The field of automated vehicle demands outstanding reliability figures to be matched by the artificially driving agents. The software architectures commonly used originate from decades of automation engineering, when robots operated only in confined environments on predefined tasks. On the other hand, autonomous driving represents an “into the wild” application for robotics. The architectures embraced until now may not be sufficiently robust to comply with such an ambitious goal. This research activity proposes a bio-inspired sensorimotor architecture for cognitive robots that addresses the lack of autonomy inherent to the rules-based paradigm. The new architecture finds its realization in an agent for autonomous driving named “Co-driver”. The Agent synthesis was extensively inspired by biological principles that contribute to give the Co-driver some cognitive abilities. Worth to be mentioned are the “simulation hypothesis of cognition” and the “affordance competition hypothesis”. The former is mainly concerned with how the Agent builds its driving skills, whereas the latter yields an interpretable agent notwithstanding the complex behaviors produced. Throughout the essay, the Agent is explained in detail, together with the bottom-up learning framework adopted. Overall, the research effort bore an effectively performing autonomous driving agent whose underlying architecture provides considerable adaptation capability. The thesis also discusses the aspects related to the implementation of the proposed ideas into a versatile software that supports both simulation environments and real vehicle platforms. The step-by-step explanation of the Co-driver is made up of theoretical considerations supported by working simulation examples, some of which are also released open-source to the research community as a driving benchmark. Eventually, guidelines are given for future research activities that may originate from the Agent and the hierarchical training framework devised. First and foremost, the exploitation of the hierarchical training framework to discover optimized longer-term driving policies.

In the present PhD thesis an optimal problem suite is proposed as benchmark for the test of numerical solvers. The problems are divided in four categories, classic, singular, constrained and hard problems. Apart from the hard problems, where it is not possible to give the analytical solution but only some details, all other problems are supplied with the derivation of the solution. The exact solution allows a precise comparison of the performance of the considered software. All of the proposed problems were taken from published papers or books, but it turned out that an analytic exact solution was only rarely provided, thus a true and reliable comparison among numerical solvers could not be done before. A typical wrong conclusion when a solver obtains a lower value of the target functional with respect to other solvers is to claim it better than the others, but it is not recognized that it has only underestimated the true value. In this thesis, a cutting edge application of optimal control to vehicles is showed: the optimization of the lap time in a race circuit track considering a number of realistic constraints. A new algorithm for path planning is completely described for the construction of a quasi G2 fitting of the GPS data with a clothoid spline in terms of the G1 Hermite interpolation problem. In particular the present algorithm is proved to work better than state of the art algorithms in terms of both efficiency and precision.

This work is focused on the development of controllable suspension systems for heavy-duty vehicles, in particular for agricultural tractors. In this field the research activity is not complete, as confirmed by the lack of scientific literature and for the few examples of commercial application for this kind of vehicles present in the market. For off-highway vehicles the load conditions can vary considerably and have an effect on the dynamic behaviour of the vehicle. Moreover, in many cases (such as tractors in agriculture), only the front axle is provided with a suspension. Typical applications of suspensions in off-highway industry include the cabin suspension (known as secondary suspension system) and the front axle suspension (known as primary suspension system). Up to now, the performance improvements have been reached through new solutions developed for the secondary systems, while the primary systems are generally implemented with passive systems, due to economical motivations and their limited energy demand. Obviously, such technical solutions partially satisfy the system requirements. Moreover, during the past few years there has been an increasing demand in power capabilities, loads and driving speeds of heavy duty vehicles. Therefore, off-highway vehicle manufacturers have shown their interest in employing controllable suspension, assumed as a potential way to reach the desired dynamic performances. The main targets of this activity is the study of the dynamical behaviour of agricultural tractors and the design of a cost-effective controllable suspension, capable to adapt the tractor dynamical behaviour, under different operating conditions. This work is part of a collaboration between Dana Corp. and the University of Trento. The main objective consists in the acquisition of competence in relation to the dynamic control of the vehicle. In particular the development of mechatronic systems according to the Model Based Design approach and the rapid prototyping of control algorithms. On this purpose, a simulation and experimental system was developed, for the testing of suspension systems and control algorithms for primary suspension systems. The first part of the thesis investigates the state of the art of the scientific literature of suspension systems for heavy duty vehicles, referring to different technologies and control solutions. In particular, attention was focused on the analysis and experimental characterization of commercial applications for this kind of vehicles present in the market. In the second part of the thesis the design development of a hydro-pneumatic suspension system is presented. The design of the control algorithms is based on the development of different multibody models of the actual tractor, including the pitch motion of the sprung mass, the load transfer effects during braking and forward-reverse maneuvers and the non-linear dynamics of the system. For an advanced analysis, a novel thermo-hydraulic model of the hydraulic system has been implemented. Several damping controls are analyzed for the specific case study. Therefore, the most promising damping strategy is integrated with other control functions, namely a self-leveling control, an original control algorithm for the reduction of the pitch motion, an anti-impact system for the hydraulic actuator and an on-line adaptation scheme, which preserves an optimal damping ratio of the suspension, even against large variations in operating conditions. According to the system requirements, the control is firstly integrated with other functionalities, such as the calibration of the suspension set-points and the procedures for the lock of the suspension. Finally, in accordance to the industrial product development, the control scheme is redefined in a Finite State Machine, useful for the subsequent generation of the ECU (Electronic Control Unit) Embedded Code. The final section of this work presents the development of an industrial prototype of suspension system, composed of a hydraulic suspension unit and a controller (hardware and software units). The prototype is tested by using a suspension bench test and Rapid Prototyping Tools for testing real-time control systems. Conclusions and final remarks and are reported in the last section.

