With connected and autonomous vehicles, no optimal standard or framework currently exists, outlining the right level of information sharing for cooperative autonomous driving. Cooperative Perception is proposed among vehicles, where every vehicle is transformed into a moving sensor platform that is capable of sharing information collected using its on-board sensors. This helps extend the line of sight and field of view of autonomous vehicles, which otherwise suffer from blind spots and occlusions. This increase in situational awareness promotes safe driving over a short range and improves traffic flow efficiency over a long range. This thesis proposes a methodology for cooperative perception for autonomous vehicles over a short range. The problem of cooperative perception is broken down into sub-tasks of cooperative relative localization and map merging. Cooperative relative localization is achieved using visual and inertial sensors, where a computer-vision based camera relative pose estimation technique, augmented with position information, is used to provide a pose-fix that is subsequently updated by dead reckoning using an inertial sensor. Prior to map merging, a technique for object localization using a monocular camera is proposed that is based on the Inverse Perspective Mapping technique. A mobile multi-robot testbed was developed to emulate autonomous vehicles and the proposed method was implemented on the testbed to detect pedestrians and also to respond to the perceived hazard. Potential traffic scenarios where cooperative perception could prove crucial were tested and the results are presented in this thesis. / MS / Perception in Autonomous Vehicles is limited to the field of view of the vehicles’ onboard sensors and the environment may not be fully perceivable due to the presence of blind spots and occlusions. To overcome this limitation, Vehicle-to-Vehicle wireless communication could be leveraged to exchange locally sensed information among vehicles within the vicinity. Vehicles may share information about their own position, heading and velocity or go one step further and share information about their surroundings as well. This latter form of cooperative perception extends each vehicle’s field of view and line of sight, and helps increase situational awareness. The result is an increase in safety over a short range whereas communication over a long range could help improve traffic flow efficiency. This thesis proposes one such technique for cooperative perception over a short range. The system uses visual and inertial sensors to perform cooperative localization between two vehicles sharing a common field of view, which allows one vehicle to locate the other vehicle in its frame of reference. Subsequently, information about objects in the surroundings of one vehicle, localized using a visual sensor is relayed to the other vehicle through communication. A mobile multi-robot testbed was developed to emulate autonomous vehicles and to experimentally evaluate the proposed method through a series of driving scenario test cases in which cooperative perception could be effective and crucial to the safety and comfort of driving.

While driving behavior is generally governed by the nature and the driving objectives of the driver, there are many situations (typically in crowded traffic conditions) where tacit communication between vehicle drivers and pedestrians govern driving behavior, significantly influencing transportation safety. The study aimed to formalize the tacit communication between vehicle drivers and pedestrians, in order to inform an investigation on effective communication mechanisms between autonomous vehicle and humans. Current autonomous vehicles engage in decision making primarily controlled by on-board or external sensory information, and do not explicitly consider communication with pedestrians. The study was a within subject 2x2x2 factorial experimental design. The three independent variables were driving context (normal driving vs. autonomous vehicle placard), driving route (1 vs. 2), and narration (yes vs. no). The primary outcome variable was driver-yield behavior. Each of the ten drivers completed the factorial design, requiring eight total drives. Data were collected using a data acquisition system (DAS) designed and installed on the experimental vehicle by the Virginia Tech Transportation Institute. The DAS collected video, audio, and kinematic data. Videos were coded using a proprietary software program, Hawkeye, based on an a priori data directory. Recommendations for future autonomous vehicle research and programming are provided. / Ph. D. / To improve traffic safety and efficiency, the current study examined factors of pedestrian-vehicle interactions. Driving is a dangerous endeavor for all parties, however, pedestrians are an especially vulnerable group. Many different solutions have been suggested including; education and training of road users, high visibility law enforcement, infrastructure changes, and vehicle solutions. Of all proposed, the vehicle solution, autonomous vehicles, shows great promise in improving traffic safety. Autonomous vehicles provide an opportunity for a high degree of safety, yet, inefficiencies exist. For instance, a vehicle might stop at all crosswalks regardless of pedestrian proximity. To this end, the current study was a scientific exploration of the factors relating to pedestrian-vehicle interactions. The exploratory nature of this work provided an opportunity to provide recommendations for programming of autonomous vehicles to balance safety and efficiency.

