Online planning and execution of minimum-time maneuvers on three-dimensional (3D) circuits is an open challenge in autonomous vehicle racing. In this paper, we present an artificial race driver (ARD) to learn the vehicle dynamics, plan and execute minimum-time maneuvers on a 3D track. ARD integrates a novel kineto-dynamical (KD) vehicle model for trajectory planning with economic nonlinear model predictive control (E-NMPC). We use a high-fidelity vehicle simulator (VS) to compare the closed-loop ARD results with a minimum-lap-time optimal control problem (MLT-VS), solved offline with the same VS. Our ARD sets lap times close to the MLT-VS, and the new KD model outperforms a literature benchmark. Finally, we study the vehicle trajectories, to assess the re-planning capabilities of ARD under execution errors. A video with the main results is available as supplementary material.

In this work, we present a novel approach to bias the driving style of an artificial race driver (ARD) for online time-optimal trajectory planning. Our method leverages a nonlinear model predictive control (MPC) framework that combines time minimization with exit speed maximization at the end of the planning horizon. We introduce a new MPC terminal cost formulation based on the trajectory planned in the previous MPC step, enabling ARD to adapt its driving style from early to late apex maneuvers in real-time. Our approach is computationally efficient, allowing for low replan times and long planning horizons. We validate our method through simulations, comparing the results against offline minimum-lap-time (MLT) optimal control and online minimum-time MPC solutions. The results demonstrate that our new terminal cost enables ARD to bias its driving style, and achieve online lap times close to the MLT solution and faster than the minimum-time MPC solution. Our approach paves the way for a better understanding of the reasons behind human drivers' choice of early or late apex maneuvers.

This paper presents kinematics-structured neural networks (KS-NN) for the lateral speed estimation of vehicles. The internal structure of the networks is designed to incorporate the kinematic principles, enhancing the physical explainability and generalization capacity. Both the internal structure and training method are devised for better generalization performance. Various linear and nonlinear variants of our estimator are assessed for accuracy and robustness. The approach is validated using an openly accessible dataset with two race cars. The performance of the novel networks is evaluated against Luenberger, neural network, factor graph and Kalman filter estimators from the literature. In comparison with a Luenberger kinematic observer, our networks improve noise rejection, and overcome the well-known observability problem for low yaw rates. Compared to existing neural network estimators, our networks exhibit better generalization capacity, are more sample-efficient, require fewer learnable parameters, and their structure is physically explainable.

In this paper, we present a real-time non-linear model-predictive control (NMPC) framework to perform minimum-time motion planning for autonomous racing cars. We introduce an innovative kineto-dynamical vehicle model, able to accurately predict non-linear longitudinal and lateral vehicle dynamics. The main parameters of this vehicle model can be tuned with only experimental or simulated maneuvers, aimed to identify the handling diagram and the maximum performance G-G envelope. The kineto-dynamical model is adopted to generate on-line minimum time trajectories with an indirect optimal control method. The motion planning framework is applied to control an autonomous 1:8 RC vehicle near the limits of handling along a test circuit. Finally, the effectiveness of the proposed algorithms is illustrated by comparing the experimental results with the solution of an off-line minimum-time optimal control problem.

The work describes the contribution of SAFESTRIP EU project technology to the implementation of the Dynamic Local Map used by C-ITS safety applications. The road strips developed in SAFESTRIP are able to detect and estimate the longitudinal and lateral position of detected vehicle at lane level. This is exploited by many existing and new C-ITS applications. Here a Cooperative Intersection Support application is described and used as example to explain the concept and highlight the benefit put forward by the road strips informations.

Real-time planning of feasible motion, and the accurate tracking of that motion are key aspects of autonomous vehicles. Various planning and lateral control algorithms have been proposed in the literature. However, no experimental comparison has been carried out to confront the performance of different algorithms. In this work some of the most popular algorithms have been experimentally tested to drive a scaled vehicle model along a track. A new algorithm for path tracking based on clothoid curves is here proposed and experimentally validated. The same curves are also used in a proposed new path planning algorithm. This planning is compared to the off-line solution of an optimal control problem. The results of the comparison and the validations are then reported and discussed.

