Abstract

International audience; This chapter describes the emerging robotics application field of intelligent vehicles – motor vehicles that have autonomous functions and capabilities. The chapter is organized as follows:- Section 62.1 provides a motivation for why the development of intelligent vehicles is important, a brief history of the field, and the potential benefits of the technology.- Section 62.2 describes the technologies that enable intelligent vehicles to sense vehicle, environment, and driver state, work with digital maps and satellite navigation, and communicate with intelligent transportation infrastructure.- Section 62.3 describes the challenges and solutions associated with road scene understanding – a key capability for all intelligent vehicles.- Section 62.4 describes advanced driver assistance systems, which use the robotics and sensing technologies described earlier to create new safety and convenience systems for motor vehicles, such as collision avoidance, lane keeping, and parking assistance.- Section 62.5 describes driver monitoring technologies that are being developed to mitigate driver fatigue, inattention, and impairment.- Section 62.6 describes fully autonomous intelligent vehicles systems that have been developed and deployed.- Sections 62.7 and 62.8 conclude the chapter with a discussion of future prospects, and provide references to further reading and additional resources.

Abstract

This thesis investigates a method to save energy and thus also extend the range of a series-production battery electric vehicle by influencing the driving style automatically with the help of a of a cruise controller. An exploration of existing methods shows that the contextual consideration of the current and upcoming driving situation is necessary to realise safe and energy-efficient driving. This limits the appropriate approaches to online methods using updated predictions of the vehicle behaviour. It turns out that the most suitable method for the intended purpose is model-predictive control (MPC). The MPC generates controls for the accelerator pedal of the vehicle based on optimised predictions of the vehicle motion and energy consumption subject to the current and future road slope, curvature, speed limits and distance to an eventually preceding vehicle. The non-linear nature of the vehicle dynamics generally necessitates the use of a non-linear prediction model and solving a non-linear optimisation which goes along with difficulties in the online real-time implementation. However in this work - by exploiting and extending the tool sets of classical MPC - a controller based on a quadratic optimal control problem with linear constraints can be formulated that approximates the nonlinearities of the plant dynamics with equivalent accuracy as a non-linear formulation. A linear prediction model of the vehicle motion is derived by a change of the model domain from time to position and a change of variables to predict the kinetic energy of the moving vehicle instead of the driving speed. Further, a convex piece-wise linear energy consumption model is included in the inequality constraints of the problem according to the methodology of separable programming to capture the consumption characteristics of the vehicle in different operating points. In this form, real-time capability and the energy-saving potential of the presented control approach can be demonstrated by simulations of the closed loop and by implementing the controller for driving experiments. A Smart ED series-production battery electric vehicle is chosen for the practical tests and all models and parameters are identified and adapted to the characteristics of the car. In this application case, a significant energy-saving potential could be demonstrated compared to human drivers. To further reduce the computational burden and speed up the computation, the so-called move blocking method for input parameterisation of the MPC control trajectory is investigated and extended within this work to a flexible move blocking approach which enables a fast computation and at the same time high tracking performance.

