With the rapid development of autonomous driving and artificial intelligence technology, end-to-end autonomous driving technology has become a research hotspot. This thesis aims to explore the application of deep reinforcement learning in the realizing of end-to-end autonomous driving. We built a deep reinforcement learning virtual environment in the Carla simulator, and based on it, we trained a policy model to control a vehicle along a preplanned route. For the selection of the deep reinforcement learning algorithms, we have used the Proximal Policy Optimization algorithm due to its stable performance. Considering the complexity of end-to-end autonomous driving, we have also carefully designed a comprehensive reward function to train the policy model more efficiently. The model inputs for this study are of two types: firstly, real-time road information and vehicle state data obtained from the Carla simulator, and secondly, real-time images captured by the vehicle's front camera. In order to understand the influence of different input information on the training effect and model performance, we conducted a detailed comparative analysis. The test results showed that the accuracy and significance of the information has a significant impact on the learning effect of the agent, which in turn has a direct impact on the performance of the model. Through this study, we have not only confirmed the potential of deep reinforcement learning in the field of end-to-end autonomous driving, but also provided an important reference for future research and development of related technologies.

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

No description available.

No description available.

The ability to accurately map and localize relevant objects surrounding a vehicle is an important task for autonomous vehicle systems. Currently, many of the environmental mapping approaches rely on the expensive LiDAR sensor. Researchers have been attempting to transition to cheaper sensors like the camera, but so far, the mapping accuracy of single-camera and dual-camera systems has not matched the accuracy of LiDAR systems. This thesis examines depth estimation algorithms and camera configurations of a triple-camera system to determine if sensor data from an additional perspective will improve the accuracy of camera-based systems. Using a synthetic dataset, the performance of a selection of stereo depth estimation algorithms is compared to the performance of two triple-camera depth estimation algorithms: disparity fusion and cost fusion. The cost fusion algorithm in both a multi-baseline and multi-axis triple-camera configuration outperformed the environmental mapping accuracy of non-CNN algorithms in a two-camera configuration.

