Robot Motion Control Research Articles

Multi-mode filter target tracking method for mobile robot using multi-agent reinforcement learning

Multi-mode filtering target tracking for mobile robot has important research significance for robot path planning, motion control and tracking robot targets. To address the problem that it is difficult for mobile robot to track targets in unknown environments, a multi-mode filtering target tracking method for mobile robot using multi-agent reinforcement learning is proposed. First, based on the extended kalman filter and combined with probability data association, the observation values in different motion modes are calculated and the system state is updated in real time, to achieve concurrent mapping, location and state estimation for each robot. Second, state communication among multi-mobile robot are established, and the multi-agent reinforcement learning model is built. Finally, based on the agent reinforcement learning model, based on the communication and communication among multi-tracking agents and the location of the target agent, the target tracking task is allocated to shorten the total path of the tracking agent, and the multi-target tracking of multi-mobile robot is completed by constantly learning and updating the strategy. The results show that the maximum tracking error of the target is 7 mm, and the calculation time of each step is only 51.1ms. The tracking success rate, observation rate and coverage rate are all high. It has important research value in robot location and navigation, service robot and other fields.

Trajectory Tracking and Obstacle Avoidance of Robotic Fish Based on Nonlinear Model Predictive Control.

The attainment of accurate motion control for robotic fish inside intricate underwater environments continues to be a substantial obstacle within the realm of underwater robotics. This paper presents a proposed algorithm for trajectory tracking and obstacle avoidance planning in robotic fish, utilizing nonlinear model predictive control (NMPC). This methodology facilitates the implementation of optimization-based control in real-time, utilizing the present state and environmental data to effectively regulate the movements of the robotic fish with a high degree of agility. To begin with, a dynamic model of the robotic fish, incorporating accelerations, is formulated inside the framework of the world coordinate system. The last step involves providing a detailed explanation of the NMPC algorithm and developing obstacle avoidance and objective functions for the fish in water. This will enable the design of an NMPC controller that incorporates control restrictions. In order to assess the efficacy of the proposed approach, a comparative analysis is conducted between the NMPC algorithm and the pure pursuit (PP) algorithm in terms of trajectory tracking. This comparison serves to affirm the accuracy of the NMPC algorithm in effectively tracking trajectories. Moreover, a comparative analysis between the NMPC algorithm and the dynamic window approach (DWA) method in the context of obstacle avoidance planning highlights the superior resilience of the NMPC algorithm in this domain. The proposed strategy, which utilizes NMPC, demonstrates a viable alternative for achieving precise trajectory tracking and efficient obstacle avoidance planning in the context of robotic fish motion control within intricate surroundings. This method exhibits considerable potential for practical implementation and future application.

The Parallel Solving Method of Robot Kinematic Equations Based on FPGA

In the implementation of robot motion control, complex kinematic computations consume too much central processing unit (CPU) time and affect the responsiveness of robot motion. To solve this problem, this paper proposes a parallel method for solving kinematic equations of articulated robots based on the coordinate rotation digital computer (CORDIC) algorithm. The method completes the fast calculation of the transcendental function based on the CORDIC algorithm, adopts the tree structure method to optimize the key computational paths of forward and inverse solutions, and designs a parallel pipeline to realize the low latency and high throughput of the kinematic equations. The experiments of the proposed method are validated based on the field-programmable gate array (FPGA) hardware experimental platform, and the experimental results demonstrate that the computational time to complete the entire kinematic equations is 4.68 μs, of which the computational time for the kinematic positive solution is 0.52 μs and the computational time for the kinematic inverse solution is 4.16 μs.

Safe Machine-Learning-Supported Model Predictive Force and Motion Control in Robotics

Many robotic tasks, such as human-robot interactions or the handling of fragile objects, require tight control and limitation of appearing forces and moments alongside sensible motion control to achieve safe yet high-performance operation. We propose a learning-supported model predictive force and motion control scheme that provides stochastic safety guarantees while adapting to changing situations. Gaussian processes (GPs) are used to learn the uncertain relations that map the robot’s states to the forces and moments. The model predictive controller uses these Gaussian process models to achieve precise motion and force control under stochastic constraint satisfaction. As the uncertainty only occurs in the static model parts — the output equations — a computationally efficient stochastic MPC formulation is used. analysis of recursive feasibility of the optimal control problem and convergence of the closed loop system for the static uncertainty case are given. Chance constraint formulation and back-offs are constructed based on the variance of the Gaussian process to guarantee safe operation. The approach is illustrated on a lightweight robot in simulations and experiments.