Assistive and rehabilitation robots are designed in the attempt to alleviate the work of the therapists and to accelerate the rehabilitation of the patients. Including accurate descriptions of the human body dynamics into the control loop of these robots can lead to the creation of smoother human-robot interfaces. In this paper we present: 1) a torque-driven musculoskeletal model of the sit-to-stand movement, 2) the optimal control (OC) solution of the corresponding predictive dynamics and 3) the model predictive control (MPC) solution that simulates how the human model interacts with a simple robot model. The model is a planar and symmetric representation of the major joints involved in the sit-to-stand movement: ankle, knee, hip, shoulder, elbow and neck. The seat has been modelled as a contact force, reacting like a spring-damper in the vertical direction and as a friction along the horizontal direction. Experimental data collected on a single subject provided the reference for qualitative movement comparison. The movement predicted by the OC exhibits the major characteristics of the real movement (e.g. preparation phase, joint torque and articular angle patterns). The MPC framework allowed us to simulate the reaction of the musculoskeletal model to an external force provided by a robot. This method could be used in the future in the design of specific target forces for assistive robot strategies and smooth human-robot interfaces.

In the design of rehabilitation robots, it is important to accurately describe the interaction between the body of the patient and the hand of the therapist. Traditional methods based on variable impedance and “help as needed” support do not have the ability to completely understand how the functional characteristics of the musculoskeletal system determine a movement pattern. The disturbance observer (DOB) is a robust tool widely used to estimate external disturbances and system uncertainties frequently embedded in rehabilitation robots to estimate the human effort. On the other hand, optimal control (OC) is the main tool used to model the human movement realisation. Despite the potential that DOB/OC-based robots can hold, they are poorly investigated because the modelling complexity of the constrained human movement. Therefore our goal was to simulate the interaction between a musculoskeletal model driven by an OC algorithm and a DOB based robot. The constrained movement has been simulated with a closed loop resembling the afferent feedback of the sensorimotor system. A inner closed loop with higher updating frequency, was used to model the superior ability of the robot to react to external forces. The simulations revealed that a DOB/OC-based rehabilitation robot could be effective in: 1) guiding the patient during very specific movements while taking into account muscle disorders and joint mobility and 2) designing more precise and effective rehabilitation robots that could target specific muscle groups.

This paper proposes a power management strategy for an hybrid electrical vehicle based on the Non-linear Model Predictive Control (NLMPC) that uses an equivalent consumption cost to control the state of charge of the battery. The predictive control is formulated as a repeated solution of a finite horizon minimum consumption problem which respects input and state constraints and vehicle dynamics also including the efficiency of the gear box. The reference speed and acceleration in the prediction step of NLMPC horizon is obtained by integrating forward the dynamic equations of the vehicle model with a fast semi-analytical method that does not use information about the past behaviour of the vehicle. The corresponding demanded torque is then optimally split between the two energy sources as solution of NLMPC and used in each instant for the definition of the power management strategy. The proposed NLMPC is tested on a simplified driver simulator of the hybrid vehicle and the on-line results are compared both with conventional Adaptive-Equivalent Consumption Minimisation Strategy (AECMS) strategies and with the global optimal strategy off-line computed that serves as benchmark.

This position paper introduces the concept of artificial “co-drivers” as an enabling technology for future intelligent transportation systems. In Sections I and II, the design principles of co-drivers are introduced and framed within general human-robot interactions. Several contributing theories and technologies are reviewed, specifically those relating to relevant cognitive architectures, human-like sensory-motor strategies, and the emulation theory of cognition. In Sections III and IV, we present the co-driver developed for the EU project interactIVe as an example instantiation of this notion, demonstrating how it conforms to the given guidelines. We also present substantive experimental results and clarify the limitations and performance of the current implementation. In Sections IV and V, we analyze the impact of the co-driver technology. In particular, we identify a range of application fields, showing how it constitutes a universal enabling technology for both smart vehicles and cooperative systems, and naturally sets out a program for future research.

A prototype for a supervising controller for machining applications is here proposed. The controller relies on the definition of an optimal control problem that aims at calculating the sequence of controls (feed rate and tool speed) that minimize a multi-objective target function. The target function allows to selectively prioritize terms related to the productivity, energy consumption, tool wear, and surface quality, by individually setting their relative weights (the case of all equal weights represents a balanced optimization.) The implementation of the proposed system on a real machine tool is briefly outlined, and the results of real machining tests are reported and compared to those obtained by typical machining on the same machine tool.

In this paper, an experimental vehicle developed at the University of Trento, Italy is illustrated. For this vehicle, the raw data of the engine torque is estimated from the experimental longitudinal velocity and acceleration of the vehicle, obtained from a sequence of automated maneuvers. Then, a suitable polynomial parametrization of the engine torque map is presented, which allows for an elegant formulation of the least squares parameter identification. Finally, a control law based on a backstepping approach is proposed, that globally asymptotically stabilizes the nonlinear dynamics to the reference speed setpoint. The proposed control law is appealing because it induces a linear relation between the reference and the actual speed and its parameters can be tuned following a PD approach. Preliminary experimental results match somewhat the predicted behavior of the simulation analysis of the proposed controller.

