The complete coverage path planning is a process of finding a path which ensures that a mobile robot completely covers the entire environment while following the planned path. In this paper, we propose a complete coverage path planning algorithm that generates smooth complete coverage paths based on clothoids that allow a nonholonomic mobile robot to move in optimal time while following the path. This algorithm greatly reduces coverage time, the path length, and overlap area, and increases the coverage rate compared to the state-of-the-art complete coverage algorithms, which is verified by simulation. Furthermore, the proposed algorithm is suitable for real-time operation due to its computational simplicity and allows path replanning in case the robot encounters unknown obstacles. The efficiency of the proposed algorithm is validated by experimental results on the Pioneer 3DX mobile robot.

Today, mobile robots have a wide range of real-world applications where they can replace or assist humans in many tasks, such as search and rescue, surveillance, patrolling, inspection, environmental monitoring, etc. These tasks usually require a robot to navigate through a dynamic environment with smooth, efficient, and safe motion. In this paper, we propose an online smooth-motion-planning method that generates a smooth, collision-free patrolling trajectory based on clothoid curves. Moreover, the proposed method combines global and local planning methods, which are suitable for changing large environments and enabling efficient path replanning with an arbitrary robot orientation. We propose a method for planning a smoothed path based on the golden ratio wherein a robot’s orientation is aligned with a new path that avoids unknown obstacles. The simulation results show that the proposed algorithm reduces the patrolling execution time, path length, and deviation of the tracked trajectory from the patrolling route compared to the original patrolling method without smoothing. Furthermore, the proposed algorithm is suitable for real-time operation due to its computational simplicity, and its performance was validated through the results of an experiment employing a differential-drive mobile robot.

This paper presents a method for optimizing the dimensions of the central opening in the mobile platform, ensuring adequate surface reachability for a 6-DOF robotic arm. The reachability map is extended with the concept of 8 Configuration Reachability to account for the redundancy of the arm, where up to eight possible joint configurations exist for a given pose of the end effector. Additionally, Weighted Reachability is proposed to quantify reachability throughout the workspace, taking into account the varying importance of surfaces, such as the ground and walls. By varying the dimensions of the central opening; width, length, height, and offset, dimension of the platform is determined for optimal reachability. The simulation results demonstrate the effectiveness of the proposed method, which achieves high reachability for selected configurations. The findings provide a practical basis for the design of mobile platforms with a robotic arm, particularly those with a central opening for operational tasks.

The technology of autonomous driving is currently attracting a great deal of interest in both research and industry. In this paper, we present a deep learning dual-model solution that uses two deep neural networks for combined braking and steering in autonomous vehicles. Steering control is achieved by applying the NVIDIA's PilotNet model to predict the steering wheel angle, while braking control relies on the use of MobileNet SSD. Both models rely on a single front-facing camera for image input. The MobileNet SSD model is suitable for devices with constrained resources, whereas PilotNet struggles to operate efficiently on smaller devices with limited resources. To make it suitable for such devices, we modified the PilotNet model using our own original network design and reduced the number of model parameters and its memory footprint by approximately 60%. The inference latency has also been reduced, making the model more suitable to operate on resource-constrained devices. The modified PilotNet model achieves similar loss and accuracy compared to the original PilotNet model. When evaluated in a simulated environment, both autonomous driving systems, one using the modified PilotNet model and the other using the original PilotNet model for steering, show similar levels of autonomous driving performance.

The continuous and reliable monitoring of soil organic carbon and soil respiration is vital for sustainable agricultural and environmental management. However, current manual methods are labor-intensive and time-consuming. This work focuses on the development of a fully automated robotic platform for in situ measurement of Soil Organic Carbon (SOC) and Soil Respiration (${\mathbf{R}}_s$). The system consists of a four-wheeled mobile platform, equipped with a robotic arm, and custom sampling and measurement tools. The platform is designed with a protected central opening that houses an on-board laboratory, enabling automated surface cleaning, soil drilling, sample collection and homogenization, SOC spectroscopy analysis, and chamber-based soil respiration measurement. The platform is equipped with a high-force mechanical insertion mechanism capable of operating a range of tools designed for soil treatment and penetration. These tools include a soil surface scraper, a soil respiration chamber, and a soil drilling unit. The mobile robotic laboratory system enables the sequential deployment of these tools in any desired order, providing flexible and efficient in-field operation.