Telepresence robots (TRs) are increasingly important for remote communication and collaboration, particularly in situations where physical presence is not possible. One key feature of TRs is person-following, which relies on the detection and distance estimation of individuals. This study proposes an autonomous person-following TR using a monocular camera and deep-learning YOLO for person detection and distance estimation. To compensate for the monocular camera's inability to provide depth information, a novel distance estimation algorithm based on focal length and person width is introduced. The estimated width information of the detected person is extracted from the bounding box generated by YOLO. A pre-trained model using the MS COCO dataset is employed with YOLO for the person detection task. For robot movement control, a region-based controller is proposed to enable the robot to move based on the detected person's location in the image captured by the camera. Finally, integration and deployment of the proposed method in the TR is carried out using the Robot Operating System (ROS). Experimental results demonstrate that the TR can successfully follow a person using the proposed algorithm, thus highlighting its effectiveness for person-following tasks.

This paper discusses the design of a consensus tracking algorithm with the practical implementation of solving distributed altitude and attitude tracking of multiple quadrotors. In contrast to most of the existing works that consider a leader agent that is non-cooperative, this paper proposes an algorithm that allows the leader agent to receive feedback from a subset of the followers. Firstly, the feedback linearization technique is utilized on the nonlinear quadrotor dynamics which yield a simple linear system. Then, the proposed consensus tracking algorithm is designed and employed to the resulting linear system to achieve consensus tracking on altitude and attitudes via local interaction between neighbours. Results obtained show that the proposed consensus tracking for a group of quadrotors can improve connectivity preservation as compared to the non-cooperative leader in the presence of an obstacle. Based on the formulation of the controller, the methodology can be easily adapted to various systems such as attitude synchronization of multiple satellite systems.

This study aims to develop a small prototype of a seed-sowing mobile robot, that can follow the desired path, and be able to collect, carry and drop the object of interest (seeds) at the designated places. The robot utilizes an infrared (IR) sensor for detecting the desired line, while an ultrasonic sensor for detecting the desired drop location. These sensor inputs are processed by a microcontroller, which in turn sends the control signal to the dc motor for the line-following task. The microcontroller also sends the control signal to a group of servo motors (robot arms) to collect, carry and drop the seeds onto the crop border. The functionality of the proposed robot was tested in a lab setting, where the results validated the concept. This robot serves as a proof of concept for the seed-sowing robot application in the agriculture sector.This study aims to develop a small prototype of a seed-sowing mobile robot, that can follow the desired path, and be able to collect, carry and drop the object of interest (seeds) at the designated places. The robot utilizes an infrared (IR) sensor for detecting the desired line, while an ultrasonic sensor for detecting the desired drop location. These sensor inputs are processed by a microcontroller, which in turn sends the control signal to the dc motor for the line-following task. The microcontroller also sends the control signal to a group of servo motors (robot arms) to collect, carry and drop the seeds onto the crop border. The functionality of the proposed robot was tested in a lab setting, where the results validated the concept. This robot serves as a proof of concept for the seed-sowing robot application in the agriculture sector.

This study addresses the design and analysis of distributed formation tracking control with disturbance rejection capability for a group of quadrotors that are perturbed by time-varying external disturbances. The proposed approach consists of two control loops: inner-loop and outer-loop control. In the inner-loop control, feedback linearization (FL) of the quadrotor system in the presence of disturbance yields linear equations with unknown disturbance parts. The unknown disturbance parts are estimated in the outer-loop control by using a disturbance observer (DO). Since the DO produces an estimation error or called residual error when estimating time-varying disturbance, this study introduces a radial basis function neural network (RBFNN) with adaptive weight to effectively approximate and eliminate the residual error. Then, to complete the formation mission, a consensus-based algorithm is implemented in the outer-loop control to enable the distributed formation tracking. The capabilities of formation tracking and online approximating are proved via the Lyapunov approach. Simulation of the quadrotor formation in the presence of time-varying wind disturbance was conducted to evaluate the effectiveness of the approach where the results obtained illustrate the robustness of the quadrotor formation towards the disturbances.