Autonomous vehicles (AVs) are a class of safety-critical systems that are capable of decision-making and operate with little or no human intervention. For such complex systems designed to function in diverse operational domains such as rain, snow, freeway, urban roads, etc., system safety is paramount. Management of the system's safety throughout its life-cycle, from the conceptualization stage to the end of the lifecycle, is of primary importance. We describe a revision of functional safety standard ISO 26262 to support autonomous vehicles and the underlying electronic/electrical control architecture. There is a need to modify the Automotive Safety Integrity Levels (ASILs) defined in the ISO 26262 as "Controllability", a factor in determining an ASIL, is no longer applicable; the driver is no longer in a position to control the vehicle. The vehicle has taken over the responsibility of evaluating the environment and determines its next course of action to complete its current mission. These decisions have a tremendous impact on the overall safety of the system during a hazardous event and can be the difference between a successful journey and a traffic incident. To better enable the designers of such systems, we introduce a new method to assess the functional safety and derive safety goals, which are the top level safety requirement. We present a new metric-Risk Mitigation Factor to assess the decision making capability of the vehicle and to replace controllability in the ASIL definition. The case study presented highlights the advantages of using the introduced metric in defining safety goals for the autonomous vehicle. / Master of Science / Autonomous vehicles (AVs) are changing the way we perceive mobility and transportation. AVs are soon to be a part of everyday life, from giving you a ride to the office to taking children to the dentist. All the possible benefits of AVs are attainable if the systems designed are safe for use. Safety in AVs is the primary challenge in design and development. It is crucial to incorporate the principles of safety in system design from the beginning of the inception phase to the end of the lifecycle of the vehicle. The challenges for ensuring safety in AVs are enormous, from implementing the correct operation for a system to assuring that system behavior is safe in the presence of a malfunction; the scale and complexity of the systems drive the safety requirements. In the work presented, we focus on the functional safety of the underlying electrical/ electronic architecture of the vehicle, describing a revision of the automotive functional safety standard ISO 26262 for AV development. We propose to leverage the decision-making capabilities of the vehicle to assure safety in a hazardous situation.

The Nemesis tracked vehicle platform is a differentially driven Humanitarian Demining tractor developed by Applied Research Associates, Inc. The vehicle is capable of teleoperational control and is outfitted with a sensor suite used for detecting and neutralizing landmines. Because the detection process requires the vehicle to travel at speeds less than 0.5 km/h, teleoperation is a tedious process. The added autonomous capabilities of waypoint navigation and obstacle avoidance could greatly reduce operator fatigue. ARA chose to leverage Virginia Tech's experience in developing an autonomous mobility capability for the Nemesis platform. The resulting algorithms utilize the waypoint navigation techniques of Virginia Tech's JAUS (Joint Architecture for Unmanned Systems) toolkit, and a modified version of the Dynamic Expanding Zones (DEZ) algorithm developed for the 2005 DARPA Grand Challenge. The modified approach discretizes the perception zones of the DEZ algorithm and provides the added capability of obstacle memory, resulting in the Discretized Dynamic Expanding Zones with Memory (DDEZm) algorithm. These additions are necessary for efficient autonomous control of the differentially driven Nemesis vehicle. The DDEZm algorithm was coded in LabVIEW and used to autonomously navigate the Nemesis vehicle through a waypoint course while avoiding obstacles. The Joint Architecture for Unmanned Systems (JAUS) was used as the communication standard to facilitate the interoperability between the software developed at Virginia Tech and the existing Nemesis software developed by ARA. In addition to development and deployment, the algorithm has been fully documented for embedded coding by a software engineer. With embedded implementation on the vehicle, this algorithm will help to increase the efficiency of the landmine detection process, ultimately saving lives. / Master of Science

