Evaluating the safety of Autonomous Vehicles (AV) is a challenging problem, especially in traffic conditions involving dynamic interactions. A thorough evaluation of the vehicle’s decisions at all possible critical scenarios is necessary for estimating and validating its safety. However, predicting the response of the vehicle to dynamic traffic conditions can be the first step in the complex problem of understanding vehicle’s behavior. This predicted response of the vehicle can be used in validating vehicle’s safety.In this paper, models based on Machine Learning were explored for predicting and classifying driver’s response. The Naturalistic Driving Study dataset (NDS), which is part of the Strategic Highway Research Program-2 (SHRP2) was used for training and validating these Machine Learning models. Various popular Machine Learning Algorithms were used for classifying and predicting driver’s response, such as Extremely Randomized Trees and Gaussian Mixture Model based Hidden Markov Model, which are widely used in multiple domains.For classifying driver’s response, longitudinal acceleration vs lateral acceleration plot (Ax-Ay plot) was divided into nine different classes and selected Machine Learning models were trained for predicting…

It’s important to predict the future actions of human in the industry assembly process. Foreseeing future actions before they have happened is an essential part for flexible human-robot collaboration and crucial safety issues. Vision-based human actions prediction from videos provides intuitive and adequate knowledge for many complex applications. This problem can be interpreted as deducing the next action of people from a short video clip. The history information needs to be considered to learn these relations between each time step for predicting the future steps. However, it is difficult to extract the history information and use it to infer the future situation with the traditional methods. In this scenario, a model is needed to handle the spatial and temporal details stored in past human motions and construct the future action based on limited accessible human demonstrations. In this paper, we apply an autoencoder based deep learning framework for human actions construction, merging into the RNN pipeline for human future actions prediction. This contrasts with traditional approaches which use hand-crafted features and different domain output. The…

For ground effect aerodynamic studies in wind tunnels, boundary layer growth over the floor of the test section is a large concern. Many different techniques have been used to remove this boundary layer, of which creating a moving ground plane is considered the best option. By creating a moving floor in the test section, the ground plane speed can be set to that of the free stream air speed, thus removing the boundary layer or at the very least mitigating the boundary layer growth. Several studies detail the aerodynamic design concerns for such devices, but little information exists on the mechanical design concerns. This work reviews lessons learned during a design study of a rolling road for the wind tunnel at California State University, Fullerton (CSUF) mainly focusing on the motor specification and cooling system design. First, an overview of the major systems that comprise a rolling road apparatus are given. Then, initial constraints and free-body diagrams are presented detailing the forces experienced by the rolling road. From these free-body diagrams, analytical equations are presented…

Lane detection is of crucial importance in ADAS because various modules (i.e., LKAS, LDWS, etc.) need robust and precise lane position to locate themselves and traffic participants to plan an optimal routine or making proper driving decisions. While most of the lane detection approaches depend on great amount of pre-processing and various assumptions to get reasonable result, the robustness and efficiency are deteriorated. To address this problem, a novel framework is proposed in this paper to realize the robust and real-time lane detection. This framework consists of two branches, where canny edge detection and Progressive Probabilistic Hough Transform (PPHT) are introduced in the first branch to achieve an efficient detection. To eliminate the dependency of the framework on assumptions such as flatten road, deep learning based encoder-decoder detection branch, which leverages the powerful nonlinear approximation ability of CNN, is introduced to improve the robustness and contribute a precise intermediate result. Since the detection rate of the CNN branch is much slower than the feature-based branch, a coordinating unit is designed. The two branches also backup…

Field Issue( Malfunction) incidents are costly for manufacture’s service department. Especially for commercial fleet customers, the downtime can be the biggest concern. To reduce the warranty cost and improve customer’s confidence in our products, preventive maintenance provides the benefit of 1.fixing the problem when it is small; 2. reducing downtime of scheduled targeted service time to reduce downtime. However, normal telematics system has difficulty in capturing useful information even with pre-set triggers. Some malfunction issue takes weeks to find out route cause due to the difficulty of repeating the error in a different vehicle and engineers to analyze large amount of data. In order to solve above challenges, a machine learning based predictive software/hardware system has been implemented. Multiple machine learning techniques, including CNN, has been utilized in the proposed pipeline to: 1) decide when to record data. 2) decide what variables to record for what period of time 3) root cause diagnostics on the spot based on time series data analysis. The system utilizes both histogram data and time series data. For the time…