Learning for Depth Control of a Robotic Penguin: A Data-Driven Model Predictive Control Approach

For bionic underwater robots, it is a great challenge for depth control due to model uncertainty and strong nonlinearity. To this end, we propose a data-driven model predictive control (MPC) approach using reinforcement learning (RL) for robotic penguin depth control. First, by imitating the underwater mode of the biological penguin, a robotic prototype with a tendon-driven head, two degrees of freedom wings, and a tendon-driven tail was designed. Then, a data-driven MPC framework is proposed considering the structure and motion properties of the robotic penguin. Specially, a data-based learning environment is constructed using a motion capture system, computational fluid dynamics, and a back-propagation neural network. Meanwhile, to maximize the benefits of the controller while ensuring safety and stability, a data-driven MPC using the RL scheme is applied to approximate the optimal policy. Combined with an appropriate reward design and periodic training, the closed-loop controller performance is significantly improved, and the validity of the proposed framework is finally tested by extensive simulations and experiments. Notably, this work will provide valuable insights into the learning-based motion control of bionic underwater robots.

An Improved Performance of the Designed Robotic Motion Control for NAO Robot Arms Using Hybrid Neural Network-Jacobian

An Improved Performance of the Designed Robotic Motion Control for NAO Robot Arms Using Hybrid Neural Network-Jacobian

Design of an optimized gait planning generator for a quadruped robot using the decision tree and random forest workspace model

AbstractReal-time gait trajectory planning is challenging for legged robots walking on unknown terrain. In this paper, to realize a more efficient and faster motion control of a quadrupedal robot, we propose an optimized gait planning generator (GPG) based on the decision tree (DT) and random forest (RF) model of the robot leg workspace. First, the framework of this embedded GPG and some of the modules associated with it are illustrated. Aiming at the leg workspace model described by DT and RF used in GPG, this paper introduces in detail how to collect the original data needed for training the model and puts forward an Interpolation Labeling with Dilation and Erosion (ILDE) data processing algorithm. After the DT and RF models are trained, we preliminarily evaluate their performance. We then present how these models can be used to predict the location relation between a spatial point and the leg workspace based on its distributional features. The DT model takes only 0.00011 s to process a sample, while the RF model can give the prediction probability. As a complement, the PID inverse kinematic model used in GPG is also mentioned. Finally, the optimized GPG is tested during a real-time single-leg trajectory planning experiment and an unknown terrain recognition simulation of a virtual quadrupedal robot. According to the test results, the GPG shows a remarkable rapidity for processing large-scale data in the gait trajectory planning tasks, and the results can prove it has an application value for quadruped robot control.

Research on Motion Control and Wafer-Centering Algorithm of Wafer-Handling Robot in Semiconductor Manufacturing.

This paper studies the AWC (Active Wafer Centering) algorithm for the movement control and wafer calibration of the handling robot in semiconductor manufacturing to prevent wafer surface contact and contamination during the transfer process. The mechanical and software architecture of the wafer-handling robot is analyzed first, which is followed by a description of the experimental platform for semiconductor manufacturing methods. Secondly, the article utilizes the geometric method to analyze the kinematics of the semiconductor robot, and it decouples the motion control of the robot body from the polar coordinates and joint space. The wafer center position is calibrated using the generalized least-square inverse method for AWC correction. The AWC algorithm is divided into calibration, deviation correction, and retraction detection. These are determined by analyzing the robot's wafer calibration process. In conclusion, the semiconductor robot's motion control and AWC algorithm are verified through experiments for correctness, feasibility, and effectiveness. After the wafer correction, the precision of AWC is <± 0.15 mm, which meets the requirements for transferring robot wafers.

