Research on Safety Control Technology for Dual Robots Based on Kinematic Models

Based on complex industrial field environment, modern industrial robots need good real-time, safety and stability, put forward higher requirements for control system. In this paper, real-time control technology and three-dimensional simulation technology of six-degree-of-freedom industrial robot are studied. A six-degree-of-freedom robot control system is developed by using CODESYS software supporting EtherCAT fieldbus. The hardware, software and core algorithm of the control system are designed. Different from the traditional CNC machine tool processing, six axial industrial robot is used to weld the trajectory of sphere-tube intersection curve, 3D simulation and welding code are automatically generated, and the algorithm rationality is tested and simulated. The proven six-degree-of-freedom robot control system can complete the real-time position and attitude control of the torch, acquire the state of the robot in real time, and support a variety of industrial robot models. It realizes automatic programming, 3D simulation, program uploading and downlinking, etc. The entire system has good real-time and reliability.

Collision risk assessment and automatic obstacle avoidance strategy for teleoperation robots

Path planning for large ships in inland waterways considering risk assessment of AIS data

A high‐speed field‐programmable gate array (FPGA) design is proposed to calculate angles and distances for biped robots in real time. A low‐complexity and high‐accuracy hardware‐oriented algorithm based on CORDIC was developed. To reduce hardware cost, a hardware sharing technique was used to realise a CORDIC scaling factor generator and three hardware sharing machines. Moreover, the multipliers and dividers were replaced by cost‐efficiency components, such as adders and shifters to further reduce hardware cost. In addition, the proposed design was implemented with a fully pipelined architecture, which achieved improved operating frequency and throughput efficiency. The proposed design was realised and verified by an FPGA device with a maximum operating frequency of 127 MHz, which achieved the calculation of angles and distances for biped robots in real time. Compared with the previous design, this work not only reduced hardware cost by at least 49.6% and average errors by at least 67.2%, but also improved the average executing performance by 62.7% when calculating ten angles for the biped robots.

Introduction: The position and pose measurement of the rehabilitation robot plays a very important role in patient rehabilitation movement, and the non-contact real-time robot position and pose measurement is of great significance. Rehabilitation training is a relatively complicated process, so it is very important to detect the training process of the rehabilitation robot in real time and accuracy. The method of the deep learning has a very good effect on monitoring the rehabilitation robot state. Methods: The structure sketch and the 3D model of the 3-PRS ankle rehabilitation robot are established, and the mechanism kinematics is analyzed to obtain the relationship between the driving input - the three slider heights - and the position and pose parameters. The whole network of the position and pose measurement is composed of two stages: (1) measuring the slider heights using the CNN based on the robot image and (2) calculating the position and pose parameter using the BPNN based on the measured slider heights from the CNN. According to the characteristics of continuous variation of the slider heights, a regression CNN is proposed and established to measure the robot slider height. Based on the data calculated by using the inverse kinematics of the 3-PRS ankle rehabilitation robot, a BPNN is established to solve the forward kinematics for the position and pose. Results: The experimental results show that the regression CNN outputs the slider height and then the BPNN accurately outputs the corresponding position and pose. Eventually, the position and pose parameters are obtained from the robot image. Compared with the traditional robot position and pose measurement method, the proposed method has significant advantages. Conclusion: The proposed 3-PRS ankle rehabilitation position and pose method can not only shorten the experiment period and cost, but also get excellent timeliness and precision. The proposed approach can help the medical staff to monitor the status of the rehabilitation robot and help the patient rehabilitation in training. Discussion: The goal of the work is to construct a new position and pose detection network based on the combination of the regression convolutional neural network (CNN) and the back propagation neural network (BPNN). The main contribution is to measure the position and pose of the 3-PRS ankle rehabilitation robot in real time, which improves the measurement accuracy and the efficiency of the medical staff work.

In order to study the collision risk of port waters that only considers environmental factors and determine specific high collision risk waters, the gridding and entropy weight-TOPSIS model is used to calculate the collision risk value of Dalian Port as an example. Taking natural environmental factors and traffic environmental factors as risk assessment indicators, the waters of Dalian Port are divided into 133 grid units by latitude and longitude, and a collision risk assessment model for port waters based on the entropy weight-TOPSIS method is established. The main collision risk locations in the port waters are determined to be the channel, the middle of the anchorage and the border waters of the anchorage, and the effectiveness of the method is verified by comparing with the locations of collision accidents that have occurred.

In the risk management of maritime transportation, near-miss collisions by ships comprise a significant risk. Under the background of intelligent transportation, the emergence of technologies such as unmanned driving put forward higher requirements for maritime risk detection models. Previous studies have rarely been able to adaptively estimate the risk of near-miss collisions in different situations, especially for rare but existing encounters. Given this, this paper aims to improve the Vessel collision risk operator (VCRO) and proposes an exponential model of the safety distance in terms of the imbalance of risk assessment in the case of ships meeting close to the safety zone. Then combining the two risk standards set in the ship collision risk operator, and considering the impact of relative speed and relative course on collision risk, the risk detection model is further improved. The simulation results show that the improved ship collision risk assessment model is more applicable and accurate for the detection of collision risk in the open sea.

