Search Results

Research interests in autonomous driving have increased significantly in recent years. Several methods are being suggested for performance optimization of autonomous vehicles. However, weather conditions such as rain, snow, and fog may hinder the performance of autonomous algorithms. It is therefore of great importance to study how the performance/efficiency of the underlying scene understanding algorithms vary with such adverse scenarios. Semantic segmentation is one of the most widely used scene-understanding techniques applied to autonomous driving. In this work, we study the performance degradation of several semantic segmentation algorithms caused by rain for off-road driving scenes. Given the limited availability of datasets for real-world off-road driving scenarios that include rain, we utilize two types of synthetic datasets.

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 latest edition of the US Department of Energy's (DOE) Advanced Vehicle Technology Competition (AVTC) series is the EcoCAR Mobility Challenge (EMC). In the third year of the EMC, the Mississippi State University (MSU) team developed and tested a perception system and a longitudinal controller to achieve SAE level 2 autonomy. Our team leveraged the model-based design approach to iterate between developing software components and executing tests in multiple environments in the loop (XIL) to verify that design requirements are met. This workflow allowed us to detect and resolve issues early in the development process. The perception system is composed of a sensor fusion and tracking algorithm. It relies on detections from a front facing camera and radar to generate tracks for a leading vehicle. The tracks from the perception system are used by a model predictive controller (MPC) to maintain a safe distance to the leading vehicle.

The autonomous collision avoidance problem for multi-trailer vehicle maneuvering is investigated in this paper. Different from conventional vehicle systems that contain one single moving part or multi-parts that can be considered as one rigid body, the interconnection between the tractor and each trailer, and interactions between trailers in the multi-trailer system introduce a high dimensional and highly complex dynamic system for the controller design. The external disturbance and parametric uncertainties further increase the difficulty in system identification and state space formulation. To implement a real time control system for various scenarios where the locations and states of the obstacles are not known beforehand, a supervisory algorithm is designed to convert the control problem to a discrete event system. The model predictive control (MPC) using limited lookahead policy is employed in the proposed algorithm.

Recent developments in the area of autonomous vehicle navigation have emphasized algorithm development for the characterization of LiDAR 3D point-cloud data. The LiDAR sensor data provides a detailed understanding of the environment surrounding the vehicle for safe navigation. However, LiDAR point cloud datasets need point-level labels which require a significant amount of annotation effort. We present a framework which generates simulated labeled point cloud data. The simulated LiDAR data was generated by a physics-based platform, the Mississippi State University Autonomous Vehicle Simulator (MAVS). In this work, we use the simulation framework and labeled LiDAR data to develop and test algorithms for autonomous ground vehicle off-road navigation. The MAVS framework generates 3D point clouds for off-road environments that include trails and trees.