arXiv subjects

Mohsen Alirezaei

Publications and source records attributed to Mohsen Alirezaei.

10 recordsLinked to original sources

arXiv2025

Quantifying Fidelity: A Decisive Feature Approach to Comparing Synthetic and Real Imagery

Virtual testing using synthetic data has become a cornerstone of autonomous vehicle (AV) safety assurance. Despite progress in improving visual realism through advanced simulators and generative AI, recent studies reveal that pixel-level fidelity alone does not ensure reliable transfer from simulation to the real world. What truly matters is whether the system-under-test (SUT) bases its decisions on consistent decision evidence in both real and simulated environments, not just whether images "look real" to humans. To this end this paper proposes a behavior-grounded fidelity measure by introducing Decisive Feature Fidelity (DFF), a new SUT-specific metric that extends the existing fidelity spectrum to capture mechanism parity, that is, agreement in the model-specific decisive evidence that drives the SUT's decisions across domains. DFF leverages explainable-AI methods to identify and compare the decisive features driving the SUT's outputs for matched real-synthetic pairs. We further propose estimators based on counterfactual explanations, along with a DFF-guided calibration scheme to enhance simulator fidelity. Experiments on 2126 matched KITTI-VirtualKITTI2 pairs demonstrate that DFF reveals discrepancies overlooked by conventional output-value fidelity. Furthermore, results show that DFF-guided calibration improves decisive-feature and input-level fidelity without sacrificing output value fidelity across diverse SUTs.

cs.AI↗

arXiv2025

A Vehicle-in-the-Loop Simulator with AI-Powered Digital Twins for Testing Automated Driving Controllers

Simulators are useful tools for testing automated driving controllers. Vehicle-in-the-loop (ViL) tests and digital twins (DTs) are widely used simulation technologies to facilitate the smooth deployment of controllers to physical vehicles. However, conventional ViL tests rely on full-size vehicles, requiring large space and high expenses. Also, physical-model-based DT suffers from the reality gap caused by modeling imprecision. This paper develops a comprehensive and practical simulator for testing automated driving controllers enhanced by scaled physical cars and AI-powered DT models. The scaled cars allow for saving space and expenses of simulation tests. The AI-powered DT models ensure superior simulation fidelity. Moreover, the simulator integrates well with off-the-shelf software and control algorithms, making it easy to extend. We use a filtered control benchmark with formal safety guarantees to showcase the capability of the simulator in validating automated driving controllers. Experimental studies are performed to showcase the efficacy of the simulator, implying its great potential in validating control solutions for autonomous vehicles and intelligent traffic.

cs.RO↗

arXiv2024

A Learning-Based Model Predictive Contouring Control for Vehicle Evasive Manoeuvres

This paper presents a novel Learning-based Model Predictive Contouring Control (L-MPCC) algorithm for evasive manoeuvres at the limit of handling. The algorithm uses the Student-t Process (STP) to minimise model mismatches and uncertainties online. The proposed STP captures the mismatches between the prediction model and the measured lateral tyre forces and yaw rate. The mismatches correspond to the posterior means provided to the prediction model to improve its accuracy. Simultaneously, the posterior covariances are propagated to the vehicle lateral velocity and yaw rate along the prediction horizon. The STP posterior covariance directly depends on the variance of observed data, so its variance is more significant when the online measurements differ from the recorded ones in the training set and smaller in the opposite case. Thus, these covariances can be utilised in the L-MPCC's cost function to minimise the vehicle state uncertainties. In a high-fidelity simulation environment, we demonstrate that the proposed L-MPCC can successfully avoid obstacles, keeping the vehicle stable while driving a double lane change manoeuvre at a higher velocity than an MPCC without STP. Furthermore, the proposed controller yields a significantly lower peak sideslip angle, improving the vehicle's manoeuvrability compared to an L-MPCC with a Gaussian Process.

cs.RO↗

arXiv2024

Model Predictive Contouring Control for Vehicle Obstacle Avoidance at the Limit of Handling Using Torque Vectoring

This paper presents an original approach to vehicle obstacle avoidance. It involves the development of a nonlinear Model Predictive Contouring Control, which uses torque vectoring to stabilise and drive the vehicle in evasive manoeuvres at the limit of handling. The proposed algorithm combines motion planning, path tracking and vehicle stability objectives, prioritising collision avoidance in emergencies. The controller's prediction model is a nonlinear double-track vehicle model based on an extended Fiala tyre to capture the nonlinear coupled longitudinal and lateral dynamics. The controller computes the optimal steering angle and the longitudinal forces per each of the four wheels to minimise tracking error in safe situations and maximise the vehicle-to-obstacle distance in emergencies. Thanks to the optimisation of the longitudinal tyre forces, the proposed controller can produce an extra yaw moment, increasing the vehicle's lateral agility to avoid obstacles while keeping the vehicle stable. The optimal forces are constrained in the tyre friction circle not to exceed the tyres and vehicle capabilities. In a high-fidelity simulation environment, we demonstrate the benefits of torque vectoring, showing that our proposed approach is capable of successfully avoiding obstacles and keeping the vehicle stable while driving a double-lane change manoeuvre, in comparison to baselines lacking torque vectoring or collision avoidance prioritisation.

cs.RO↗

arXiv2024

Awareness in robotics: An early perspective from the viewpoint of the EIC Pathfinder Challenge "Awareness Inside''

