- Autonomous Vehicle Technology and Safety
- Occupational Health and Safety Research
- Transportation and Mobility Innovations
- Vehicle emissions and performance
- Vehicle Dynamics and Control Systems
- Risk and Safety Analysis
- Infrastructure Maintenance and Monitoring
- Traffic Prediction and Management Techniques
- Remote Sensing and LiDAR Applications
- Advanced Neural Network Applications
- Electric Vehicles and Infrastructure
- Cardiac Arrest and Resuscitation
- Traffic control and management
- Automotive and Human Injury Biomechanics
- Advanced Vision and Imaging
- Digital Transformation in Industry
- Reinforcement Learning in Robotics
- Robot Manipulation and Learning
- Smart Parking Systems Research
- Manufacturing Process and Optimization
- Smart Materials for Construction
- Industrial Vision Systems and Defect Detection
- Robotics and Sensor-Based Localization
- Analytical Chemistry and Sensors
- Mechanical Engineering and Vibrations Research
Western Michigan University
2020-2024
Land Sea Air Autonomy (United States)
2024
University of Colorado Colorado Springs
2024
Colorado State University
2024
Oak Ridge National Laboratory
2022
Commercialization of autonomous vehicle technology is a major goal the automotive industry, thus research in this space rapidly expanding across world. However, despite high level activity, literature detailing straightforward and cost-effective approach to development an AV platform sparse. To address need, we present methodology results regarding instrumentation controls 2019 Kia Niro which was developed for local pilot program. This includes drive-by-wire actuation kit, Aptiv...
Advancements in driving automation systems such as Lane Keeping Assist has shown improvements safety by reducing traffic accidents. Nonetheless, despite the promise of these technologies, some studies have statistical data that a poor resilient operation. Therefore, there is need to design more robust and Advanced Driver Assistance Systems (ADAS) while broadening their operational domain. This study proposes set non-functional system level requirements informed applying Resilience...
<div class="section abstract"><div class="htmlview paragraph">Autonomous vehicle technology has the potential to improve safety, efficiency, and cost of our current transportation system by removing human error. With sensors available today, it is possible for development these vehicles, however, there are still issues with autonomous operations in adverse weather conditions (e.g. snow-covered roads, heavy rain, fog, etc.) due degradation sensor data quality insufficiently robust...
<div class="section abstract"><div class="htmlview paragraph">Contemporary ADS and ADAS localization technology utilizes real-time perception sensors such as visible light cameras, radar sensors, lidar greatly improving transportation safety in sufficiently clear environmental conditions. However, when lane lines are completely occluded, the reliability of on-board automated systems breaks down, vehicle control must be returned to human driver. This limits operational design...
<div class="section abstract"><div class="htmlview paragraph">Accurate perception of the driving environment and a highly accurate position vehicle are paramount to safe Autonomous Vehicle (AV) operation. AVs gather data about using various sensors. For robust localization system, incoming from multiple sensors is usually fused together advanced computational algorithms, which historically requires high-compute load. To reduce AV compute load its negative effects on energy...
<div class="section abstract"><div class="htmlview paragraph">Practical applications of recently developed sensor fusion algorithms perform poorly in the real world due to a lack proper evaluation during development. Existing metrics do not properly address wide variety testing scenarios. This issue can be addressed using proactive performance measurements such as tools resilience engineering theory rather than reactive root mean square error. Resilience is an established...
<div class="section abstract"><div class="htmlview paragraph">Traditional autonomous vehicle perception subsystems that use onboard sensors have the drawbacks of high computational load and data duplication. Infrastructure-based sensors, which can provide quality information without burden duplication, are an alternative to traditional subsystems. However, these technologies still in early stages development not been extensively evaluated for lane detection system performance....
<div class="section abstract"><div class="htmlview paragraph">Lane detection plays a critical role in autonomous vehicles for safe and reliable navigation. Lane is traditionally accomplished using camera sensor computer vision processing. The downside of this traditional technique that it can be computationally intensive when high quality images at fast frame rate are used has reliability issues from occlusion such as, glare, shadows, active road construction, more. This study...
The sensing and compute load auxiliary energy consumption in autonomous vehicles may be significant due to the large number of sensors high from sensor processing route planning. To understand this issue, study investigates top-down usage an electric 2015 Kia Soul fully instrumented with state a state-specific computer for path planning processing. A chassis dynamometer was then used evaluate cases (1) no or computation, (2) only operating, (3) plus load. vehicle operated autonomously on...
Increased energy consumption from autonomous vehicle (AV) sensors and computational load as well upfront costs of are barriers to broad AV adoption. For high quality reliable perception the driving environment, incoming data multiple need be fused together using advanced algorithms, which requires a compute load. As an alternative, infrastructure-based can designed facilitate sensing by supporting vehicle-to-infrastructure (V2I) information exchange. This work presents initial development...
<div class="section abstract"><div class="htmlview paragraph">Connected and Automated Vehicles (CAV) provide new prospects for energy-efficient driving due to their improved information accessibility, enhanced processing capacity, precise control. The idea of the Eco-Driving (ED) control problem is perform speed planning a connected automated vehicle using data obtained from high-resolution maps Vehicle-to-Everything (V2X) communication. With recent goal commercialization...
<div class="section abstract"><div class="htmlview paragraph">Modern vehicles use automated driving assistance systems (ADAS) products to automate certain aspects of driving, which improves operational safety. In the U.S. in 2020, 38,824 fatalities occurred due automotive accidents, and typically about 25% these are associated with inclement weather. ADAS features have been shown reduce potential collisions by up 21%, thus reducing overall accidents. But utilize camera sensors...
Autonomous vehicle technology has tremendous potential for revolutionizing the current transportation industry.Companies and investors are funding a staggering amount of development, leading to large number high paying jobs that require new skills.But traditional university engineering education model not kept up with demand as evidenced by popularity Udacity, Udemy, other massive open online courses.A paradigm multidisciplinary is needed meet learner industry demand.To begin address this...
Safe autonomous vehicle (AV) operations depend on an accurate perception of the driving environment, which necessitates use a variety sensors. Computational algorithms must then process all this sensor data, typically results in high on-vehicle computational load. For example, existing lane markings are designed for human drivers, can fade over time, and be contradictory construction zones, require specialized sensing processing AV. But, standard avoided if information is simply transmitted...
<div class="section abstract"><div class="htmlview paragraph">Evaluating real-world hazards associated with perception subsystems is critical in enhancing the performance of autonomous vehicles. The reliability vehicles are paramount for safe and efficient operation. While current studies employ different metrics to evaluate subsystem failures vehicles, there still exists a gap development emphasis on engineering requirements. To address this gap, study proposes establishment...