To cope with the increasing demand of a more sustainable mobility, the main Original Equipment Manufacturers are producing vehicles equipped with hybrid propulsion systems that increase the overall vehicle efficiency and mitigate the emission problem at a local level. The newly gained degrees of freedom of the hybrid powertrain need to be handled by advanced energy management techniques that allow to fully exploit the system capabilities. In this thesis we propose an optimal control approach to the solution of the energy management problem, putting emphasis on the importance of accurate models for the reliability of the optimization solution. In the first part of the thesis we address the energy management problem for a hybrid electric vehicle, including the mitigation of the battery aging mechanisms. We show that, with an optimal management strategy, we could extend the battery life up to 25% for some driving cycles while keeping the fuel savings performance substantially unaltered. In the second part of the thesis we focus on the hydrostatic hybrid transmission, a different hybridization solution that is able to fulfill the high power demand of heavy duty off-highway vehicles. Also in this case, we formulate the energy management problem as an optimal control problem, dealing with the complexity introduced by the discrete valve actuations in the framework of mixed-integer optimal control. We show that, using hydraulic accumulators to recover energy from the regenerative braking, we could reduce fuel consumption up to 13% for a typical driving cycle. In the third and last part of the thesis we show how the optimization approach can be used to systematically design and calibrate control algorithms, casting the calibration problem into a Linear Matrix Inequality. We first develop a non-overshooting closed-loop control for the actuation pressure of a wet clutch, proving the effectiveness of the control on an experimental setup. Finally, we focus on the design of a dead-zone based kinematic observer for the estimation of the lateral velocity of a road vehicle. The structure of the observer presents good noise rejection performance, allowing for the selection of a higher observer gain that improves the estimation accuracy.

The challenge of implementing and executing a legal contract in a machine has been gaining significant interest recently with the advent of blockchain, smart contracts, LegalTech and IoT technologies. Popular software engineering methods, including agile ones, are unsuitable for such outcome-critical software. Instead, formal specifications are crucial for implementing smart contracts to ensure they capture the intentions of stakeholders, also that their execution is compliant with the terms and conditions of the original natural-language legal contract. This thesis concerns supporting the semi-automatic generation of formal specifications of legal contracts written in Natural Language (NL). The main contribution is a framework, named Contratto, where the transformation process from NL to a formal specification is subdivided into 5 steps: (1) identification of ambiguous terms in the contract and manual disambiguation; (2) structural and semantic annotation of the legal contract; (3) discovery of relationships among the concepts identified in step (2); (4) formalization of the terms used in the NL text into a domain model; (5) generation of formal expressions that describe what should be implemented by programmers in a smart contract. A systematic literature review on the main topic of the thesis was performed to support the definition of the framework. Requirements were derived from standard business contracts for a preliminary implementation of tools that support the transformation process, particularly concerning step (2). A prototype environment was proposed to semi-automate the transformation process although significant manual intervention is required. The preliminary evaluation confirms that the annotation tool can perform the annotation as well as human annotators, albeit novice ones.