Due to blockage by large obstacles, perception of detection sensors such as lidar, radar, and stereo vision can have visibility restrictions. The assessment of collision risk against moving vehicles in the occluded area is difficult because vehicle motion information for perception is not available. In order to overcome this difficulty, this paper presents a probabilistic approach of collision risk assessment for the potential collision of vehicles in the occluded area. The probabilistic assessment consists of three steps: a field of view (FoV) modeling of perception, a motion prediction of potential collision, and a probabilistic collision risk assessment. The first step is a FoV modeling of perception to classify the occluded region of perception visibility. The second step is motion predictions of the potential collision vehicles by applying the modeled FoV to the roadway geometry in the precise map. The final step is a probabilistic assessment of the collision risk for the occluded vehicles based on the motion predictions and probabilistic modeling of vehicle speed on the road. The proposed collision risk assessment was evaluated using various occlusion scenarios in real traffic situations, such as an alleyway.

We analyzed commercial fleet operations data collected by a South Korean rent-a-car company, SK Networks Co. Ltd., to evaluate the differences between collision-free and collision-involved drivers with the ultimate goal of predicting driver collision risk. The first objective was to identify critical variables related to collision risk. The second objective was to build and compare classification models to predict the colli-sion involvement of a driver. Data used in the analysis were collected through Long-Range (LoRa) Internet of Things (IoT) modem-Fleet management system (FMS) devices, a first commercial implementation of LoRa modems in the vehicle. These devices have five main built-in modules, i.e., On-Board Diagnostics (OBD-II) Connector, GPS, LoRa modem, Gravity sensor, and Bluetooth. They can communicate with the vehi-cle, the driver’s smartphone, and the host server. Data from 3,854 drivers with a total of 2.19 million trips recorded in 2018 were explored. Out of these 3,854 drivers, 514 (13.3%) were involved in at least one collision. Predictor variables were selected based on previous research that uti-lized naturalistic data to identify factors affecting collision risk (Dingus et al., 2016; Tselentis, Yannis, & Vlahogianni, 2016; Bian, Yang, Zhao, & Liang, 2018; Jin et al., 2018). Forty-eight predictor variables that may affect collision risk were selected, which can be categorized into two groups: 27 variables were related to the business and the environment, characterized by how much drivers traveled, in what type of vehicles, on what types of roads, and during what times of the day; the other 22 variables were driving behavior-related variables, capturing overspeeding, potential fatigue, rapid speed changes, and counts of traffic regulation violations. After a feature selection phase based on univariate analysis, nine variables were select-ed to be used in the classification models. These selected vari-ables are running driving time (driving time excluding idling time), trip frequency per thousand kilometer driving, accumu-lated count of violation, accumulated amount of fine, the per-centage of trips driving a compact car (<1,000 cc), the per-centage of trips driving older than a 2016 car model, the per-centage of trips during 6 a.m.-9 a.m., the percentage of trips that ended during 2 a.m.-7 a.m., and the sum of rapid accelera-tion and deceleration frequencies per kilometer. A total of twenty classification models were built and compared to classify collision-involved and non-collision in-volved drivers: 5 classification modeling techniques (Logistic Regression (LR), Random Forest (RF), k-Nearest Neighbor (kNN), Support Vector Machine (SVM) and Gradient boosted trees (GBT)) x 4 sampling methods (Up, Down, Smote, and No-sampling). The GBT-down sampled model showed the best classification performance according to Area under the Curve (0.804) and Area under the Precision and Recall Curve (0.406) statistics. Comparing relative variable importance val-ues for the best three classification models (GBT, RF, and LR), both running driving time and violation count were found to be the most influential variables, followed by the sum of rapid acceleration and deceleration frequencies, accumulated amount of fine, trip frequency per thousand kilometer driving, and the percentage of trips driving a compact car. These re-sults agree with the results of previous naturalistic studies: driver behavior-related variables are highly related to collision likelihood, although running driving time in our dataset was likely dictated by businesses. This dataset provided us with a unique opportunity to take an in-depth look at the relationship between collisions and business, environment, and driving behavior-related variables by using naturalistic data from newly-invented LoRa IoT-FMS devices. To the best of our knowledge, this study was the first naturalistic study connecting both driving data and various types of traffic violations (e.g., overspeeding, lane, sign, park-ing, toll fees, and fine amount). Interestingly, non-driving-related violation types such as parking or toll-fee violation counts were also strongly correlated with collision involve-ment; suggesting that collision-involvement is likely not just a skill issue but also an attitude issue regarding the law. In terms of industrial applications, this study suggests multiple oppor-tunities. Through a better understanding of the influential vari-ables related to collision-involvement (e.g., accumulated vio-lations), fleet operators can build policies to enhance their fleet safety, reducing collision rates and the associated costs. Further, in the long-term, this study can provide a framework for developing a Usage-Based Rent-a-car (UBR) service for car rental field, similar to Usage-Based Insurance (UBI), which can reduce drivers’ rental fees based on their driving behaviors.