The DARPA Challenges were created in response to a Congressional and Department of Defense (DoD) mandate that one-third of US operational ground combat vehicles be unmanned by the year 2015. The Urban Challenge is the latest competition that tasks industry, academia, and inventors with designing an autonomous vehicle that can safely operate in an urban environment. A basic and important capability needed in a successful competition vehicle is the ability to detect and classify objects. The most important objects to classify are other vehicles on the road. Navigating traffic, which includes other autonomous vehicles, is critical in the obstacle avoidance and decision making processes. This thesis provides an overview of the algorithms and software designed to detect and locate these vehicles. By combining the individual strengths of laser range-finding and vision processing, the two sensors are able to more accurately detect and locate vehicles than either sensor acting alone. The range-finding module uses the built-in object detection capabilities of IBEO Alasca laser rangefinders to detect the location, size, and velocity of nearby objects. The Alasca units are designed for automotive use, and so they alone are able to identify nearby obstacles as vehicles with a high level of certainty. After some basic filtering, an object detected by the Alasca scanner is given an initial classification based on its location, size, and velocity. The vision module uses the location of these objects as determined by the ranger finder to extract regions of interest from large images through perspective transformation. These regions of the image are then examined for distinct characteristics common to all vehicles such as tail lights and tires. Checking multiple characteristics helps reduce the number of false-negative detections. Since the entire image is never processed, the image size and resolution can be maximized to ensure the characteristics are as clear as possible. The existence of these characteristics is then used to modify the certainty level from the IBEO and determine if a given object is a vehicle. / Master of Science

Autonomous vehicles offer means to complete unsafe military operations without endangering the lives of soldiers. Such solutions have fueled many efforts towards designing autonomous, or unmanned, systems. Military and academic research efforts alike continue to focus on developing these systems. While many different autonomous vehicles have been introduced, however, such complex systems have limited drive-by-wire operability. The complete process to up-fit a vehicle to fully autonomous operation involves the design, up-fit, testing and verification of many different subsystems. The objective of this thesis is to design and model an autonomous steering system requiring little modifications to an existing steering system. It is desirable to still operate the vehicle manually as well as preserve the vehicle's visual appearance. Up-fit and implementation of the designed steering system and verification of its functionality has been documented as well. Utilization of the supplied controller and software has enabled the testing and characterization of the system. The proposed design offers a solution to a wide variety of wheeled vehicles steered via the traditional and common steering wheel method. In addition, modifications have been made to an existing simulation of an unmanned vehicle in a military testbed environment (Fort Benning). The simulation accounts for the control methodology as it has been designed and tested with, which offers the ability to analyze the dynamics of the unmanned system. / Master of Science

This dissertation first conducts a study on raw-data level cooperative perception for enhancing the detection ability of self-driving systems for connected autonomous vehicles (CAVs). A LiDAR (Light Detection and Ranging sensor) point cloud-based 3D object detection method is deployed to enhance detection performance by expanding the effective sensing area, capturing critical information in multiple scenarios and improving detection accuracy. In addition, a point cloud feature based cooperative perception framework is proposed on edge computing system for CAVs. This dissertation also uses the features' intrinsically small size to achieve real-time edge computing, without running the risk of congesting the network. In order to distinguish small sized objects such as pedestrian and cyclist in 3D data, an end-to-end multi-sensor fusion model is developed to implement 3D object detection from multi-sensor data. Experiments show that by solving multiple perception on camera and LiDAR jointly, the detection model can leverage the advantages from high resolution image and physical world LiDAR mapping data, which leads the KITTI benchmark on 3D object detection. At last, an application of cooperative perception is deployed on edge to heal the live map for autonomous vehicles. Through 3D reconstruction and multi-sensor fusion detection, experiments on real-world dataset demonstrate that a high definition (HD) map on edge can afford well sensed local data for navigation to CAVs.

