Search Results

There is significant potential for connected and autonomous vehicles to impact vehicle efficiency, fuel economy, and emissions, especially for hybrid-electric vehicles. These improvements could have large-scale impact on oil consumption and air-quality if deployed in large Mobility-as-a-Service or ride-sharing fleets. As part of the US Department of Energy's current Advanced Vehicle Technology Competition (AVCT), EcoCAR: The Mobility Challenge, Mississippi State University’s EcoCAR Team is redesigning and doing the development work necessary to convert a conventional gasoline spark-ignited 2019 Chevy Blazer into a hybrid-electric vehicle with SAE Level 2 autonomy. The target consumer segments for this effort are the Mobility-as-a-Service fleet owners, operators and riders. To accomplish this conversion, the MSU team is implementing a P4 mild hybridization strategy that is expected to result in a 30% increase in fuel economy over the stock Blazer.

The University of Wisconsin - Madison hybrid vehicle team has designed and constructed a four-wheel drive, charge sustaining, parallel hybrid-electric sport utility vehicle for entry into the FutureTruck 2003 competition. This is a multi-year project utilizing a 2002 4.0 liter Ford Explorer as the base vehicle. Wisconsin's FutureTruck, nicknamed the ‘Moolander’, weighs 2000 kg and includes a prototype aluminum frame. The Moolander uses a high efficiency, 1.8 liter, common rail, turbo-charged, compression ignition direct injection (CIDI) engine supplying 85 kW of peak power and an AC induction motor that provides an additional 60 kW of peak power. The 145 kW hybrid drivetrain will out-accelerate the stock V6 powertrain while producing similar emissions and drastically reducing fuel consumption. The PNGV Systems Analysis Toolkit (PSAT) model predicts a Federal Testing Procedure (FTP) combined driving cycle fuel economy of 16.05 km/L (37.8 mpg).

The University of Wisconsin - Madison FutureTruck Team has designed and built a four-wheel drive, charge sustaining, parallel hybrid-electric sport utility vehicle for entry into the FutureTruck 2001 competition. The base vehicle is a 2000 Chevrolet Suburban. Our FutureTruck is nicknamed the “Moollennium” and weighs approximately 2427 kg. The vehicle uses a high efficiency, 2.5 liter, turbo-charged, compression ignition common rail, direct-injection engine supplying approximately 104 kW of peak power and a three phase AC induction motor that provides an additional 68.5 kW of peak power. This hybrid drivetrain is an attractive alternative to the large displacement V8 drivetrain, as it provides comparable performance with lower emissions and fuel consumption. The PNGV Systems Analysis Toolkit (PSAT) model predicts a Federal Testing Procedure (FTP) urban driving cycle fuel economy of 11.24 km/L (26.43 mpg) with California Ultra Low Emission Vehicle (ULEV) emissions levels.

The University of Wisconsin - Madison FutureTruck Team has designed and built a four-wheel drive, charge sustaining, parallel hybrid-electric sport utility vehicle for entry into the FutureTruck 2002 competition. This is a two-year project with tiered goals; the base vehicle for both years is a 2002 Ford Explorer. Wisconsin's FutureTruck, nicknamed the ‘Moolander’, weighs approximately 2050 kg. The vehicle uses a high efficiency, 2.5 liter, turbo-charged, compression ignition common rail, direct-injection engine supplying approximately 100 kW of peak power and a AC induction motor that provides an additional 33 kW of peak power. This hybrid drivetrain is an attractive alternative to the large displacement V6 drivetrain, as it provides comparable performance with similar emissions and drastically reduced fuel consumption.

The objective of this study was to observe and attempt to understand the effects of equivalence ratio and simulated exhaust gas recirculation (EGR) on the exhaust emissions and performance of a L-head single cylinder utility engine. In order to isolate these effects and limit the confounding influences caused by poor fuel mixture preparation and/or vaporization produced by the carburetor/intake port combination, the engine was operated on a premixed propane/air mixture. To simulate the effects of EGR, a homogeneous mixture of propane, air, and nitrogen was used. Engine measurements were obtained at the operating conditions specified by the California Air Resources Board (CARB) Raw Gas Method Test Procedure. Measurements included exhaust emissions levels of HC, CO, and NOx, and engine pressure data.

Regenerative testing methods can be used to allow the testing of hydraulic pumps and motors at significantly higher power and flow levels than that of the power supply used. This method can also increase the accuracy of system efficiency measurements. The increase in accuracy is realized because only the power added to compensate for the system losses needs to be measured with great accuracy. Typically, for the operation points of interest this will be a much smaller quantity than the overall power of the system. Knowing that the error in flow measurements is a function of the quantity measured, the benefit of measuring the losses becomes clear. An additional, distinct advantage of regenerative testing is that no dynamometer or load is needed. This results in a much simpler test setup. This paper documents the development of such a test program at the University of Wisconsin-Madison.

Identifying edge cases for designed algorithms is critical for functional safety in autonomous driving deployment. In order to find the feasible boundary of designed algorithms, simulations are heavily used. However, simulations for autonomous driving validation are expensive due to the requirement of visual rendering, physical simulation, and AI agents. In this case, common sampling techniques, such as Monte Carlo Sampling, become computationally expensive due to their sample inefficiency. To improve sample efficiency and minimize the number of simulations, we propose a tailored active learning approach combining the Support Vector Machine (SVM) and the Gaussian Process Regressor (GPR). The SVM learns the feasible boundary iteratively with a new sampling point via active learning. Active Learning is achieved by using the information of the decision boundary of the current SVM and the uncertainty metric calculated by the GPR.

We present an approach in which an open-source software infrastructure is used for testing the behavior of autonomous vehicles through computer simulation. This software infrastructure is called CAVE, from Connected Autonomous Vehicle Emulator. As a software platform that allows rapid, low-cost and risk-free testing of novel designs, methods and software components, CAVE accelerates and democratizes research and development activities in the field of autonomous navigation.

The SAE AutoDrive Challenge II is a four-year collegiate competition dedicated to developing a Level 4 autonomous vehicle by 2025. In January 2023, the participating teams each received a Chevy Bolt EUV. Within a span of five months, the second phase of the competition took place in Ann Arbor, MI. The authors of this contribution, who participated in this event as team Wisconsin Autonomous representing the University of Wisconsin–Madison, secured second place in static events and third place in dynamic events. This has been accomplished by reducing reliance on the actual vehicle platform and instead leveraging physical analogs and simulation. This paper outlines the software and hardware infrastructure of the competing vehicle, touching on issues pertaining sensors, hardware, and the software architecture employed on the autonomous vehicle. We discuss the LiDAR-camera fusion approach for object detection and the three-tier route planning and following systems.