Search

The importance of proper data normalization for deep neural networks is well known. However, in continuous-time state-space model estimation, it has been observed that improper normalization of either the hidden state or hidden state derivative of the model estimate, or even of the time interval can lead to numerical and optimization challenges with deep learning based methods. This results in a reduced model quality. In this contribution, we show that these three normalization tasks are inherently coupled. Due to the existence of this coupling, we propose a solution to all three normalization challenges by introducing a normalization constant at the state derivative level. We show that the appropriate choice of the normalization constant is related to the dynamics of the to-be-identified system and we derive multiple methods of obtaining an effective normalization constant. We compare and discuss all the normalization strategies on a benchmark problem based on experimental data from a cascaded tanks system and compare our results with other methods of the identification literature., Comment: This work has been accepted for presentation at the 20th IFAC Symposium on System Identification 2024

In a typical car-following scenario, target vehicle speed fluctuations act as an external disturbance to the host vehicle and in turn affect its energy consumption. To control a host vehicle in an energy-efficient manner using model predictive control (MPC), and moreover, enhance the performance of an ecological adaptive cruise control (EACC) strategy, forecasting the future velocities of a target vehicle is essential. For this purpose, a deep recurrent neural network-based vehicle speed prediction using long-short term memory (LSTM) and gated recurrent units (GRU) is studied in this work. Besides these, the physics-based constant velocity (CV) and constant acceleration (CA) models are discussed. The sequential time series data for training (e.g. speed trajectories of the target and its preceding vehicles obtained through vehicle-to-vehicle (V2V) communication, road speed limits, traffic light current and future phases collected using vehicle-to-infrastructure (V2I) communication) is gathered from both urban and highway networks created in the microscopic traffic simulator SUMO. The proposed speed prediction models are evaluated for long-term predictions (up to 10 s) of target vehicle future velocities. Moreover, the results revealed that the LSTM-based speed predictor outperformed other models in terms of achieving better prediction accuracy on unseen test datasets, and thereby showcasing better generalization ability. Furthermore, the performance of EACC-equipped host car on the predicted velocities is evaluated, and its energy-saving benefits for different prediction horizons are presented., Comment: Submitted to IFAC World Congress 2023

In this work, a predictive eco-driving assistance system (pEDAS) with the goal to assist drivers in improving their driving style and thereby reducing the energy consumption in battery electric vehicles while enhancing the driving safety and comfort is introduced and evaluated. pEDAS in this work is equipped with two model predictive controllers (MPCs), namely reference-tracking MPC and car-following MPC, that use the information from onboard sensors, signal phase and timing (SPaT) messages from traffic light infrastructure, and geographical information of the driving route to compute an energy-optimal driving speed. An optimal speed suggestion and informative advice are indicated to the driver using a visual feedback. pEDAS provides continuous feedback and encourages the drivers to perform energy-efficient car-following while tracking a preceding vehicle, travel at safe speeds at turns and curved roads, drive at energy-optimal speed determined using dynamic programming in freeway scenarios, and travel with a green-wave optimal speed to cross the signalized intersections at a green phase whenever possible. Furthermore, to evaluate the efficacy of the proposed pEDAS, user studies were conducted with 41 participants on a dynamic driving simulator. The objective analysis revealed that the drivers achieved mean energy savings up to 10%, reduced the speed limit violations, and avoided unnecessary stops at signalized intersections by using pEDAS. Finally, the user acceptance of the proposed pEDAS was evaluated using the Technology Acceptance Model (TAM) and Theory of Planned Behavior (TPB). The results showed an overall positive attitude of users and that the perceived usefulness and perceived behavioral control were found to be the significant factors in influencing the behavioral intention to use pEDAS., Comment: Transportation Research Part C: Emerging Technologies Journal

This paper proposes an ecological adaptive cruise control (EACC) concept with the primary goal to minimize the fuel consumption in a city bus with an internal combustion engine (ICE). A hybrid model predictive control (HMPC) is implemented in this work to control both continuous and discrete-time variables. Moreover, a multi-objective optimization problem for EACC is formulated in time-domain as a mixed-integer quadratically constrained quadratic programming (MIQCQP) problem. The proposed HMPC-EACC performs robust vehicle-following while tracking a leading vehicle and plans fuel-efficient acceleration and deceleration maneuvers for the host vehicle. Additionally, it uses the signal phase and timing (SPaT) information to compute a green wave reference speed for the host vehicle to cross the signalized intersections at a green phase. Moreover, the proposed controller performs pulse and glide (PnG) to optimally control the engine ON and OFF states and save additional fuel. Furthermore, the performance of the proposed strategy is evaluated on a real-world driving profile and compared against a baseline controller from the literature. Finally, the influence of different prediction horizons on the fuel savings and computation times are studied. The results reveal significant reduction in fuel consumption with HMPC-EACC and demonstrate that the proposed controller is real-time capable., Comment: Submitted to IEEE Vehicular Power and Propulsion 2021

An easily moving and safe transportation is an indicator in any country in the world of economic growth and well-being. For the past 100 years, innovation within the automotive sector has brought major technological advances leading to safer, cleaner and more affordable vehicles. But for the most time since the inception of the moving assembly line for vehicle production by Henry Ford, the changes have been incremental / evolutionary. Thanks to the new possibilities due to the IT / wireless revolution, the automotive industry appears to be on the cusp of revolutionary change with potential to dramatically reshape not just the competitive landscape but also the way we interact with vehicles, and indeed the future design of our roads and cities. Apart from connected personal mobility, vehicles are also envisioned to provide Value Added Services (VAS) such as autonomous driving via Vehicle-to-Vehicle (V2V) and Vehicle-to-infrastructure (V2I), electric load balancing via Vehicle-to-Grid (V2G) solutions, communication solutions using Visible Light Communications (VLC) etc. The development and evaluation of vehicular VAS requires a modular and scalable multidisciplinary simulation platform. In this paper we propose a novel simulation platform named Cyber-Automotive Simulation \& Evaluation Platform (CASEP). The purpose of CASEP is to evaluate and visualize the gains of various vehicular VAS with special emphasis on commercial vehicle VAS. The use cases are evaluated with respect to the mission-specific performance indicators, thereby providing usable metrics for optimization. The visualization platform is being developed using the UNITY 3D engine, thereby enabling intuitive interaction as in real physics-based games, Comment: published in the Commercial Vehicle Technology Symposium 2016