Abstract

div"Due to recent advances in sensor technology and the exponential increase in computation power of electronic control units (ECUs) along with their increasing affordability, active safety and vehicle automation have become major trends in the commercial vehicle industry. New regulations for increased safety are also a major driver behind the industry's increased interest in that topic. As a result, being a crucial part of vehicle automation, steering systems had to be adapted to enable Active Steering. Consequently, commercial vehicle steering designers introduced the concept of torque and angle overlay using an electric motor in series with the conventional hydraulic steering system. However, despite the fact that these systems are becoming more prevalent in the market, they still suffer from inefficiencies intrinsic to the conventional hydraulic steering system still being used. These inefficiencies are a result of"/div""div"flow metering losses due to the use of control valves to regulate the pump flow output, as well as inside the steering gear with the use control valves to build assistance pressure."/div""div""br""/div""div""div"In this research project, we investigate the potential use of the proven pump Displacement Control (DC) technology in steering on-highway commercial vehicles. DC pumps have been shown to signicantly improve system efficiency as they allow the removal of control valves typically used to regulate "/div""div"ow [1]. Instead, the displacement of the pump can be directly controlled to vary the pump's flow rate and direction,"/div""div"and thus eliminating throttling losses. The DC technology has been successfully used in a steer-by-wire conguration for an articulated frame steering vehicle and has been shown to signicantly improve efficiency and productivity, as well as result in a reduction in fuel consumption [2]."/div""/div""div""br""/div""div""div"In this work, we propose a steer-by-wire system, using DC pump technology, for on-highway commercial vehicles, and present the dierent possible congurations in which it can be implemented. Moreover, the benets and drawbacks of the steer-by-wire system are researched and identied. Subsequently, the system is designed and validated in simulation, on laboratory test setup, as well as on a test vehicle to prove its feasibility."/div""/div""div""br""/div""div""div"Chief among the drawbacks of the steer-by-wire system is potential failures that can lead to the complete loss of the steering function of the vehicle. As a result, different possible fail-safe mechanisms are researched from which the most suitable ones are proposed to allow the steer-by-wire system to fail safely. Moreover, two of the proposed fail-safe mechanism are implemented onto the test vehicle to prove and validate their feasibility."/div""/div""div""br""/div""div""div"Furthermore, an alternative way of using displacement controlled pumps for active steering is be proposed. For this concept, we investigate the possibility of actively controlling the driver's steering effort by varying the pump displacement while maintaining the mechanical link between the steering wheel and the road wheels. If successful, this method will allow for a more efficient way of providing steering assistance as it does away with the conventional control valves used to build pressure and regulate pump flow, and thus eliminating throttling losses. This method has also the advantage of having an intrinsic fail-safe mechanism with manual steering being always possible should the hydraulic or electric systems fail."/div""/div

Abstract

ITSC 2011 : International IEEE Conference on Intelligent Transportation Systems, WASHINGTON, ETATS-UNIS, 05-/10/2011 - 07/10/2011; This paper presents the implementation of a highly automated driving system on automotive Electronic Control Units (ECUs). It integrates a perception component, which uses the combination of high-level sensors to map the environment, a co-pilot, which finds an optimal trajectory in this environment and a control component, which guides the vehicle on this trajectory. The cooperation between human and automation is managed by the driving Mode Selection and arbitration Unit (MSU) and Human-Machine Interface (HMI) components. The co-pilot and control components have been implemented on AUTOSAR-based ECUs, the other components in the RTMaps environment on a standard PC. It has been first been tested on the simulation tool SiVIC and was then transferred to a physical vehicle on test track.

Abstract

Today there is a growing interest in automotive sensor monitoring systems. One of the main challenges is to make them an effective and valuable aid in dangerous situations, improving transportation safety. The main limitation of visual aid systems is that they do not produce accurate results in critical visibility conditions, such as in presence of rain, fog or smoke. Radar systems can greatly help in overcoming such limitations. In particular, imaging radar is gaining interest in the framework of Driver Assistance Systems (DAS). In this manuscript, a new methodology able to reconstruct the 3D imaged scene and to detect the presence of multiple targets within each line of sight is proposed. The technique is based on the use of Compressive Sensing (CS) theory and produces the estimation of multiple targets for each line of sight, their range distance and their reflectivities. Moreover, a fast approach for 2D focus based on the FFT algorithm is proposed. After the description of the proposed methodology, different simulated case studies are reported in order to evaluate the performances of the proposed approach. Document type: Article