Task-oriented safety field for robot control in human-robot collaborative assembly based on residual learning

With the development of smart manufacturing, human-robot collaboration (HRC) is seen as the future of manufacturing. In a manufacturing environment with HRC, safety has been raising significant attention since the conventional separation of workspaces between robots and humans is removed. In this paper, a dynamic safety field is constructed that takes into account the collaborative assembly task requirements and the motions of both humans and robots. This safety field guides robot actions, ensuring that the robot carries out the required tasks while maintaining a safe distance from human workers. Based on the task requirements and safety considerations between humans and robots, a robot motion planning and control problem is formulated. To solve this problem, a hybrid RRL control scheme is proposed where a residual reinforcement learning (RRL) method is developed to combine the safety field-based control method with a deep reinforcement learning (DRL) method. Numerical studies are conducted to evaluate the performance of the proposed, which is compared with a pure deep Q-network (DQN) based method and a rapidly exploring random tree (RRT) method. The simulation results show that the proposed method can effectively optimize robot trajectories and outperforms the DQN-based and the RRT method in terms of computational efficiency.

Calibration Considering the Direction of Rotation for Contact Type Three-Dimensional Position-Measuring Instruments

In Japan, the aging of sewage facilities due to long-term use has become a significant social issue. As a result, there has been a growing interest in portable and easy-to-operate standalone pipe inspection robots in recent years. However, the pipes being inspected not only have level differences due to joint connections but also pose a high risk of toppling over due to deterioration, collapses, and sludge caused by external disturbances. Many standalone robots address this by suppressing tipping through tire shape and axle adjustments. However, this method is for suppression and not complete prevention. Therefore, we are exploring a software-based approach to prevent tipping through control of robot movement and aiming to achieve advanced self-position estimation. Currently, we are in the stage of verifying this self-position estimation. However, due to the curved nature of the pipes, it is difficult to accurately measure the robot's position and orientation using conventional measurement instruments. Thus, we have developed a specialized three-dimensional position measurement instrument for pipe inspection robots. Furthermore, although we performed calibration in the translational direction of the instrument, while improvements in accuracy were observed in the translational direction, the accuracy in the rotational direction deteriorated. In this paper, we propose a method to simultaneously calibrate the translational and rotational accuracy of the instrument to address this issue. We discuss the mechanism model, calibration parameters, elimination of redundant parameters by introducing redundancy, and parameter estimation using the Newton method. Additionally, through comparative validation using the instrument, we confirm that the position accuracy after calibration is within the range of approximately ±1.0 mm, and the orientation accuracy is within the range of approximately ±0.3 degrees. This demonstrates the effectiveness of the proposed method.

Model-based variable impedance learning control for robotic manipulation

The capability to adapt compliance by varying muscle stiffness is crucial for dexterous manipulation skills in humans. Incorporating compliance in robot motor control is crucial for enabling real-world force interaction tasks with human-like dexterity. In this study, we introduce a novel approach, we call “deep Model Predictive Variable Impedance Controller (MPVIC)” for compliant robotic manipulation, which combines Variable Impedance Control with Model Predictive Control (MPC). The method involves learning a generalized Cartesian impedance model of a robot manipulator through an exploration strategy to maximize information gain. Within the MPC framework, this learned model is utilized to adapt the impedance parameters of a low-level variable impedance controller, thereby achieving the desired compliance behavior for various manipulation tasks without requiring retraining or finetuning. We assess the efficacy of the proposed deep MPVIC approach using a Franka Emika Panda robotic manipulator in simulations and real-world experiments involving diverse manipulation tasks. Comparative evaluations against model-free and model-based reinforcement learning approaches in variable impedance control are conducted, considering aspects such as transferability between tasks and performance. The results demonstrate the effectiveness and potential of the presented approach for advancing robotic manipulation capabilities.

An Analytical Method for Sensitivity Analysis of Rigid Multibody System Dynamics Using Projective Geometric Algebra

Abstract The analytical sensitivity analysis, i.e., the analytical first-order partial derivatives of dynamical equations, is one key to improving descent-based optimization methods for motion planning and control of robots. This paper proposes an efficient algorithm that recursively evaluates the analytic gradient of the dynamical equations of a multibody system. The theory of projective geometric algebra (PGA) is used to generate the algorithm. It provides a systemic and geometrically intuitive interpretation for the multibody system dynamics, and the resulting algorithm is highly efficient, with concise formula. The algorithm is first applied to the open-chain system and extended for the cases when kinematic loops are contained. The runtime varying with respect to the degree-of-freedom (DOF) of the system is analyzed. The results are compared with that obtained from the algorithm based on spatial vector algebra (SVA) using open-source matlab codes. A 2DOF serial robot, a 3DOF robot with a kinematic loop and the PUMA560 robot are used for the validation of the minimum-effort motion planning, and it is verified that the proposed algorithm improves the efficiency.

