Emma:An accurate,efficient,and multi-modality strategy for autonomous vehicle angle prediction

Autonomous driving and self-driving vehicles have become the most popular selection for customers for their convenience.Vehicle angle prediction is one of the most prevalent topics in the autonomous driving industry,that is,realizing real-time vehicle angle prediction.However,existing methods of vehicle angle prediction utilize only single-modal data to achieve model prediction,such as images captured by the camera,which limits the performance and efficiency of the prediction system.In this paper,we present Emma,a novel vehicle angle prediction strategy that achieves multi-modal prediction and is more efficient.Specifically,Emma exploits both images and inertial measurement unit(IMU)signals with a fusion network for multi-modal data fusion and vehicle angle prediction.Moreover,we design and implement a few-shot learning module in Emma for fast domain adaptation to varied scenarios(e.g.,different vehicle models).Evaluation results demonstrate that Emma achieves overall 97.5%accuracy in predicting three vehicle angle parameters(yaw,pitch,and roll),which outperforms traditional single-modalities by approximately 16.7%-36.8%.Additionally,the few-shot learning module presents promising adaptive ability and shows overall 79.8%and 88.3%accuracy in 5-shot and 10-shot settings,respectively.Finally,empirical results show that Emma reduces energy consumption by 39.7%when running on the Arduino UNO board.

Optimizing Steering Angle Predictive Convolutional Neural Network for Autonomous Car

Deep learning techniques,particularly convolutional neural networks(CNNs),have exhibited remarkable performance in solving visionrelated problems,especially in unpredictable,dynamic,and challenging environments.In autonomous vehicles,imitation-learning-based steering angle prediction is viable due to the visual imagery comprehension of CNNs.In this regard,globally,researchers are currently focusing on the architectural design and optimization of the hyperparameters of CNNs to achieve the best results.Literature has proven the superiority of metaheuristic algorithms over the manual-tuning of CNNs.However,to the best of our knowledge,these techniques are yet to be applied to address the problem of imitationlearning-based steering angle prediction.Thus,in this study,we examine the application of the bat algorithm and particle swarm optimization algorithm for the optimization of the CNN model and its hyperparameters,which are employed to solve the steering angle prediction problem.To validate the performance of each hyperparameters’set and architectural parameters’set,we utilized the Udacity steering angle dataset and obtained the best results at the following hyperparameter set:optimizer,Adagrad;learning rate,0.0052;and nonlinear activation function,exponential linear unit.As per our findings,we determined that the deep learning models show better results but require more training epochs and time as compared to shallower ones.Results show the superiority of our approach in optimizing CNNs through metaheuristic algorithms as compared with the manual-tuning approach.Infield testing was also performed using the model trained with the optimal architecture,which we developed using our approach.

Mesoplasticity Approach to Studies of the Cutting Mechanism in Ultra-precision Machining

There have been various theoretical attempts by researchers worldwide to link up different scales of plasticity studies from the nano-, micro- and macro-scale of observation, based on molecular dynamics, crystal plasticity and continuum mechanics. Very few attempts, however, have been reported in ultra-precision machining studies. A mesoplasticity approach advocated by Lee and Yang is adopted by the authors and is successfully applied to studies of the micro-cutting mechanisms in ultra-precision machining. Traditionally, the shear angle in metal cutting, as well as the cutting force variation, can only be determined from cutting tests. In the pioneering work of the authors, the use of mesoplasticity theory enables prediction of the fluctuation of the shear angle and micro-cutting force, shear band formation, chip morphology in diamond turning and size effect in nano-indentation. These findings are verified by experiments. The mesoplasticity formulation opens up a new direction of studies to enable how the plastic behaviour of materials and their constitutive representations in deformation processing, such as machining can be predicted, assessed and deduced from the basic properties of the materials measurable at the microscale.

Development and application of a throughflow method for high-loaded axial flow compressors

In this paper, a novel engineering platform for throughflow analysis based on streamline curvature approach is developed for the research of a 5-stage compressor. The method includes several types of improved loss and deviation angle models, which are combined with the authors' adjustments for the purpose of reflecting the influences of three-dimensional internal flow in high-loaded multistage compressors with higher accuracy. In order to validate the reliability and robustness of the method, a series of test cases, including a subsonic compressor P&W 3S1, a transonic rotor NASA Rotor 1B and especially an advanced high pressure core compressor GE E^3 HPC, are conducted. Then the computation procedure is applied to the research of a 5-stage compressor which is designed for developing an industrial gas turbine. The overall performance and aerodynamic configuration predicted by the procedure, both at design- and part-speed conditions, are analyzed and compared with experimental results, which show a good agreement. Further discussion regarding the universality of the method compared with CFD is made afterwards. The throughflow method is verified as a reliable and convenient tool for aerodynamic design and performance prediction of modern high-loaded compressors. This method is also qualified for use in the further optimization of the 5-stage compressor.