Abstract

The increase in the number of deaths due to ground traffic accidents is a global problem. In such context, the development of new vehicular technologies is considered an alternative to improve road safety. Within the field of new vehicle technologies, it is possible to find driver assistance systems. These systems interact in an active or passive way with the driver, reducing their workload by presenting information about their surroundings, which may imply the safer direction of a land vehicle. Taking into account that one of the main reasons for road traffic fatalities in the world is the lane change in a road, hereby we created a cooperative driver assistance system for the lane change, arising from the combination of a kinematic model and a probabilistic graphical one. By combining these two models, we try to improve the response in the assistance of the system, given the direct dependence of the system with a human. Due to the latter, the response of such systems cannot be deterministic in nature. One of the motivations to use probabilistic graphical models is the flexibility of this machines learning technique in modeling the problem addressed in this thesis. In addition to this contribution of applying a specific probabilistic graphical model in our assistance system, other contributions can be found in this thesis, including the development of a Driving simulation platform with a reconfigurable structure. The ability to reconfigure the structure of the driving simulator platform was of great importance for the development and evaluation of the assistance system hereby proposed in each of its stages. In addition, the decision to model a cooperative approach in our assistance system is due to the great potential of the vehicular communications with respect to improving transport safety and efficiency. The moderate cost that is being projected in vehicular communications is another relevant fact. Finally, the description and application of our assistance system model can be considered as a possibility in the area for the development of an application that needs a close response to the reality, based on the uncertainties present in the problem under consideration. O aumento no número de mortes por causa de acidentes de tráfego terrestre é um problema global. No âmbito dessa problemática, o desenvolvimento de novas tecnologias veiculares é considerado uma alternativa para melhorar a segurança viária. Dentro do domínio das novas tecnologias veiculares, é possível encontrar sistemas de assistência ao motorista. Esses sistemas interagem de maneira ativa ou passiva com o motorista, conseguindo reduzir sua carga de trabalho, apresentando informações de seu entorno, o que pode implicar uma direção mais segura de um veículo terrestre. Levando em consideração que um dos principais motivos de mortes por acidentes de tráfego terrestre no mundo é a mudança de faixa em uma pista, neste trabalho, realizamos a tarefa de criar um sistema cooperativo de assistência ao motorista para a mudança de faixa, a partir da combinação de um modelo cinemático e de um modelo gráfico probabilístico. Mediante a combinação destes dois modelos, procuramos melhorar a resposta na assistência por parte do sistema, dada a dependência direta que o sistema tem dos humanos. Por essa última razão, a resposta deste tipo de sistemas não pode ser determinística por natureza. Uma das motivações para utilizar os modelos gráficos probabilísticos é a flexibilidade da técnica de machine learning em modelar o problema abordado nesta tese. Além dessa contribuição de aplicar um modelo gráfico probabilístico específico em nosso sistema de assistência, outras contribuições podem ser encontradas nesta tese, incluindo o desenvolvimento de uma plataforma de simulação para a condução, com uma estrutura reconfigurável. A capacidade de poder reconfigurar a estrutura da plataforma de simulação foi de grande importância para o desenvolvimento e avaliação do sistema de assistência proposto nesta tese, em cada uma de suas etapas. Além disso, a decisão de modelar um enfoque cooperativo, em nosso sistema de assistência, se deve ao grande potencial que tem as comunicações veiculares com respeito à melhora da segurança e da eficiência do transporte. O custo moderado que está sendo projetado nas comunicações veiculares é outro fato relevante. A descrição e aplicação de nosso modelo final podem ser considerados mais uma possibilidade na área para o desenvolvimento de uma aplicação, que precise de uma resposta próxima da realidade, a partir das incertezas presentes no problema considerado.

