Search Results

Autonomous vehicle operation is dependent upon accurate position estimation and thus a major concern of implementing the autonomous navigation is obtaining robust and accurate data from sensors. This is especially true, in case of Inertial Measurement Unit (IMU) sensor data. The IMU consists of a 3-axis gyro, 3-axis accelerometer, and 3-axis magnetometer. The IMU provides vehicle orientation in 3D space in terms of yaw, roll and pitch. Out of which, yaw is a major parameter to control the ground vehicle’s lateral position during navigation. The accelerometer is responsible for attitude (roll-pitch) estimates and magnetometer is responsible for yaw estimates. However, the magnetometer is prone to environmental magnetic disturbances which induce errors in the measurement.

Autonomous ground vehicles can use a variety of techniques to navigate the environment and deduce their motion and location from sensory inputs. Visual Odometry can provide a means for an autonomous vehicle to gain orientation and position information from camera images recording frames as the vehicle moves. This is especially useful when global positioning system (GPS) information is unavailable, or wheel encoder measurements are unreliable. Feature-based visual odometry algorithms extract corner points from image frames, thus detecting patterns of feature point movement over time. From this information, it is possible to estimate the camera, i.e., the vehicle’s motion. Visual odometry has its own set of challenges, such as detecting an insufficient number of points, poor camera setup, and fast passing objects interrupting the scene. This paper investigates the effects of various disturbances on visual odometry.

It is rare for an attempt towards optimization at the fleet-level when consideration is given to the sheer number of seemingly unpredictable interactions among vehicles and infrastructure in congested urban areas. To close the gap, we introduce a simulation based framework to explore the impact of speed synchronization on fuel economy improvement for fleets in traffic. The framework consists of traffic and vehicle modules. The traffic module is used to simulate driver behavior in urban traffic; and the vehicle module is employed to estimate fuel economy. Driving schedule is the linkage between these two modules. To explore the impact, a connected vehicle technology sharing vehicle speed information is used for better fuel economy of a fleet including six vehicles. In all scenarios analyzed, the leading vehicle operates under the EPA Urban Dynamometer Driving Schedule (UDDS), while the other five vehicles follow the leader consecutively.

Current artificial intelligence techniques for end to end driving of autonomous vehicles typically rely on a single form of learning or training processes along with a corresponding dataset or simulation environment. Relatively speaking, success has been shown for a variety of learning modalities in which it can be shown that the machine can successfully “drive” a vehicle. However, the realm of real-world driving extends significantly beyond the realm of limited test environments for machine training. This creates an enormous gap in capability between these two realms. With their superior neural network structures and learning capabilities, humans can be easily trained within a short period of time to proceed from limited test environments to real world driving.

Robust autonomous navigation in unstructured environments is an unsolved problem and critical to the operation of autonomous military and rescue ground vehicles. Two-dimensional path planners operating on occupancy grids or costs maps can produce infeasible paths when the operational area includes complex terrain. Recently, sample-based path planners that plan on LiDAR-acquired point-cloud maps have been proposed. These approaches require no discretization of the operational area and provide direct pose estimation by modeling vehicle and terrain interaction. In this paper, we show that direct sample-based path planning on point clouds is effective and robust in unstructured environments. Robustness is demonstrated by completing a system parameter sensitivity analysis of the system in an Unreal simulation environment and partnered with field validation.

Off-road vehicle operation requires constant decision-making under great uncertainty. Such decisions are multi-faceted and range from acquisition decisions to operational decisions. A major input to these decisions is terrain information in the form of soil properties. This information needs to be propagated to path planning algorithms that augment them with other inputs such as visual terrain assessment and other sensors. In this sequence of steps, many resources are needed, and it is not often clear how best to utilize them. We present an integrated approach where a mission’s overall performance is measured using a multiattribute utility function. This framework allows us to evaluate the value of acquiring terrain information and then its use in path planning. The computational effort of optimizing the vehicle path is also considered and optimized. We present our approach using the data acquired from the Keweenaw Research Center terrains and present some results.