Application of reinforcement learning algorithm on robot motion control and navigation in webots simulator

Covid-19 has changed people’s way of life since its outbreak in December 2019. The transmission of the virus mainly relies on droplets or aerosols produced by infected people while they breathe, talk, cough or sneeze. The infection can occur over a long distance, especially indoors. To reduce connectivity between the people indoors such as in restaurants, the application of robots for food delivery may be one of the solutions. In this research, a reinforcement learning algorithm is applied to the motion control and navigation of a robot which can be modified into a robot food runner to maintain social distances in restaurants. In this project, we test the algorithm’s ability to explore the environment and find a suitable path to the target point through learning by comparing its trajectories to the shortest theoretical path. The results obtained through the simulation on Webots show that the algorithm works well to find a destination from a randomly selected starting point even though a random obstacle is presented. However, still it has great potential to be extended to a continuous environment.

Applying an Artificial Neuromolecular System to the Application of Robotic Arm Motion Control in Assisting the Rehabilitation of Stroke Patients-An Artificial World Approach.

Stroke patients cannot use their hands as freely as usual. However, recovery after a stroke is a long road for many patients. If artificial intelligence can assist human arm movement, it is believed that the possibility of stroke patients returning to normal hand movement can be significantly increased. In this study, the artificial neuromolecular system (ANM system) developed by our laboratory is used as the core motion control system to learn to control the mechanical arm, produce similar human rehabilitation actions, and assist patients in transiting between different activities. The strength of the ANM system lies in its ability to capture and process spatiotemporal information by exploiting the dynamic information processing inside neurons. Five experiments are conducted in this research: continuous learning, dimensionality reduction, moving problem domains, transfer learning, and fault tolerance. The results show that the ANM system can find out the arm movement trajectory when people perform different rehabilitation actions through the ability of continuous learning and reduce the activation of multiple muscle groups in stroke patients through the learning method of reducing dimensions. Finally, using the ANM system can reduce the learning time and performance required to switch between different actions through transfer learning.

A Hierarchical Framework for Quadruped Robots Gait Planning Based on DDPG.

In recent years, significant progress has been made in employing reinforcement learning for controlling legged robots. However, a major challenge arises with quadruped robots due to their continuous states and vast action space, making optimal control using simple reinforcement learning controllers particularly challenging. This paper introduces a hierarchical reinforcement learning framework based on the Deep Deterministic Policy Gradient (DDPG) algorithm to achieve optimal motion control for quadruped robots. The framework consists of a high-level planner responsible for generating ideal motion parameters, a low-level controller using model predictive control (MPC), and a trajectory generator. The agents within the high-level planner are trained to provide the ideal motion parameters for the low-level controller. The low-level controller uses MPC and PD controllers to generate the foot-end force and calculates the joint motor torque through inverse kinematics. The simulation results show that the motion performance of the trained hierarchical framework is superior to that obtained using only the DDPG method.

Modeling and Simulation of Dynamics in Soft Robotics: a Review of Numerical Approaches

Abstract Purpose of review In this review, we briefly summarize the numerical methods commonly used for the nonlinear dynamic analysis of soft robotic systems. The underlying mechanical principles as well as the geometrical treatment tailored for soft robots are introduced with particular emphasis on one-dimensional models. Additionally, the review encompasses three-dimensional frameworks, available simulation packages, and various types of interaction models, shedding light on the design, actuation, motion control, and internal and external forces of soft robots. Recent findings Reduced-order models can offer high efficiency in characterizing nonlinear deformations, allowing convenient tailoring based on specific structural and material configurations. For pursuing high simulation accuracy and detailed mechanics, the finite element method proves to be a valuable tool through numerous off-the-shelf platforms. Furthermore, machine learning has emerged as a promising tool to effectively address the challenges within the mechanics community. Summary A wide range of kinematic and dynamic numerical models is available for simulating the behaviors of soft robots, offering exceptional adaptability to different geometries and structures based on existing modeling theories and numerical solution algorithms. However, the trade-off between computational complexity and simulation accuracy remains a challenge in achieving fast, accurate, and robust control of soft robots in complex environments.

