The Planning Process of Transport Tasks for Autonomous Vans—Case Study

Abstract

Transport is an area that is developing at a tremendous pace. This development applies not only to electric and hybrid cars appearing more and more often on the road but also to those of an autonomous or semi-autonomous nature. This applies to both passenger cars and vans. In many different publications, you can find a description of a number of benefits of using automated guided vehicles (AGV) for logistics and technical tasks, e.g., in the workplace. An important aspect is the use of knowledge management and machine learning, i.e., artificial intelligence (AI), to design these types of processes. An important issue in the construction of autonomous vehicles is the IT connection of sensors receiving signals from the environment. These signals are data for deep learning algorithms. The data after IT processing enable the decision-making by AI systems, while the used machine learning algorithms and neural networks are also needed for video image analysis in order to identify and classify registered objects. The purpose of this article is to present and verify a mathematical model used to respond to vehicles’ demand for a transport service under set conditions. The optimal conditions of the system to perform the transport task were simulated, and the efficiency of this system and benefits of this choice were determined.

Real-Time Hardware-in-the-Loop Emulation of Path Tracking in Low-Cost Agricultural Robots

“…Localization of the Agribot can be achieved using different approaches [38]; in this study, the posture of the robot (1) for emulation purposes can be obtained by the formulation of the inverse kinematics model formulation of x, y, and θ, which are defined, respectively, by (10), (11), and (5).…”

“…For experiments with the Agribot, we employ an inertial measurement unit (IMU) from WitMotion (https://witmotion-sensor.com/) to obtain the yaw angular velocity ω of the robot, which allows us to compute the robot's orientation (yaw) angle θ by integration. We also use two encoders, from USDigital (https://www.usdigital.com/), to obtain the angular velocity of each wheel, ω R and ω L ; from this information and the orientation, we can establish the actual position x, y, of the robot using the inverse kinematics model, (10) and (11). Thus, we can close the loop and control the robot's position.…”

“…Current research and development are focused, principally, on autonomous operation, motion prediction, and correction of trajectories [6][7][8][9]. Likewise, there are works related to vehicle route planning [10], optimization of routes, and vehicle routing [11]. Here, it is important to mention that the research oriented on UGV navigation for indoor and outdoor applications [12], Ref.…”

Multi-Agent Decision-Making Modes in Uncertain Interactive Traffic Scenarios via Graph Convolution-Based Deep Reinforcement Learning

“…In an uncertain interactive traffic scenario, the driving environment has rigorous dynamic characteristics and high uncertainty, and the influences of driving behaviors of different traffic participants will be transmitted continuously [10]. On the level of transportation overall, all traffic participants need to cooperate efficiently [11]. At the traffic participant level, individuals need to judge the risk factors and make appropriate decisions sensitively based on dynamic scene changes [12].…”

Measuring Performance During a Fallback Procedure in Autonomous Vehicles

“…More efficient transportation would not only be faster but also more environmentally friendly and, most likely, cheaper over time including logistics. In fact, various simulation models have been implemented to plan distribution services carried out by autonomous vans (Caban et al, 2022). At the same time, cars could become available to people who have traditionally not been able to use them due to physical, age, or other limitations.…”