Accurate perception of the driving environment and a highly accurate position of the vehicle are paramount to safe Autonomous Vehicle (AV) operation. AVs gather data about the environment using various sensors. For a robust perception and localization system, incoming data from multiple sensors is usually fused together using advanced computational algorithms, which historically requires a high-compute load. To reduce AV compute load and its negative effects on vehicle energy efficiency, we propose a new infrastructure information source (IIS) to provide environmental data to the AV. The new energy–efficient IIS, chip–enabled raised pavement markers are mounted along road lane lines and are able to communicate a unique identifier and their global navigation satellite system position to the AV. This new IIS is incorporated into an energy efficient sensor fusion strategy that combines its information with that from traditional sensor.

This paper describes a multi-sensor data set, suitable for testing algorithms to detect and track pedestrians and cyclists, with an autonomous vehicle’s sensor suite. The data set can be used to evaluate the benefit of fused sensing algorithms, and provides ground truth trajectories of pedestrians, cyclists, and other vehicles for objective evaluation of track accuracy. One of the principal bottlenecks for sensing and perception algorithm development is the ability to evaluate tracking algorithms against ground truth data. By ground truth we mean independent knowledge of the position, size, speed, heading, and class of objects of interest in complex operational environments. Our goal was to execute a data collection campaign at an urban test track in which trajectories of moving objects of interest are measured with auxiliary instrumentation, in conjunction with several autonomous vehicles (AV) with a full sensor suite of radar, lidar, and cameras.

This paper presents real-world driving energy and fuel consumption results for the second-generation Chevrolet Volt plug-in hybrid electric vehicle (PHEV). A drive cycle, local to Michigan Technological University, was designed to mimic urban and highway driving test cycles in terms of distance, transients and average velocity, but with significant elevation changes to establish an energy intensive real-world driving cycle for assessing potential energy savings for connected and automated vehicle (CAV) control. The investigation began by establishing baseline and repeatability of energy consumption at various battery states of charge. It was determined that drive cycle energy consumption under a randomized set of boundary conditions varied within 3.6% of mean energy consumption regardless of initial battery state of charge.

This paper presents the development of a reduced-order powertrain model for energy and SOC estimation of a multi-mode plug-in hybrid electric vehicle using only vehicle speed profile and route elevation as inputs. Such a model is intended to overcome the computational inefficiencies of higher fidelity powertrain and vehicle models in short and long horizon energy optimization efforts such as Coordinated Adaptive Cruise Control (CACC), Eco Approach and Departure (EcoAND), Eco Routing, and PHEV mode blending. The reduced-order powertrain model enables Connected and Automated Vehicles (CAVs) to utilize the onboard sensor and connected data to quickly react and plan their maneuvers to highly dynamic road conditions with minimal computational resources.

This paper presents a methodology to optimize the blending of charge-depleting (CD) and charge-sustaining (CS) modes in a multi-mode plug-in hybrid electric vehicle (PHEV) that reduces overall energy consumption when the selected route cannot be completely driven in all-electric mode. The PHEV used in this investigation is the second-generation Chevrolet Volt and as many as four instrumented vehicles were utilized simultaneously on road to acquire validation data. The optimization method used is dynamic programming (DP) paired with a reduced-order powertrain model to enable onboard embedded controller compatibility and computational efficiency in optimally blending CD, CS modes over the entire drive route.

As the world searches for ways to reduce humanity’s impact on the environment, the automotive industry looks to extend the viable use of the gasoline engine by improving efficiency. One way to improve engine efficiency is through more effective control. Torque-based control is critical in modern cars and trucks for traction control, stability control, advanced driver assistance systems, and autonomous vehicle systems. Closed loop torque-based engine control systems require feedback signal(s); indicated mean effective pressure (IMEP) is a useful signal but is costly to measure directly with in-cylinder pressure sensors. Previous work has been done in torque and IMEP estimation using crankshaft acceleration and ion sensors, but these systems lack accuracy in some operating ranges and the ability to estimate cycle-cycle variation.