Abstract

El moviment és un atribut perceptiu del cervell humà molt important. La percepció visual que fa el cervell del moviment és el procés d’inferir la velocitat i direcció dels elements d’un escenari mitjançant entrades visuals. Anàlogament, la visió per computador s’assisteix mitjançant informació del moviment de l’escena. En visió per computador, la detecció de moviment és útil per a resoldre problemes com per exemple segmentació, estimació de la profunditat, estimació de l’estructura a partir del moviment, compressió de dades o navegació entre d’altres. Aquests problemes són comuns a diferents aplicacions, com ara vídeo vigilància, navegació de robots i sistemes avançats d’assistència a la conducció (Advanced Driver Assistance Systems, ADAS). Una de les tècniques més utilitzades per a detectar moviment, és el càlcul d’optical flow. El treball tractat en aquesta tesi pretén que les formulacions d’optical flow siguin més apropiades als requeriments i condicions dels escenaris de conducció. En aquest context, es proposa una nova representació de l’espai-variant anomenada representació reverse log-polar, i es demostra que, quan s’utilitza per a ADAS, té un rendiment millor que la tradicional representació log-polar. La representació espai-variant redueix la quantitat de dades necessàries que han de ser processades. Una altra contribució important està relacionada amb l’anàlisi de la influència de les característiques específiques d’escenaris de conducció per a la precisió de l’optical flow. S’han considerat característiques tals com la velocitat del vehicle i la textura de la carretera. D’aquest estudi s’infereix que, el pes del terme de regularització s’ha d’adaptar segons una mesura d’error i per a diferents velocitats i textures de la carretera. També es mostra que la representació polar d’optical flow funciona molt millor per a escenaris de conducció on el moviment principal són translacions. Degut als requeriments d’aquest estudi, i per la manca de bases de dades es presenta una nova base de dades sintètica que conté: i) seqüències amb diferents velocitats i textures en un escenari urbà; ii) seqüències amb moviments complexos de la càmera col·locada al vehicle; i iii) seqüències amb altres vehicles en moviment dintre la mateixa escena. L’optical flow corresponent a cada seqüència s’obté mitjançant la tècnica de ray-tracing. A més a més, es presenten algunes aplicacions per a optical flow en escenaris ADAS. Per començar, proposem una tècnica robusta basada en RANSAC per estimar la línia de l’horitzó. Després, presentem una estimació de l’egomotion per a comparar la representació espai-variant proposada amb les representacions clàssiques. Com a contribució final, es proposa una modificació del terme de regularització que millora notablement els resultats per a aplicacions d’ADAS. Aquesta adaptació s’avalua mitjançant tècniques d’optical flow d’última generació. Els experiments realitzats amb una base de dades pública (KITTI) validen els avantatges d’utilitzar la modificació proposada. La percepción del movimiento es uno de los más importantes atributos del cerebro humano. La percepción visual del movimiento consiste en inferir velocidad y dirección de los elementos móviles que interactúan en una escena, mediante la interpretación de diferentes entradas visuales. Análogamente, la visión por computador hace uso de la información del movimiento en la escena. La detección de movimiento en visión por computador es útil para resolver problemas tales como: segmentación, estimación de profundidad, compresión, navegación, entre otros. Estos problemas son comunes en distintas aplicaciones, por ejemplo: video vigilancia, navegación de robots y sistemas avanzados de asistencia a la conducción (ADAS). Una de las técnicas más utilizadas para detectar movimiento es la estimación del flujo óptico. El trabajo abordado en esta tesis busca formulaciones del flujo óptico más adecuadas a las necesidades y condiciones de los escenarios de conducción. En este contexto, se propuso una novedosa representación del espacio, llamada representación inversa log-polar, la cual se demuestra que tiene un desempeño mejor que la tradicional representación logpolar para aplicaciones ADAS. Las representaciones de espacio-variante reducen la cantidad de datos a ser procesados. Otra contribución importante está relacionada con el análisis de la influencia de las características específicas de los escenarios de conducción en la precisión del flujo óptico estimado. Características tales como la velocidad del vehículo y la textura de la carretera son consideradas en el estudio. De este estudio, se infiere que el peso del término de regularización tiene que ser adaptado de acuerdo con la medida de error requerida y para diferentes velocidades y texturas de la carretera. También se concluye que la representación polar del flujo óptico es la más apropiada en escenarios de conducción, donde el movimiento predominante es la translación. Debido a las exigencias de tal estudio, y por falta de las bases de datos