IMPROVING HUMAN AWARENESS DURING COLLABORATION WITH ROBOT: REVIEW

Human-robot collaboration is a widespread topic within the concept of Industry 4.0. Such collaboration brings new opportunities to improve ergonomics and innovative options for manufacturing automation; however, most of the modern collaborative industrial applications are limited by the fact that neither collaborative side is fully aware of the partner: the human operator may not see the robot movement due to own engagement in the work process, and the collaborative robot simply has no means of knowing the position of the operator. Dynamic replanning of the robot trajectory with respect to the operator's current position can increase the efficiency and safety of cooperation since the robot will be able to avoid collisions and proceed in task completion; however, the other side of communication remains unresolved. This paper provides a review of methods of improving human awareness during collaboration with a robot. Covered techniques include graphical, acoustic and haptic feedback implementations. The work is focused on the practical applicability of the approaches, and analyses present challenges associated with each method.

Deep reinforcement learning-based rehabilitation robot trajectory planning with optimized reward functions

Deep reinforcement learning (DRL) provides a new solution for rehabilitation robot trajectory planning in the unstructured working environment, which can bring great convenience to patients. Previous researches mainly focused on optimization strategies but ignored the construction of reward functions, which leads to low efficiency. Different from traditional sparse reward function, this paper proposes two dense reward functions. First, azimuth reward function mainly provides a global guidance and reasonable constraints in the exploration. To further improve the efficiency, a process-oriented aspiration reward function is proposed, it is capable of accelerating the exploration process and avoid locally optimal solution. Experiments show that the proposed reward functions are able to accelerate the convergence rate by 38.4% on average with the mainstream DRL methods. The mean of convergence also increases by 9.5%, and the percentage of standard deviation decreases by 21.2%–23.3%. Results show that the proposed reward functions can significantly improve learning efficiency of DRL methods, and then provide practical possibility for automatic trajectory planning of rehabilitation robot.

PID-based with Odometry for Trajectory Tracking Control on Four-wheel Omnidirectional Covid-19 Aromatherapy Robot

Inhalation therapy is one of the most popular treatments for many pulmonary conditions. The proposed Covid-19 aromatherapy robot is a type of Unmanned Ground Vehicle (UGV) mobile robot that delivers therapeutic vaporized essential oils or drugs needed to prevent or treat Covid-19 infections. It uses four omnidirectional wheels with a controlled speed to possibly move in all directions according to its trajectory. All motors for straight, left, or right directions need to be controlled, or the robot will be off-target. The paper presents omnidirectional four-wheeled robot trajectory tracking control based on PID and odometry. The odometry was used to obtain the robot's position and orientation, creating the global map. PID-based controls are used for three purposes: motor speed control, heading control, and position control. The omnidirectional robot had successfully controlled the movement of its four wheels at low speed on the trajectory tracking with a performance criterion value of 0.1 for the IAEH, 4.0 for MAEH, 0.01 for RMSEH, 0.00 for RMSEXY, and 0.06 for REBS. According to the experiment results, the robot's linear velocity error rate is 2%, with an average test value of 1.3 percent. The robot heading effective error value on all trajectories is 0.6%. The robot's direction can be monitored and be maintained at the planned trajectory. Doi: 10.28991/esj-2021-SPER-13 Full Text: PDF

Colored 3D Path Extraction Based on Depth-RGB Sensor for Welding Robot Trajectory Generation

The necessity for intelligent welding robots that meet the demand in real industrial production, according to the objectives of Industry 4.0, has been supported owing to the rapid development of computer vision and the use of new technologies. To improve the efficiency in weld location for industrial robots, this work focuses on trajectory extraction based on color features identification on three-dimensional surfaces acquired with a depth-RGB sensor. The system is planned to be used with a low-cost Intel RealSense D435 sensor for the reconstruction of 3D models based on stereo vision and the built-in color sensor to quickly identify the objective trajectory, since the parts to be welded are previously marked with different colors, indicating the locations of the welding trajectories to be followed. This work focuses on 3D color segmentation with which the points of the target trajectory are segmented by color thresholds in HSV color space and a spline cubic interpolation algorithm is implemented to obtain a smooth trajectory. Experimental results have shown that the RMSE error for V-type butt joint path extraction was under 1.1 mm and below 0.6 mm for a straight butt joint; in addition, the system seems to be suitable for welding beads of various shapes.

Obstacle Avoidance Using CTC and Virtual Structure for Leader-Follower Formation on Mobile Robot

This research examined the development of the combination of virtual structure and leader-follower as an obstacle avoidance method in the formation control of a mobile robot. The formation of the robots are designed with the Separation Bearing Control (SBC) approach between the leader robot (RL) and the virtual robot (RV). The virtual robot is used as a virtual follower and a reference trajectory for the follower robot (RF). When the follower robot detects an obstacle, the follower robot trajectory is adjusted using a trajectory planner for obstacle avoidance. After passing the obstacle, the follower robot will track its position back in formation using virtual robot position and heading as reference. Leader robot and follower are perturbed by disturbances. In order to ensure the achievement of small error tracking, a controller is designed using the integration of kinematic and dynamics controllers with disturbance observer. The kinematic and dynamics controllers are designed using input-output linearisation (IOL) method and computed torque control (CTC). The effectiveness of the proposed method is verified by the simulation result.Keywords: CTC, leader follower, obstacle avoidance, SBC, virtual structure.