Search

Feasible local motion planning for autonomous mobile robots in dynamic environments requires predicting how the scene evolves. Conventional navigation stakes rely on a local map to represent how a dynamic scene changes over time. However, these navigation stakes depend highly on the accuracy of the environmental map and the number of obstacles. This study uses semantic segmentation-based drivable area estimation as an alternative representation to assist with local motion planning. Notably, a realistic 3D simulator based on an Unreal Engine was created to generate a synthetic dataset under different weather conditions. A transfer learning technique was used to train the encoder-decoder model to segment free space from the occupied sidewalk environment. The local planner uses a nonlinear model predictive control (NMPC) scheme that inputs the estimated drivable space, the state of the robot, and a global plan to produce safe velocity commands that minimize the tracking cost and actuator effort while avoiding collisions with dynamic and static obstacles. The proposed approach achieves zero-shot transfer from a simulation to real-world environments that have never been experienced during training. Several intensive experiments were conducted and compared with the dynamic window approach (DWA) to demonstrate the effectiveness of our system in dynamic sidewalk environments. [ABSTRACT FROM AUTHOR]

The transportation sector is under increasing pressure to reduce greenhouse gas emissions by decarbonizing its operations. One prominent solution that has emerged is the adoption of electric vehicles (EVs). As the electric vehicles market experiences rapid growth, the utilization of lithium-ion batteries (LiB) has become the predominant choice for energy storage. However, it is important to note that lithium-ion battery technology is sensitive to factors, like excessive voltage and temperature. Therefore, the development of an accurate battery model and a reliable state of charge (SOC) estimator is crucial to safeguard against the overcharging and over-discharging of the battery. Numerous studies have been conducted to address lithium-ion battery cell modeling and SOC estimations. These studies have explored variations in the number of RC networks within the model and different estimation methods. However, it is worth mentioning that the capacity of a single lithium-ion battery cell is relatively low and cannot be directly employed in electric vehicles. To meet the total capacity and voltage requirements for electric vehicles, multiple cells are typically connected in series or parallel configurations to form a battery pack. Surprisingly, this aspect has often been overlooked in previous research. To tackle this overlooked challenge, our study introduces a comprehensive battery pack model and an advanced Battery Management System (BMS). We then integrate these components into an electric vehicle model. Subsequently, we simulate the integrated EV-BMS model under the conditions of four different urban driving scenarios to replicate real-world driving conditions. The BMS that we have developed includes an Extended Kalman Filter (EKF)-based SOC estimation system, a mechanism for controlling coolant flow, and a passive cell-balancing algorithm. These components work together to ensure the safe and efficient operation of the battery pack within the electric vehicles. [ABSTRACT FROM AUTHOR]

The paper presents the mathematical model of a quadrotor unmanned aerial vehicle (UAV) and the design of robust Self-Tuning PID controller based on fuzzy logic, which offers several advantages over certain types of conventional control methods, specifically in dealing with highly nonlinear systems and parameter uncertainty. The proposed controller is applied to the inner and outer loop for heading and position trajectory tracking control to handle the external disturbances caused by the variation in the payload weight during the flight period. The results of the numerical simulation using gazebo physics engine simulator and real-time experiment using AR drone 2.0 test bed demonstrate the effectiveness of this intelligent control strategy which can improve the robustness of the whole system and achieve accurate trajectory tracking control, comparing it with the conventional proportional integral derivative (PID). [ABSTRACT FROM AUTHOR]

Three-dimensional object detection utilizing LiDAR point cloud data is an indispensable part of autonomous driving perception systems. Point cloud-based 3D object detection has been a better replacement for higher accuracy than cameras during nighttime. However, most LiDAR-based 3D object methods work in a supervised manner, which means their state-of-the-art performance relies heavily on a large-scale and well-labeled dataset, while these annotated datasets could be expensive to obtain and only accessible in the limited scenario. Transfer learning is a promising approach to reduce the large-scale training datasets requirement, but existing transfer learning object detectors are primarily for 2D object detection rather than 3D. In this work, we utilize the 3D point cloud data more effectively by representing the birds-eye-view (BEV) scene and propose a transfer learning based point cloud semantic segmentation for 3D object detection. The proposed model minimizes the need for large-scale training datasets and consequently reduces the training time. First, a preprocessing stage filters the raw point cloud data to a BEV map within a specific field of view. Second, the transfer learning stage uses knowledge from the previously learned classification task (with more data for training) and generalizes the semantic segmentation-based 2D object detection task. Finally, 2D detection results from the BEV image have been back-projected into 3D in the postprocessing stage. We verify results on two datasets: the KITTI 3D object detection dataset and the Ouster LiDAR-64 dataset, thus demonstrating that the proposed method is highly competitive in terms of mean average precision (mAP up to 70 % ) while still running at more than 30 frames per second (FPS). [ABSTRACT FROM AUTHOR]

Autonomous navigation and collision avoidance missions represent a significant challenge for robotics systems as they generally operate in dynamic environments that require a high level of autonomy and flexible decision-making capabilities. This challenge becomes more applicable in micro aerial vehicles (MAVs) due to their limited size and computational power. This paper presents a novel approach for enabling a micro aerial vehicle system equipped with a laser range finder to autonomously navigate among obstacles and achieve a user-specified goal location in a GPS-denied environment, without the need for mapping or path planning. The proposed system uses an actor–critic-based reinforcement learning technique to train the aerial robot in a Gazebo simulator to perform a point-goal navigation task by directly mapping the noisy MAV's state and laser scan measurements to continuous motion control. The obtained policy can perform collision-free flight in the real world while being trained entirely on a 3D simulator. Intensive simulations and real-time experiments were conducted and compared with a nonlinear model predictive control technique to show the generalization capabilities to new unseen environments, and robustness against localization noise. The obtained results demonstrate our system's effectiveness in flying safely and reaching the desired points by planning smooth forward linear velocity and heading rates. [ABSTRACT FROM AUTHOR]