This paper aims at stimulating the discussion on the future of Intelligent Vehicles. It is a position paper, indicating converging technologies that, in our opinion, will have to be used in future Intelligent Vehicles. We present a vision according to which Intelligent Vehicles will evolve into Human-peer Robots, here called Co-Drivers. Co-Drivers will be able to “understand” human drivers and to form symbiotic systems with them. The general architecture of Co-Drivers, the building blocks and the technologies that are needed to bring them to life are discussed, pointing out which parts have been already researched and which gaps still remain. We clarify what “understanding driver” actually means and how a joint system can be obtained. The paper will identify research needs and paths, and hopefully trigger interest.

This paper reports a novel intersection support (IS) system for motorcycles developed through the SAFERIDER project (IS). The IS function described is built on a receding horizon approach that is designed for a set of predefined intersection scenarios. In the receding horizon scheme, a nonlinear optimal control problem is repetitively solved in real time, yielding a reference motion plan. The initial value of the longitudinal jerk (control input) of each plan is used as a measure of the correction that the rider has to apply to conform to an optimal-safe maneuver. This technique has the advantage of yielding a homogenous measure of the threat independent of the scenario, and it is directly linked with the control variable that the rider should use to accordingly change the vehicle's longitudinal dynamics. Additionally, the receding horizon approach naturally accommodates road geometry and constraint attributes, motorcycle dynamics, rider input, and riding styles. Warning feedback is given to the rider by an appropriate combination of human-machine interface elements, such as the haptic throttle, the vibrating glove, and the visual display. This paper explains the IS concept, discusses the implementation aspects of the proposed receding horizon approach, and presents the results of pilot tests conducted on a top-of-the-range riding simulator.

This paper deals with the integration of multiple advanced driver-assistance systems (ADAS) and in-vehicle information systems (IVIS) in a holistic driver-support system. The paper presents the results of a project named Integrated Safety Systems (INSAFES), which was part of PReVENT: an integrating project carried out under the European Framework Programme 6. Integration in INSAFES is tackled at three different levels in the framework of a “cognitive car” perspective: 1) at the perception level, to represent the world around the vehicle, including object-tracking between sensor fields and the detection of driver intentions; 2) at the decision level, to reproduce humanlike holistic motion plans, which serve as “reference maneuvers” to evaluate the motion alternatives that a driver faces; and 3) at the level of interaction with the driver and vehicle control ( action level), to arbitrate between the requests of functions competing for driver attention. A function that provides simultaneous longitudinal and lateral support has been developed. It gives support for safe speed, safe distance, lane change, and all-around collision avoidance all at the same time. At its core, there is a tool (evasive/reference maneuver) that constantly evaluates two possible alternatives (in lane and evasive/lane change) and compares them with the driver input to detect which one applies, which dictates warnings and driver interactions, and whether there is a better alternative. In addition, a “warning manager” has been developed, acting like a referee who lets the ADAS applications work standalone and then combines the requests of each application, prioritizes them, and manages the interaction with the user. The warning manager can be particularly useful in the case of integration of pre-existing standalone functions, which can be quickly reused. If a holistic ADAS is developed, the warning manager can still be used to combine it with IVIS functions. In fact, depending on the kind of ADAS and IVIS considered, the most suitable approach can be either to combine functions in a unified multifunctional driver-support application or to arbitrate between them through the warning manager.

This paper describes a novel driver-support system that helps to maintain the correct speed and headway (distance) with respect to lane curvature and other vehicles ahead. The system has been developed as part of the Integrating Project PReVENT under the European Framework Programme 6, which is named SAfe SPEed and safe distaNCE (SASPENCE). The application uses a detailed description of the situation ahead of the vehicle. Many sensors [radar, video camera, Global Positioning System (GPS) and accelerometers, digital maps, and vehicle-to-vehicle wireless local area network (WLAN) connections] are used, and state-of-the-art data fusion provides a model of the environment. The system then computes a feasible maneuver and compares it with the driver's behavior to detect possible mistakes. The warning strategies are based on this comparison. The system “talks” to the driver mainly via a haptic pedal or seat belt and “listens” to the driver mainly via the vehicle acceleration. This kind of operation, i.e., the comparison between what the system thinks is possible and what the driver appears to be doing, and the consequent dialog can be regarded as simple implementations of the rider–horse metaphor (H-metaphor). The system has been tested in several situations (driving simulator, hardware in the loop, and real road tests). Objective and subjective data have been collected, revealing good acceptance and effectiveness, particularly in awakening distracted drivers. The system intervenes only when a problem is actually detected in the headway and/or speed (approaching curves or objects) and has been shown to cause prompt reactions and significant speed correction before getting into really dangerous situations.