Collision risk assessment in real-time is of critical importance to prevent ship collision at sea. Therefore, this paper presents a real-time collision risk assessment method based on an improved Non-linear Velocity Obstacle (NL-VO) algorithm. The proposed method consists of two main modules: trajectory uncertainty module assumes that the increase in the radius of the circular restricted area is consistent with the Wiener process; collision risk assessment module utilizes the NL-VO algorithm combined with the dynamic circular restricted area to evaluate the potential collisions. Several encounter scenarios in a specific port channel are designed to demonstrate the feasibility of using this proposed method to assess ship collision risk in real-time. The results are visualized and illustrated that this improved NL-VO algorithm can timely identify a ship that is in danger of colliding with the own ship and know when the collision will occur, which contributes to reducing ship collision occurrence probability.

A new method, Global Newton-Raphson (GNR), for forward kinematics analysis of six degree-of-freedom (DOF) parallel robots is proposed, in order to obtain direct solutions of parallel robots in real time without divergence. The parallel robot can produce 3-DOF linear motions and 3-DOF angular motions, and feeds back positions of actuators measured by position sensors in real time. The GNR for the robot is built by Taylor series expansion and Newton-Raphson iteration with descent operator. Applying the GNR, the real generalized pose of moving platform is solved with respect to the base for a set of given positions of actuators. Accuracy and real time property of the GNR for the 6-DOF parallel robot are analyzed. The theoretical analysis indicated that the presented method can achieve the numerical convergent solution in real time with high accuracy, even the initial guesses are far from a solution.

In this paper the authors propose a solution in which an intelligent algorithm - genetic algorithm in our case - is used to generate commands for a robot in real time, so that the robot can determine the optimal moves considering several aspects: route tracking and low power consumption. Genetic algorithms are intelligent solutions for multi-criteria optimization and using them to find solutions to the optimization problems containing constrictions. However, they were designed as algorithms running on computer and therefore cannot ensure rapid generation of the solutions. On the other hand, the problem of determining the optimal response to command a robot requires real time response. The paper presents a method for hardware implementation and integration in a FPGA circuit of a genetic algorithm, in order to accelerate the convergence and to generate solutions in real time.

Traditional optical flow methods are designed to generate two-dimensional (2D) motion fields. However in some applications, only the motion field along a predefined line is needed, while the rest of the redundant 2D region (Cong et al., CVPR, 2009) can be ignored. In this paper, we propose a general framework for estimating one-dimensional (1D) motion field using the $$L_1$$L1 norm metric, which can be flexible for adding any constraints depending on the specific intention. Compared with 2D methods in model calculation, which often obtain a local optimal solution, our 1D version has the advantage of real-time global optimization and sub-pixel accuracy with a large displacement capacity. The synthesized experiments have justified the effectiveness of our 1D model. Two vision applications are investigated: (i) for crowd counting, we design a novel unified framework for both line of interest and region of interest counting using our 1D motion model to mosaic the dynamic blobs. Such a framework can adapt to new site without scene-specific learning and overcome overfitting. (ii) For visual odometry, we apply our 1D model to estimate the linear velocity of the robot in real time and obtain a comparable result with the benchmark Encoder. Experiments verified that our proposed model can produce satisfactory results in real time.

In the conditions of bad weather, the small vessels maneuvering ability of collision avoidance is seriously reduced and the vulnerability to maritime accidents increases due to the influence of strong wind and wave. This paper proposes a collision avoidance decision-making and control method for small vessels using the integrated collision risk assessment based on fuzzy logic. First, the speed of wind and height of wave in the bad weather conditions are fuzzified. Then, the collision risk indices are selected for fuzzy inference to get the basic collision risk which will be integrated with the vulnerability to collision accidents and it helps to improve the accuracy of collision risk assessment. According to the current multi-ships encounter situations, the similar cases are retrieved from the case database, and the collision avoidance decision is given after fuzzy adjustments. To implement collision avoidance actions, a fuzzy algorithm for nonlinear ship heading dynamic surface control (DSC) control considering input saturation and uncertainties is designed. The problem of "computational expansion" that may occur in high-order systems is avoided by using DSC technology. Finally, simulation experiments are implemented to verify the effectiveness of the collision avoidance method.

The purpose of this work is to control a remote mobile robot in real time by detecting and avoiding obstacles in the navigation environment using an RGB-D camera. To this end, an advanced signal and image processing are applied to the acquired environment images in the aim to define the optimal motion path. the experimental results prove that the mobile robot follows the optimal trajectory and avoids all the obstacles in the navigation environment.