Consciousness has been historically a heavily debated topic in engineering, science, and philosophy. On the contrary, awareness had less success in raising the interest of scholars in the past. However, things are changing as more and more researchers are getting interested in answering questions concerning what awareness is and how it can be artificially generated. The landscape is rapidly evolving, with multiple voices and interpretations of the concept being conceived and techniques being developed. The goal of this paper is to summarize and discuss the ones among these voices connected with projects funded by the EIC Pathfinder Challenge called ``Awareness Inside'', a nonrecurring call for proposals within Horizon Europe designed specifically for fostering research on natural and synthetic awareness. In this perspective, we dedicate special attention to challenges and promises of applying synthetic awareness in robotics, as the development of mature techniques in this new field is expected to have a special impact on generating more capable and trustworthy embodied systems.

cs.RO↗

arXiv2023

Model Validation of a Low-Speed and Reverse Driving Articulated Vehicle

For the autonomous operation of articulated vehicles at distribution centers, accurate positioning of the vehicle is of the utmost importance. Automation of these vehicle poses several challenges, e.g. large swept path, asymmetric steering response, large slide slip angles of non-steered trailer axles and trailer instability while reversing. Therefore, a validated vehicle model is required that accurately and efficiently predicts the states of the vehicle. Unlike forward driving, open-loop validation methods can not be used for reverse driving of articulated vehicles due to their unstable dynamics. This paper proposes an approach to stabilize the unstable pole of the system and compares three vehicle models (kinematic, non-linear single track and multibody dynamics model) against real-world test data obtained from low-speed experiments at a distribution center. It is concluded that single track non-linear model has a better performance in comparison to other models for large articulation angles and reverse driving maneuvers.

cs.RO↗

arXiv2023

Model Predictive Contouring Control for Vehicle Obstacle Avoidance at the Limit of Handling

This paper proposes a non-linear Model Predictive Contouring Control (MPCC) for obstacle avoidance in automated vehicles driven at the limit of handling. The proposed controller integrates motion planning, path tracking and vehicle stability objectives, prioritising obstacle avoidance in emergencies. The controller's prediction model is a non-linear single-track vehicle model with the Fiala tyre to capture the vehicle's non-linear behaviour. The MPCC computes the optimal steering angle and brake torques to minimise tracking error in safe situations and maximise the vehicle-to-obstacle distance in emergencies. Furthermore, the MPCC is extended with the tyre friction circle to fully exploit the vehicle's manoeuvrability and stability. The MPCC controller is tested using real-time rapid prototyping hardware to prove its real-time capability. The performance is compared with a state-of-the-art Model Predictive Control (MPC) in a high-fidelity simulation environment. The double lane change scenario results demonstrate a significant improvement in successfully avoiding obstacles and maintaining vehicle stability.

cs.RO↗

arXiv2023

An Unscented Kalman Filter-Informed Neural Network for Vehicle Sideslip Angle Estimation

This paper proposes a novel vehicle sideslip angle estimator, which uses the physical knowledge from an Unscented Kalman Filter (UKF) based on a non-linear single-track vehicle model to enhance the estimation accuracy of a Convolutional Neural Network (CNN). The model-based and data-driven approaches interact mutually, and both use the standard inertial measurement unit and the tyre forces measured by load sensing technology. CNN benefits from the UKF the capacity to leverage the laws of physics. Concurrently, the UKF uses the CNN outputs as sideslip angle pseudo-measurement and adaptive process noise parameters. The back-propagation through time algorithm is applied end-to-end to the CNN and the UKF to employ the mutualistic property. Using a large-scale experimental dataset of 216 manoeuvres containing a great diversity of vehicle behaviours, we demonstrate a significant improvement in the accuracy of the proposed architecture over the current state-of-art hybrid approach combined with model-based and data-driven techniques. In the case that a limited dataset is provided for the training phase, the proposed hybrid approach still guarantees estimation robustness.

eess.SY↗

arXiv2022

Multiple Faults Estimation in Dynamical Systems: Tractable Design and Performance Bounds

In this article, we propose a tractable nonlinear fault isolation filter along with explicit performance bounds for a class of nonlinear dynamical systems. We consider the presence of additive and multiplicative faults, occurring simultaneously and through an identical dynamical relationship, which represents a relevant case in several application domains. The proposed filter architecture combines tools from model-based approaches in the control literature and regression techniques from machine learning. To this end, we view the regression operator through a system-theoretic perspective to develop operator bounds that are then utilized to derive performance bounds for the proposed estimation filter. In the case of constant, simultaneously and identically acting additive and multiplicative faults, it can be shown that the estimation error converges to zero with an exponential rate. The performance of the proposed estimation filter in the presence of incipient faults is validated through an application on the lateral safety systems of SAE level 4 automated vehicles. The numerical results show that the theoretical bounds of this study are indeed close to the actual estimation error.

math.OC↗

arXiv2021

Safe Imitation Learning on Real-Life Highway Data for Human-like Autonomous Driving

This paper presents a safe imitation learning approach for autonomous vehicle driving, with attention on real-life human driving data and experimental validation. In order to increase occupant's acceptance and gain drivers' trust, the autonomous driving function needs to provide a both safe and comfortable behavior such as risk-free and naturalistic driving. Our goal is to obtain such behavior via imitation learning of a planning policy from human driving data. In particular, we propose to incorporate barrier functions and smooth spline-based motion parametrization in the training loss function. The advantage is twofold: improving safety of the learning algorithm, while reducing the amount of needed training data. Moreover, the behavior is learned from highway driving data, which is collected consistently by a human driver and then processed towards a specific driving scenario. For development validation, a digital twin of the real test vehicle, sensors, and traffic scenarios are reconstructed toward high-fidelity and physics-based modeling technologies. These models are imported to simulation tools and co-simulated with the proposed algorithm for validation and further testing. Finally, we present experimental results and analyses, and compare with the conventional imitation learning technique (behavioral cloning) to justify the proposed development.

eess.SY↗