The category of life is considered central to the heterogeneous field known as Italian thought or Italian theory. Its centrality helps explain the outsized role that Italian thinkers like Giorgio Agamben, Rosi Braidotti, Roberto Esposito, and Toni Negri play in international conceptualizations of biopolitics. Scholars have attempted to trace the roots of this emphasis on life back to thinkers such as Vico and Croce, Italian Marxist traditions such as workerism, “imports” like Heideggerian ontology and Foucauldian critique, and even Italy’s geography. These histories fail to interrogate the paradox that Italian thought usually deals with life in abstract terms, rather than with real, embodied lives. Styles of Existence, Italy 1961–1982 offers an alternative genealogy of Italian thought that focuses on the role that philology played in transforming conceptions of life and self in postwar Italy. It argues that the poet and filmmaker Pier Paolo Pasolini and art critic and feminist Carla Lonzi show us what living looks like by applying the tools and concepts of interpretation and criticism they acquired as artists and critics to their own lives. It makes the case for their inclusion in the unofficial canon of Italian thought, and for acknowledging the debts that later philosophical treatments of life owe to Pasolini and Lonzi’s existential attempts to overcome the distance between theory and praxis. Pasolini and Lonzi, both well-known for their polemical contributions to debates about politics, gender, and sexuality in Italy’s long 1968, are discussed here together for the first time. Styles of Existence lays out the theoretical tenets, preferred methodologies, and historical arcs of their life philologies, tracing them across an array of sources including diaries, screenplays, television talk shows, and newspaper columns. Both authors’ projects are examined from a comparatist perspective, which means that they are situated in Pasolini and Lonzi’s cultural and discursive contexts as Marxist and feminist intellectuals, respectively, and in relation to contemporaneous domestic and international trends and debates. Responding to a request by Pasolini that his works be read philologically, chapter one proposes a philological rereading of his corpus that takes into account his love for space and dedication to the irrational. Proposing the notion of “lunar hermeneutics” as a conceptual frame, it demonstrates that Pasolini incorporates tools from philology and stylistic criticism in his social critique and filmmaking in response to changing global and national political landscapes in the late 1950s and early 1960s, and especially the developments of the space race. Chapter two elaborates the features of Pasolini’s project of “Marxist linguistics” in the mid-1960s as a political answer to rapid industrialization and globalization, demonstrating that Pasolini expands the scope of lunar hermeneutics with contributions from semiotics and insights from his work as a filmmaker. Close readings of Pasolini’s aesthetic writings in Empirismo eretico (1972) and his film Uccellacci e uccellini (1966) illustrate the importance of cinema to his revised theory of language and understanding of self. Chapter three examines Pasolini’s collection of political writings, Scritti corsari (1975), as an example of Auerbachian-inspired Weltliteratur, showing that the work is designed as a philological exercise dedicated to the critical preservation of human forms of life threatened with extinction. Turning to Lonzi, chapter four provides the first theoretical and historical account of autocoscienza or self-consciousness making, the feminist, relational practice that Lonzi developed with other members of the group Rivolta femminile in the early 1970s. Lonzi formulates autocoscienza as a subversive mediation of critical and postcolonial theory as well as of modern art, and envisions an “unforeseen subject” who refuses to comply with the misogyny and inequalities inherent to prevailing models of liberational subjectivity. Chapter five reassesses Lonzi’s rejection of Hegelian and psychoanalytic theories of recognition, and her engagement with Alexander Kojève’s anthropomorphizing rendition of Hegel, to argue that autocoscienza provides its own affirmative feminist theory and practice of recognition focused on listening and responsiveness among equals. Chapter six considers the diary’s central role in Lonzi’s philological project of self by linking it to autocoscienza and her theory of clitorality. It argues that the sexed dimension of autocoscienza is what makes viable a transition from theory to praxis, and from emphasis on the collective to the self. By focusing on the diary, it restores the contributions of “Sara,” another Rivolta member, and the influence of hagiographical writings on Lonzi’s conception of female freedom. Finally, chapter seven unearths Lonzi’s obsessive “dialogue” with Pasolini in her “feminist diary” Taci, anzi parla [Hush, No Speak] (1978) as a case study in the practice of autocoscienza. Lonzi’s disagreements with Pasolini about culture, sexuality, and women’s rights, and their largely overlapping views on freedom and expression, are situated in the context of Italian debates about abortion in the mid-1970s. This chapter argues that Lonzi’s relation to Pasolini transforms her understanding of self and helps her refine and recalibrate the goals of autocoscienza. In conceiving of the self and selfhood in philological rather than philosophical terms, Pasolini and Lonzi challenge theories of the subject predominant in critical theory and offer precursors to contemporary concepts like Agamben’s homo sacer. Their aesthetics of existence require a reconsideration of the scope of philology in the twentieth century, the parameters of political theory, the legacy and historiography of Italy’s long ’68, and our understanding of what it means to live a meaningful human life. The detailed recovery of Lonzi’s intensive engagement with Pasolini and his work, finally, points to an unlikely source of influence on radical Italian feminism.

El objetivo general de la presente investigación fue trazar la formación, trayectoria artística y de vida de lxs artistas Carla Montalvo y Jesús María Álvarez y analizar la crítica al discurso pastoral que desarrollan en sus lenguajes, temáticas y prácticas estéticas, a través del análisis de las performances “Bosque Blanco” y “Arequipa es Choqollo”. Específicamente, se buscó indagar sobre cómo estxs artistas representan las sexualidades no hegemónicas en sus prácticas estéticas del performance mediante el uso de la iconografía cristiana y de qué manera su experiencia personal se relaciona con su preocupación por hacer uso de iconografía cristiana para cuestionar la subjetividad sexual, empleando el giro icónico y el testimonio con este fin. Para ello se aplicó un enfoque metodológico cualitativo, narrativo y se utilizaron guías de entrevistas biográficas/monotemáticas adecuadas a cada caso para profundizar en la especificidad y diferencia de cada unx. Asimismo, se aplicaron fichas de análisis formal y visual de las performances en vídeo e imagen. / The general objective of this research was to trace the training, artistic and life trajectory of the artists Carla Montalvo and Jesús María Álvarez and analyze the critique of pastoral discourse that they develop in their languages, themes and aesthetic practices of performance: "Bosque Blanco" and “Arequipa is Choqollo”. Specifically, we seek to investigate how these artists represent non-hegemonic sexualities in their aesthetic practices of performance using Christian iconography and how their personal experience relates to their concern to use it in order to question sexual subjectivity. With this objective, we used the iconic turn and the testimony. Likewise, we employed a narrative qualitative methodological approach and biographical interviews, appropriate to each case, to delve into the specificity and difference of each one. In addition, we applied formal and visual analysis sheets of video and image of the performances.