The advancement in embedded systems and positional accuracy with base station GPS modules created opportunity to develop high performance autonomous ground vehicles. However, the development of vehicle model and making accurate state estimations play vital role in reducing the cross track error. The present research focus on developing Linear Quadratic Gaussian (LQG) with Kalman estimator for autonomous ground vehicle to track various routes, that are made with the series of waypoints. The model developed in the LQG controller is a kinematic bicycle model, which mimics 1/5th scale truck. Further, the cubic spline fit has been used to connect the waypoints and generate the continuous desired/target path. The testing and implementation has been done at APS labs, MTU on the mentioned vehicle to study the performance of controller. Python has been used for simulations, controller coding and interfacing the sensors with controller.

China's plug-in electric vehicle (PEV) market with stocks at 7.8 million is the world's largest in 2021, and it accounts for half of the global PEV growth in 2021. The PEV market in China has dramatically evolved since the pandemic in 2020: over 20% of all new PEV sales are from China by mid-2022. Recent features of PEV market dynamics, consumer acceptance, policies, and infrastructure have important implications for both the global energy market and manufacturing stakeholders. From the perspective of demand pull-supply push, this study analyzes China's PEV industry with a market dynamics framework by reviewing sales, product and brand, infrastructure, and government policies from the last few years and outlooking the development of the new government’s 14th Five-Year Plan (2021-2025).

The current focus in the ongoing development of autonomous driving systems (ADS) for heavy duty vehicles is that of vehicle operational safety. To this end, developers and researchers alike are working towards a complete understanding of the operating environments and conditions that autonomous vehicles are subject to during their mission. This understanding is critical to the testing and validation phases of the development of autonomous vehicles and allows for the identification of both the nominal and edge case scenarios encountered by these systems. Previous work by the authors saw the development of a comprehensive scenario generation framework to identify an operating domain specification (ODS), or external and internal conditions an autonomous driving system can expect to encounter on its mission to form critical scenario groups for autonomous vehicle testing and validating using statistical patterns, clustering, and correlation.

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 high quality information without the computational burden and data duplication, are an alternative to traditional autonomous vehicle perception subsystems. However, these technologies are still in the early stages of development and have not been extensively evaluated for lane detection system performance. Therefore, there is a lack of quantitative data on their performance relative to traditional perception methods, especially during hazardous scenarios, such as lane line occlusion, sensor failure, and environmental obstructions.

Lane detection plays a critical role in autonomous vehicles for safe and reliable navigation. Lane detection is traditionally accomplished using a camera sensor and computer vision processing. The downside of this traditional technique is that it can be computationally intensive when high quality images at a fast frame rate are used and has reliability issues from occlusion such as, glare, shadows, active road construction, and more. This study addresses these issues by exploring alternative methods for lane detection in specific scenarios caused from road construction-induced lane shift and sun glare. Specifically, a U-Net, a convolutional network used for image segmentation, camera-based lane detection method is compared with a radar-based approach using a new type of sensor previously unused in the autonomous vehicle space: radar retro-reflectors.

The AutoDrive Challenge competition sponsored by General Motors and SAE gives undergraduate and graduate students an opportunity to get hands-on experience with autonomous vehicle technology and development as they work towards their degree. Michigan Technological University has participated in the AutoDrive Challenge since its inception in 2017 with students participating through MTU’s Robotic System Enterprise. The MathWorks Simulation Challenge has been a component of the competition since its second year, tasking students with the development of perception, control and testing algorithms using MathWorks software products. This paper presents the pedagogical approach graduate student mentors used to enable students to build their understanding of autonomous vehicle concepts using familiar tools. This approach gives undergraduate students a productive experience with these systems that they may not have encountered in coursework within their academic program.