Behavior adaptation for mobile robots via semantic map compositions of constraint-based controllers.

Specifying and solving Constraint-based Optimization Problems (COP) has become a mainstream technology for advanced motion control of mobile robots. COP programming still requires expert knowledge to transform specific application context into the right configuration of the COP parameters (i.e., objective functions and constraints). The research contribution of this paper is a methodology to couple the context knowledge of application developers to the robot knowledge of control engineers, which, to our knowledge, has not yet been carried out. The former is offered a selected set of symbolic descriptions of the robots' capabilities (its so-called "behavior semantics") that are translated in control actions via "templates" in a "semantic map"; the latter contains the parameters that cover contextual dependencies in an application and robot vendor-independent way. The translation from semantics to control templates takes place in an "interaction layer" that contains 1) generic knowledge about robot motion capabilities (e.g., depending on the kinematic type of the robots), 2) spatial queries to extract relevant COP parameters from a semantic map (e.g., what is the impact of entering different types of "collision areas"), and 3) generic application knowledge (e.g., how the robots' behavior is impacted by priorities, emergency, safety, and prudence). This particular design of, and interplay between, the application, interaction, and control layers provides a structured, conceptually simple approach to advance the complexity of mobile robot applications. Eventually, industry-wide cooperation between representatives of the application and control communities should result in an interaction layer with different standardized versions of semantic complexity.

A Novel Human Intention Prediction Approach Based on Fuzzy Rules through Wearable Sensing in Human-Robot Handover.

With the use of collaborative robots in intelligent manufacturing, human-robot interaction has become more important in human-robot collaborations. Human-robot handover has a huge impact on human-robot interaction. For current research on human-robot handover, special attention is paid to robot path planning and motion control during the handover process; seldom is research focused on human handover intentions. However, enabling robots to predict human handover intentions is important for improving the efficiency of object handover. To enable robots to predict human handover intentions, a novel human handover intention prediction approach was proposed in this study. In the proposed approach, a wearable data glove and fuzzy rules are firstly used to achieve faster and accurate human handover intention sensing (HIS) and human handover intention prediction (HIP). This approach mainly includes human handover intention sensing (HIS) and human handover intention prediction (HIP). For human HIS, we employ wearable data gloves to sense human handover intention information. Compared with vision-based and physical contact-based sensing, wearable data glove-based sensing cannot be affected by visual occlusion and does not pose threats to human safety. For human HIP, we propose a fast handover intention prediction method based on fuzzy rules. Using this method, the robot can efficiently predict human handover intentions based on the sensing data obtained by the data glove. The experimental results demonstrate the advantages and efficacy of the proposed method in human intention prediction during human-robot handover.

Research on the design of mechanical robot control system for industrial PC in the context of big data

Abstract In the digitalization of big data information, how to use big data technology to design and study the mechanical robot control system of industrial PC has become a key topic of concern in today’s society. In this paper, robot kinematic modeling is mainly used to analyze and study the robot motion equations and control system operation mechanism, and the motion controller of the industrial robot control system is selected from the CLIPPERPMAC controller of the PMAC motion controller series. The approach to reducing the operation error of the industrial robot system from the control perspective is discussed. The error is reduced by adjusting the PID parameters of the PMAC motion controller in automatic and manual ways, and the error is further reduced by introducing fuzzy control algorithms. By comparing the original curve, the curve after the PID adjustment of PMAC itself and the curve after the introduction of the fuzzy controller, the curve error is kept below 5%, which is determined to be an effective method to reduce the error. This study can precisely realize the design and research of mechanical robot control systems, thus providing a guiding reference value for the research of industrial robot mechanization.

A viscosity-type scheme for optimization problems in Hadamard spaces with applications

In this article, we propose a viscosity-type scheme for approximating a common solution of convex minimization problem, monotone vector field inclusion problem and fixed point problem involving multi-valued nonexpansive mapping in the framework of Hadamard spaces. We obtain a strong convergence theorem for the sequence generated therefrom to a solution of the problem. Furthermore, we apply our results to compute the Fréchet mean, find the mean of probabilities, minimize energy of measurable mappings and solve a problem of two-arm robotic motion control. Finally, we give numerical example to demonstrate the applicability of the method and also issue comparisons with some existing methods. Our results extend and complement some recent results in the literature.