Recent advancements in time-optimal trajectory planning, control, and state estimation for autonomous vehicles have paved the way for the emerging field of autonomous racing. In the last 5-10 years, this form of racing has become a popular and challenging testbed for autonomous driving algorithms, aiming to enhance the safety and performance of future intelligent vehicles. In autonomous racing, the main goal is to develop real-time algorithms capable of autonomously maneuvering a vehicle around a racetrack, even in the presence of moving opponents. However, as a vehicle approaches its handling limits, several challenges arise for online trajectory planning and control. The vehicle dynamics become nonlinear and hard to capture with low-complexity models, while fast re-planning and good generalization capabilities are crucial to execute optimal maneuvers in unforeseen scenarios. These challenges leave several open research questions, three of which will be addressed in this thesis. The first explores developing accurate yet computationally efficient vehicle models for online time-optimal trajectory planning. The second focuses on enhancing learning-based methods for trajectory planning, control, and state estimation, overcoming issues like poor generalization and the need for large amounts of training data. The third investigates the optimality of online-executed trajectories with simplified vehicle models, compared to offline solutions of minimum-lap-time optimal control problems using high-fidelity vehicle models. This thesis consists of four parts, each of which addresses one or more of the aforementioned research questions, in the fields of time-optimal vehicle trajectory planning, control and state estimation. The first part of the thesis presents a novel artificial race driver (ARD), which autonomously learns to drive a vehicle around an obstacle-free circuit, performing online time-optimal vehicle trajectory planning and control. The following research questions are addressed in this part: How optimal is the trajectory executed online by an artificial agent that drives a high-fidelity vehicle model, in comparison with a minimum-lap-time optimal control problem (MLT-OCP), based on the same vehicle model and solved offline? Can the artificial agent generalize to circuits and conditions not seen during training? ARD employs an original neural network with a physics-driven internal structure (PhS-NN) for steering control, and a novel kineto-dynamical vehicle model for time-optimal trajectory planning. A new learning scheme enables ARD to progressively learn the nonlinear dynamics of an unknown vehicle. When tested on a high-fidelity model of a high-performance car, ARD achieves very similar results as an MLT-OCP, based on the same vehicle model and solved offline. When tested on a 1:8 vehicle prototype, ARD achieves similar lap times as an offline optimization problem. Thanks to its physics-driven architecture, ARD generalizes well to unseen circuits and scenarios, and is robust to unmodeled changes in the vehicle’s mass. The second part of the thesis deals with online time-optimal trajectory planning for dynamic obstacle avoidance. The research questions addressed in this part are: Can time-optimal trajectory planning for dynamic obstacle avoidance be performed online and with low computational times? How optimal is the resulting trajectory? Can the planner generalize to unseen circuits and scenarios? At each planning step, the proposed approach builds a tree of time-optimal motion primitives, by performing a sampling-based exploration in a local mesh of waypoints. The novel planner is validated in challenging scenarios with multiple dynamic opponents, and is shown to be computationally efficient, to return near-time-optimal trajectories, and to generalize well to new circuits and scenarios. The third part of the thesis shows an application of time-optimal trajectory planning with optimal control and PhS-NNs in the context of autonomous parking. The research questions addressed in this part are: Can an autonomous parking framework perform fast online trajectory planning and tracking in real-life parking scenarios, such as parallel, reverse and angle parking spots, and unstructured environments? Can the framework generalize to unknown variations in the vehicle’s parameters and road adherence, and operate with measurement noise? The autonomous parking framework employs a novel penalty function for collision avoidance with optimal control, a new warm-start strategy and an original PhS-NN for steering control. The framework executes complex maneuvers in a wide range of parking scenarios, and is validated with a high-fidelity vehicle model. The framework is shown to be robust to variations in the vehicle’s mass and road adherence, and to operate with realistic measurement noise. The fourth and last part of the thesis develops novel kinematics-structured neural networks (KS-NNs) to estimate the vehicle’s lateral velocity, which is a key quantity for time-optimal trajectory planning and control. The KS-NNs are a special type of PhS-NNs: their internal structure is designed to incorporate the kinematic principles, which enhances the generalization capabilities and physical explainability. The research questions addressed in this part are: Can a neural network-based lateral velocity estimator generalize well when tested on a vehicle not used for training? Can the network’s parameters be physically explainable? The approach is validated using an open dataset with two race cars. In comparison with traditional and neural network estimators of the literature, the KS-NNs improve noise rejection, exhibit better generalization capacity, are more sample-efficient, and their structure is physically explainable.

Mobile assistive robotics can play a key role to improve the autonomy and lifestyle of patients. In this context, RoboEye project aims to support people affected by mobility problems that range from very impairing pathologies (like ALS, amyotrophic lateral sclerosis) to old age. Any severe motor disability is a condition that limits the capability of interacting with the environment, even the domestic one, caused by the loss of the control on our own mobility. Although these pathologies are relatively rare, the number of people affected by this disease are increasing during the years. The focus of this project is the restore of persons’ mobility using novel technologies based on the gaze on a power wheelchair designed to enable the user to move easily and autonomously inside his home. A novel and intuitive control system was designed to achieve such a goal, in which a non-invasive eye tracker, a monitor, and a 3D camera represent some of the core elements. The developed prototype integrates, on a standard power wheelchair, functionalities from the mobile robotics field, with the main benefit of providing to the user two driving options and comfortable navigation. The most intuitive, and direct, modality foresees the continuous control of the frontal and angular velocities of the wheelchair by gazing at different areas of the monitor. The second, semi-autonomous, enables the navigation toward a selected point in the environment by just pointing and activating the wished destination while the system autonomously plans and follows the trajectory that brings the wheelchair there. The main goal is the development of shared control, combining direct control by the user with the comfort of autonomous navigation based on augmented reality markers. A first evaluation has been performed on a real test bed where specific motion metrics are evaluated. The designs of the control structure and driving interfaces were tuned thanks to the testing of some volunteers, habitual users of standard power wheelchairs. The driving modalities, especially the semi-autonomous one, were modelled and qualified to verify their efficiency, reliability, and safety for domestic usage.