The field of autonomous driving is as active as it has ever been, but the reality where an autonomous vehicle can drive on all roads is currently decades away. Instead, using an on-the-fly learning method, such as qHebb learning, a system can,after some demonstration, learn the appearance of any road and take over the steering wheel. By training in a simulator, the amount and variation of training can increase substantially, however, an on-rails auto-pilot does not sufficiently populate the learning space of such a model. This study aims to explore concepts that can increase the variance in the training data whilst the vehicle trains online. Three computationally light concepts are proposed that each manages to result in a model that can navigate through a simple environment, thus performing better than a model trained solely on the auto-pilot. The most noteworthy approach uses multiple thresholds to detect when the vehicle deviates too much and replicates the action of a human correcting its trajectory. After training on less than 300 frames, a vehicle successfully completed the full test environment using this method. / Autonom körning är ett aktivt område inom både industrin och forskarvärlden, men ännu är en verklighet där förarlösa fordon kan ta sig fram oavsett väg, decennier bort. Istället kan man genom att använda en adaptiv inlärningsmodell som qHebb learning uppnå ett system som kan ta sig fram självmant på alla vägar, efter en initial inlärningsperiod. Genom att använda en simulator skulle möjligheten att träna en sådan modell öka avsevärt, likaså variationen av vägtyper och det omgivande landskapet. Dock klarar inte en enformig autopilot att fylla modellens lärningsrymd. Detta arbete stävar efter att utforska koncept som kan öka variationen på träningsdatan, medan fordonet kör. Tre prestandalätta metoder presenteras som alla överträffar autopiloten och resulterar i en modell som lärt sig att följa en väg längs kurvor och raksträckor. Det främsta konceptet använder sig av två tröskelvärden för att korrigera fordonets styrning då den avviker för mycket från den korrekta rutten. Efter träning på färre än 300 bilder lyckas denna metod slutföra alla testsegment utan kollision.

Die Dresdner Rede von Carla Del Ponte wurde ohne Manuskript frei gehalten und war stark geprägt von der mehrsprachigen Herkunft der gebürtigen Tessinerin. Auch bestand ein wesentlicher Teil ihres Auftritts aus einer Interviewsituation, bei der das Publikum Fragen an die Rednerin richten konnte. Wir haben daher für Frau Del Pontes Rede auf den üblichen Textabdruck an dieser Stelle verzichtet. Sie können sie jedoch als Audiodatei jederzeit und in voller Länge auf unser Internetseite (www.staatsschauspiel-dresden.de) nachhören.

This project’s goal was to assess both the challenges of implementing the Deep Q-Learning algorithm to create an autonomous car in the CARLA simulator, and the driving performance of the resulting model. An agent was trained to follow waypoints based on two main approaches. First, a camera-based approach, which allowed the agent to gather information about the environment from a camera sensor. The image along with other driving features were fed to a convolutional neural network. Second, an approach focused purely on following the waypoints without the camera sensor. The camera sensor was substituted for an array containing the agent’s angle with respect to the upcoming waypoints along with other driving features. Even though the camera-based approach was the best during evaluation, no approach was successful in consistently following the waypoints of a straight route. To increase the performance of the camera-based approach more training episodes need to be provided. Furthermore, both approaches would greatly benefit from experimentation and optimization of the model’s neural network configuration and its hyperparameters.