is walking with wheels raising and falling. Finally, a multi-algorithm combination control scheme formulated based on the above control effects has been demonstrated to be effective for the dynamic switching of the wheel-and-leg modal.

Natural calamities are affecting many parts of the world. Natural disasters, terrorist attacks, earthquakes, wildfires, floods and all unpredicted phenomena. Disasters cause emergency conditions, so imperative to coordinate the prompt delivery of essential services to the sufferers. Often, disasters lead many people to perish by becoming trapped inside, but many more also perish as a result of individuals receiving rescue either too late or not at all. The implementation and design of a Receiver module utilizing Davinci code processor DVM6437, Wireless camera receiver, Zigbee Transceiver and Global Positioning System (GPS) is proposed in this manuscript for Wireless Vision-based Semi-Autonomous rescue robots that are employed in rough terrain. The receiver side’s Zigbee transceiver module eliminates the limitations of tele-operating rescue robots by enabling the control station to receive GPS data signals and aids in robot management by sending control signals wirelessly. Half and full-duplex communication are supported by the Davinci processor DVM6437, a digital media fixed-point DSP processor that relies on Very Long Instruction Words. It includes an extensive instruction set that is ideal for real-time salvage operations. DVM processor is coded utilizing MATLAB Simulink. MATLAB codes and Simulink blocks are employed under Embedded IDE link.

This study introduces a hybrid model that utilizes a model-based optimization method to generate training data and an artificial neural network (ANN)-based learning method to offer real-time exoskeleton support in lifting activities. For the model-based optimization method, the torque of the knee exoskeleton and the optimal lifting motion are predicted utilizing a two-dimensional (2D) human–exoskeleton model. The control points for exoskeleton motor current profiles and human joint angle profiles from cubic B-spline interpolation represent the design variables. Minimizing the square of the normalized human joint torque is considered as the cost function. Subsequently, the lifting optimization problem is tackled using a sequential quadratic programming (SQP) algorithm in sparse nonlinear optimizer (SNOPT). For the learning-based approach, the learning-based control model is trained using the general regression neural network (GRNN). The anthropometric parameters of the human subjects and lifting boundary postures are used as input parameters, while the control points for exoskeleton torque are treated as output parameters. Once trained, the learning-based control model can provide exoskeleton assistive torque in real time for lifting tasks. Two test subjects’ joint angles and ground reaction forces (GRFs) comparisons are presented between the experimental and simulation results. Furthermore, the utilization of exoskeletons significantly reduces activations of the four knee extensor and flexor muscles compared to lifting without the exoskeletons for both subjects. Overall, the learning-based control method can generate assistive torque profiles in real time and faster than the model-based optimal control approach.

We design a scheme for laser-inertial odometry and mapping with bundle adjustment (BA-LIOM), which can greatly mitigate the problem of undesired ground warping due to sparsity of laser scans and significantly reduce odometry drift. Specifically, an Inertial measurement unit (IMU)-assisted adaptive voxel map initialization algorithm is proposed and elaborately integrated with the existing framework LIO-SAM, allowing for accurate registration in the beginning of the localization and mapping process. In addition, to accommodate to fast-moving and structure-less scenarios, we design a tightly coupled odometry, which jointly optimizes both the IMU preintegration constraints and scan matching with adaptive voxel maps. The voxels (edge and plane, respectively) are updated with BA optimization. And then the accurate mapping result is obtained by performing local BA. The proposed BA-LIOM is thoroughly assessed using datasets collected from multiple platforms over a variety of environments. Experimental results show the superiority of BA-LIOM over the state-of-the-art methods in robustness and precision, especially for large-scale scenarios. BA-LIOM improves the accuracy of localization by $61\%$ and $73\%$ on the buildings and lawn datasets, respectively, and has a $29\%$ accuracy improvement over LIO-SAM on the KITTI datasets. A supplementary video can be accessed at https://youtu.be/5l4ZFhTc2sw.

At present, the research of soft crawling robot pays more attention to the material manufacturing, but neglects the robot modeling. The high degree of freedom of the soft crawling robot makes it more difficult to establish its motion model and analyzes its motion performance. The centimeter-level wireless driven soft crawling robot has great advantages and application scenarios in narrow space exploration. Therefore, this paper proposed a soft robot driven by magnetism to crawling inchworm. By studying the crawling behavior of inchworm and the characteristics of flexible materials driven by magnetism, the structure of the soft robot was designed and the motion model of inchworm was established. The motion model is analyzed and simulated, the structure size of the robot is optimized, and the effectiveness of the model is verified by experiments. The robot’s crawling motion is realized by coupling the structure of the robot’s torso and legs with the flexible magnetic film. Driven by the alternating magnetic field, the maximum motion speed of the robot is 28.24 mm/s. At the same time, the robot can also move in narrow space such as pipes, which can satisfy the centimeter-level space detection and ensure the high efficiency, providing a new idea for narrow space detection.

