Object detection is an essential component of autonomous mobile robotic systems, enabling robots to understand and interact with the environment. Object detection and recognition have made significant progress using convolutional neural networks (CNNs). Widely used in autonomous mobile robot applications, CNNs can quickly identify complicated image patterns, such as objects in a logistic environment. Integration of environment perception algorithms and motion control algorithms is a topic subjected to significant research. On the one hand, this paper presents an object detector to better understand the robot environment and the newly acquired dataset. The model was optimized to run on the mobile platform already on the robot. On the other hand, the paper introduces a model-based predictive controller to guide an omnidirectional robot to a particular position in a logistic environment based on an object map obtained from a custom-trained CNN detector and LIDAR data. Object detection contributes to a safe, optimal, and efficient path for the omnidirectional mobile robot. In a practical scenario, we deploy a custom-trained and optimized CNN model to detect specific objects in the warehouse environment. Then we evaluate, through simulation, a predictive control approach based on the detected objects using CNNs. Results are obtained in object detection using a custom-trained CNN with an in-house acquired data set on a mobile platform and in the optimal control for the omnidirectional mobile robot.
The symmetry of the omnidirectional robot motion abilities around its central vertical axis is an important advantage regarding its driveability for the flexible interoperation with fixed conveyor systems. The paper illustrates a Hardware in the Loop architectural approach for integrated development of an Ominidirectional Mobile Robot that is designed to serve in a dynamic logistic environment. Such logistic environments require complex algorithms for autonomous navigation between different warehouse locations, that can be efficiently developed using Robot Operating System nodes. Implementing path planning nodes benefits from using Matlab-Simulink, which provides a large selection of algorithms that are easily integrated and customized. The proposed solution is deployed for validation on a NVIDIA Jetson Nano, the embedded computer hosted locally on the robot, that runs the autonomous navigation software. The proposed solution permits the live connection to the omnidirectional prototype platform, allowing to deploy algorithms and acquire data for debugging the location, path planning and the mapping information during real time autonomous navigation experiments, very useful in validating different strategies.
Monitoring and tracking issues related to autonomous mobile robots are currently intensively debated in order to ensure a more fluent functionality in supply chain management. The interest arises from both theoretical and practical concerns about providing accurate information about the current and past position of systems involved in the logistics chain, based on specialized sensors and Global Positioning System (GPS). The localization demands are more challenging as the need to monitor the autonomous robot’s ongoing activities is more stringent indoors and benefit from accurate motion response, which requires calibration. This practical research study proposes an extended calibration approach for improving Omnidirectional Mobile Robot (OMR) motion response in the context of mechanical build imperfections (misalignment). A precise indoor positioning system is required to obtain accurate data for calculating the calibration parameters and validating the implementation response. An ultrasound-based commercial solution was considered for tracking the OMR, but the practical observed errors of the readily available position solutions requires special processing of the raw acquired measurements. The approach uses a multilateration technique based on the point-to-point distances measured between the mobile ultrasound beacon and a current subset of fixed (reference) beacons, in order to obtain an improved position estimation characterized by a confidence coefficient. Therefore, the proposed method managed to reduce the motion error by up to seven-times. Reference trajectories were generated, and robot motion response accuracy was evaluated using a Robot Operating System (ROS) node developed in Matlab-Simulink that was wireless interconnected with the other ROS nodes hosted on the robot navigation controller.
The paper proposes an adaptive method for compensating the speed dependent position estimation offset introduced by parameter sub-evaluation needed for proper operation of an industry adopted flux observer used in field oriented control schemes for PMSM. The method was tested using a test-bench composed of the PMSM control kit YRotate-IT-RX23T from Renesas driving a PMSM connected to a generator with resistive load used as adjustable brake. The experimental results are compared with the simulations of the modeled test-bench.