abstract: Autonomous Vehicles (AVs), or self-driving cars, are poised to have an enormous impact on the automotive industry and road transportation. While advances have been made towards the development of safe, competent autonomous vehicles, there has been inadequate attention to the control of autonomous vehicles in unanticipated situations, such as imminent crashes. Even if autonomous vehicles follow all safety measures, accidents are inevitable, and humans must trust autonomous vehicles to respond appropriately in such scenarios. It is not plausible to program autonomous vehicles with a set of rules to tackle every possible crash scenario. Instead, a possible approach is to align their decision-making capabilities with the moral priorities, values, and social motivations of trustworthy human drivers.Toward this end, this thesis contributes a simulation framework for collecting, analyzing, and replicating human driving behaviors in a variety of scenarios, including imminent crashes. Four driving scenarios in an urban traffic environment were designed in the CARLA driving simulator platform, in which simulated cars can either drive autonomously or be driven by a user via a steering wheel and pedals. These included three unavoidable crash scenarios, representing classic trolley-problem ethical dilemmas, and a scenario in which a car must be driven through a school zone, in order to examine driver prioritization of reaching a destination versus ensuring safety. Sample human driving data in CARLA was logged from the simulated car’s sensors, including the LiDAR, IMU and camera. In order to reproduce human driving behaviors in a simulated vehicle, it is necessary for the AV to be able to identify objects in the environment and evaluate the volume of their bounding boxes for prediction and planning. An object detection method was used that processes LiDAR point cloud data using the PointNet neural network architecture, analyzes RGB images via transfer learning using the Xception convolutional neural network architecture, and fuses the outputs of these two networks. This method was trained and tested on both the KITTI Vision Benchmark Suite dataset and a virtual dataset exclusively generated from CARLA. When applied to the KITTI dataset, the object detection method achieved an average classification accuracy of 96.72% and an average Intersection over Union (IoU) of 0.72, where the IoU metric compares predicted bounding boxes to those used for training. / Dissertation/Thesis / Masters Thesis Mechanical Engineering 2020

Autonomous vehicles (AVs) are a disruptive technology that is expected to vastly change the current transportation system. AV potential benefits in terms of safety, mobility, efficiency and other impacts types have been documented in the literature. AVs are expected to increase travel demand due to the enhanced ease of making trips and provision of mobility to people currently with travel-limiting disabilities. The potential increase in travel demand, with its attendant congestion, may probably be offset by the transportation network capacity increase due to the reduced operational headways between AVs. However, such capacity benefits can be fully realized only when AVs fully saturate the market, because operating at low headways may be unsafe for Human Driven Vehicles (HDVs). Thus, to promote AV ownership while capturing the capacity benefits of an AV-only traffic stream, the conversion of traditional lanes to AV-exclusive use is prescribed often. In the AV-exclusive lanes, the vehicles can operate at reduced headways and at higher speeds, sharply increasing throughput. However, the metric used frequently by researchers for AV-exclusive lane evaluation is the total system travel time. AV-exclusive lanes may appear to be beneficial in terms of total system travel time but may come at a cost of environmental protection and social equity, the other two elements of sustainable development. Appropriating HDV lanes for AV-exclusive use will cause congestion on HDV lanes thereby increasing their emissions. Further, the AVs benefits may be accompanied by increased cost of HDV travel, which raises questions about equity. This thesis therefore presents a sustainable AV-exclusive lane deployment strategy by formulating and solving a multicriteria bi-level optimization problem with equity-related constraints. Mathematically, the problem is described as a discrete network design problem. Recognizing the difficulty of solving this NIP hard problem, the thesis combines the active set method with heuristic conditionalities to improve computational efficiency. The thesis’s framework can be used by agencies for evaluation and decision support regarding AV-exclusive lane deployment in a manner that fosters long-term sustainability.

No description available.