In this paper, we consider the problem of contact parameters (slippage and sinkage) estimation for multi-modal robot locomotion on granular terrains. To describe the contact events in the same framework for robots operated at different modes (e.g., wheel, leg), we propose a unified description of contact parameters for multi-modal robots. We also provide a parameter estimation method for multi-modal robots based on CNN and DWT (discrete wavelet transformation) techniques and verify its effectiveness over different types of granular terrains. Besides motion modes, this paper also considers the influence of slope angles and the robot’s handing angles over contact parameters. Through comparison and analysis of the prediction results, our method can not only effectively predict the contact parameters of multi-modal robot locomotion on a granular medium (better than $96\%$ accuracy) but also achieves the same or better performance when compared to other (direct) contact measurement methods designed for individual motion modes, that is, single-modal robots such as quadruped robots and mars rovers. Our proposed unified contact parameter estimation method can be useful for studying the interaction mechanics between multi-modal robots and granular terrains as well as terrain classification tasks due to its superior sensitivity which is analyzed in the experiments.

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.

Coverage path planning (CPP) is a subfield of path planning problems in which free areas of a given domain must be visited by a robot at least once while avoiding obstacles. In some situations, the path may be optimized for one or more criteria such as total distance traveled, number of turns, and total area covered by the robot. Accordingly, the CPP problem has been formulated as a multi-objective optimization (MOO) problem, which turns out to be a challenging discrete optimization problem, hence conventional MOO algorithms like Non-dominated Sorting Genetic Algorithm-2 (NSGA-II) do not work as it is. This study implements a modified NSGA-II to solve the MOO problem of CPP for a mobile robot. In this paper, the proposed method adopted two objective functions: (1) the total distance traveled by the robot and (2) the number of turns taken by the robot. The two objective functions are used to calculate energy consumption. The proposed method is compared to the hybrid genetic algorithm (HGA) and the traditional genetic algorithm (TGA) in a rectilinear environment containing obstacles of various complex shapes. In addition, the results of the proposed algorithm are compared to those generated by HGA, TGA, oriented rectilinear decomposition, and spatial cell diffusion and family of spanning tree coverage in existing research papers. The results of all comparisons indicate that the proposed algorithm outperformed the existing algorithms by reducing energy consumption by 5 to 60%. This paper provides the facility to operate the robot in different modes.

The ability of quadruped robots to overcome obstacles is a critical factor that limits their practical application. Here, a design concept and a control algorithm are presented that aim at enhancing the explosive force of quadruped robots during jumping by utilizing elastic energy storage components. The hind legs of the quadruped robot are designed as energy storage units. Tension springs are utilized as components for storing energy and are installed in a parallel structure on the hind leg. Energy is stored during the compression process of the robot’s torso and released during the jumping phase. The optimal foot force is calculated using a single rigid body model. The mapping relationship between the force applied to the foot and the resulting joint torque is established by developing a dynamic model of the hind legs. Simulation experiments were conducted using the Webots physics engine to compare the impact of varying spring stiffness on joint torque during the jumping process. This study determined the optimal spring stiffness under specific conditions. The hind legs’ torque saving ratio reaches 19%, and the energy-saving ratio reaches 13%, which validates the effectiveness and feasibility of integrating elastic energy storage components.

Human gait trajectory prediction is a long-standing research topic in human–machine interaction. However, there are two shortcomings in the current gait trajectory prediction technology. The first shortcoming is that the neural network model of gait prediction only predicts dozens of future time frames of gait trajectory. The second shortcoming is that the gait prediction neural network model is uninterpretable. We propose the Interpretable-Concatenation former (IC-former) model, which can predict long-term gait trajectories and explain the prediction results by quantifying the importance of data at different positions in the input sequence. Experiments prove that the IC-former model we proposed not only makes a breakthrough in prediction accuracy but also successfully explains the data basis of the prediction.

This paper explores and experimentally compares the effectiveness of robot-stopping approaches based on the speed and separation monitoring for improving fluency in collaborative robotics. In the compared approaches, a supervisory controller checks the distance between the bounding volumes enclosing human operator and robot and prevents potential collisions by determining the robot’s stop time and triggering a stop trajectory if necessary. The methods are tested on a Franka Emika robot with 7 degrees of freedom, involving 27 volunteer participants, who are asked to walk along assigned paths to cyclically intrude the robot workspace, while the manipulator is working. The experimental results show that scaling online the dynamic safety zones is beneficial for improving fluency of human-robot collaboration, showing significant statistical differences with respect to alternative approaches.

With the rise of deep reinforcement learning (RL) methods, many complex robotic manipulation tasks are being solved. However, harnessing the full power of deep learning requires large datasets. Online RL does not suit itself readily into this paradigm due to costly and time-consuming agent-environment interaction. Therefore, many offline RL algorithms have recently been proposed to learn robotic tasks. But mainly, all such methods focus on a single-task or multitask learning, which requires retraining whenever we need to learn a new task. Continuously learning tasks without forgetting previous knowledge combined with the power of offline deep RL would allow us to scale the number of tasks by adding them one after another. This paper investigates the effectiveness of regularisation-based methods like synaptic intelligence for sequentially learning image-based robotic manipulation tasks in an offline-RL setup. We evaluate the performance of this combined framework against common challenges of sequential learning: catastrophic forgetting and forward knowledge transfer. We performed experiments with different task combinations to analyse the effect of task ordering. We also investigated the effect of the number of object configurations and the density of robot trajectories. We found that learning tasks sequentially helps in the retention of knowledge from previous tasks, thereby reducing the time required to learn a new task. Regularisation-based approaches for continuous learning, like the synaptic intelligence method, help mitigate catastrophic forgetting but have shown only limited transfer of knowledge from previous tasks.