necesarias, se presenta un nuevo conjunto de datos sintéticos el cual contiene: i) secuencias de diferentes velocidades y texturas en un escenario urbano; ii) secuencias con movimientos complejos de la cámara dispuesta en el vehículo; y iii) secuencias con otros vehículos en movimiento en la escena. El flujo óptico correspondiente a cada secuencia es obtenido mediante una técnica de ray-tracing. Adicionalmente, se presentan algunas aplicaciones de flujo óptico en ADAS. Primeramente se propone una técnica robusta basada en RANSAC para estimar la línea de horizonte. Seguidamente se presenta una estimación del egomotion para comparar la representación de espacio-variante propuesta con los esquemas clásicos. Como contribución final, se propone una modificación en el término de regularización que mejora notablemente los resultados en las aplicaciones ADAS. Los resultados experimentales en una base de datos pública (KITTI) validan las ventajas de la utilización de la modificación propuesta. Motion perception is one of the most important attributes of the human brain. Visual motion perception consists in inferring speed and direction of elements in a scene based on visual inputs. Analogously, computer vision is assisted by motion cues in the scene. Motion detection in computer vision is useful in solving problems such as segmentation, depth from motion, structure from motion, compression, navigation and many others. These problems are common in several applications, for instance, video surveillance, robot navigation and advanced driver assistance systems (ADAS). One of the most widely used techniques for motion detection is the optical flow estimation. The work in this thesis attempts to make optical flow suitable for the requirements and conditions of driving scenarios. In this context, a novel space-variant representation called reverse log-polar representation is proposed that is shown to be better than the traditional log-polar space-variant representation for ADAS. The space-variant representations reduce the amount of data to be processed. Another major contribution in this research is related to the analysis of the influence of specific characteristics from driving scenarios on the optical flow accuracy. Characteristics such as vehicle speed and road texture are considered in the aforementioned analysis. From this study, it is inferred that the regularization weight has to be adapted according to the required error measure and for different speeds and road textures. It is also shown that polar represented optical flow suits driving scenarios where predominant motion is translation. Due to the requirements of such a study and by the lack of needed datasets a new synthetic dataset is presented; it contains: i) sequences of different speeds and road textures in an urban scenario; ii) sequences with complex motion of an on-board camera; and iii) sequences with additional moving vehicles in the scene. The ground-truth optical flow is generated by the ray-tracing technique. Further, few applications of optical flow in ADAS are shown. Firstly, a robust RANSAC based technique to estimate horizon line is proposed. Then, an egomotion estimation is presented to compare the proposed space-variant representation with the classical one. As a final contribution, a modification in the regularization term is proposed that notably improves the results in the ADAS applications. This adaptation is evaluated using a state of the art optical flow technique. The experiments on a public dataset (KITTI) validate the advantages of using the proposed modification.

Abstract

We present an approach for validation of advanced driver assistance systems, based on randomized algorithms. The new method consists of an iterative randomized simulation using adaptive importance sampling. The randomized algorithm is more efficient than conventional simulation techniques. The importance sampling pdf is estimated by a kernel density estimate, based on the results from the previous iteration. The concept is illustrated with a simple adaptive cruise control problem.

Abstract

When it comes to road safety, professional drivers find themselves under pressure in various circumstances and are also exposed to diverse risk factors. To minimize personal negative consequences – and negative consequences for road safety – KFV carried out a project on work-related road safety on behalf of and in collaboration with the AUVA. Data on driving behavior, working conditions, individual pressure, distraction, and challenges relating to driver assistance and in-vehicle information systems was gathered using naturalistic driving observations (17 professional drivers), 11 in-depth interviews, 11 mobility diaries, and 2 focus group discussions. These reveal that reduction in cognitive performance is a comprehensive problem linked both to driver assistance systems as well as other forms of distraction. Based on the project findings, measures were developed by experts to improve road safety by making driving less distracting and less exhausting.