Mechanical engineering seniors at Lawrence Technological University complete a capstone design project: either an SAE collegiate design series (CDS) vehicle or an industry-sponsored project (ISP). Starting in 2015, the Lawrence Tech CDS advisors worked together to redesign the five-credit three-semester sequence. The overall goals of the modifications were to improve student design, project management and communication skills; integrate SAE CDS projects into the curriculum; and increase faculty advisor involvement in the classroom. Initial results from the 2015-2016 academic year showed improvement in the first offering of the new sequence (Mynderse et. al. 2016). Ongoing assessment of course modifications includes faculty advisor observation, student surveys, and direct assessment of student technical output. This work expands on previous results with finalized learning outcomes, resulting session-by-session schedules, and new assessment data. The revised sequence consists of three courses: Introduction to Projects, Competition Projects 1, and Competition Projects 2. Introduction to Projects runs during the Spring semester only and introduces students the CDS projects while using a designette to practice the engineering design process and project management. Students complete…

Aniruddha Mitra Professor of Mechanical Engineering, Georgia Southern University Keith Russell Undergraduate Student, Mechanical Engineering Department, Georgia Southern University This study focuses on the design of off-road vehicles to avoid “Hang Up” and “Nose In” failures with specific case study of Georgia Southern University’s SAE mini BAJA vehicle. The BAJA vehicle may encounter two distinct kinds of failure while climbing or descending terrain obstacles: “Hang Up” failure, and “Nose In” failures. Hang up failure occurs when the bottom of the chassis of the vehicle makes contact with the obstacle. This occurs after the front tires have cleared the obstacle but before the rear tires have. This mitigates the pace of the vehicle and may cause damage. Nose in failure is when the protruding front bumper or “nose” of the vehicle makes direct contact with either the ground or the obstacle. The possible ramifications of this event are much more disastrous than the Hang up failure. Nose in failure can send the vehicle into an end over end flip, or cause significant structural damage to the…

In this paper, we present a framework for the robot to learn how to place objects to a workpiece by learning from humans in smart manufacturing. In the proposed framework, the semantic event chain (SEC) is implemented to identify the general object-action-location relationships. The Generalized Voronoi Diagrams (GVD) is used to determine the relative position and orientation between the object the corresponding mount. In the learning phase, we keep tracking the image segments in the human demonstration. For the moment when a spatial relation of some segments are changed in a discontinuous way, the state changes are recorded by the SEC, while the relative position and orientation of the object and the corresponding mount are presented by GVD. When the object or the relative position and orientation between the object and the workpiece are changed, the GVD, as well as the shape of contours extracted from the GVD, are also different. The Fourier Descriptor (FD) is applied to describe these differences on the shape of contours in the GVD. An FD-based similarity measurement algorithm is…

The HyPACE (Hybrid Petrol Advanced Combustion Engine) project is a part UK government funded research project established to develop a high thermal efficiency petrol engine optimised for hybrid vehicle applications. The project combines the capabilities of a number of partners (Jaguar Land Rover, Borg Warner, MAHLE Powertrain, Johnson Matthey, Cambustion and Oxford University) with the target of achieving a 10% vehicle fuel consumption reduction, whilst still achieving a 90 to 100 kW/litre power rating through the novel application of a combination of new technologies. The donor engine for the project was Jaguar Land Rover’s new Ingenium 4-cylinder petrol engine which includes an advanced continuously variable intake valve actuation mechanism. The new HyPACE boosting system utilises a Borg Warner 48V eTurbo™ featuring a variable geometry turbine which enables the capability to both provide electrical assistance, to improve dynamic response when required, as well as being able to utilise waste exhaust gas energy to generate electricity. This paper presents results from a testing programme which demonstrates the capability of the new boosting system to extend the stoichiometric…