Experimental investigation of online path planning for electric vehicles

Winter, Christoph; Ritzer, Peter; Brembeck, Jonathan

doi:10.1109/itsc.2016.7795741

Cited by 15 publications

(15 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The planning of the path and velocity profile is out of the scope of this work. We assume that a planning module similar to [20] exits and is able to provide the motion demand (1) as a lookup table. In the real world application the vehicle states C , C , C can be estimated e.g.…”

Section: E Training Setupmentioning

confidence: 99%

Reinforcement Learning-based Path Following Control for a Vehicle with Variable Delay in the Drivetrain

Ultsch

Mirwald

Brembeck

et al. 2020

2020 IEEE Intelligent Vehicles Symposium (IV)

Self Cite

View full text Add to dashboard Cite

In this contribution we propose a reinforcement learning-based controller which is able to solve the path following problem for vehicles with significant delay in the drivetrain. To efficiently train the controller, a control-oriented simulation model for a vehicle with combustion engine, automatic gear box and hydraulic brake system has been developed. In addition, to enhance the reinforcement learning-based controller, we have introduced preview information in the feedback state to better deal with the delays. We present our approach of designing a reward function which enables the reinforcement learning-based controller to solve the problem. The controller is trained using the Soft Actor-Critic algorithm by incorporating the developed simulation model. Finally, the performance and robustness is evaluated in simulation. Our controller is able to follow an unseen path and is robust against variations in the vehicle parameters, in our case an additional payload.

show abstract

Section: E Training Setupmentioning

confidence: 99%

Reinforcement Learning-based Path Following Control for a Vehicle with Variable Delay in the Drivetrain

Ultsch

Mirwald

Brembeck

et al. 2020

2020 IEEE Intelligent Vehicles Symposium (IV)

Self Cite

View full text Add to dashboard Cite

show abstract

“…This gradient descent search algorithm is already successfully being used on a rapid-prototyping real-time system. For example, it was employed—similar to the one proposed in this manuscript—in previous research on path planning tasks [4]. This gradient descent optimization has been implemented and successfully tested on a dSpace real-time control system with a sample time of 100 ms.…”

Section: Real-time Nonlinear Moving Horizon Estimationmentioning

confidence: 99%

“…Especially for future autonomous vehicles, it is necessary to determine an accurate vehicle position so as to guarantee a reliable vehicle path/trajectory generation, and to follow control functionality cf. [2,3,4].…”

Section: Introductionmentioning

confidence: 99%

Nonlinear Constrained Moving Horizon Estimation Applied to Vehicle Position Estimation

Brembeck

2019

Sensors

Self Cite

View full text Add to dashboard Cite

The design of high–performance state estimators for future autonomous vehicles constitutes a challenging task, because of the rising complexity and demand for operational safety. In this application, a vehicle state observer with a focus on the estimation of the quantities position, yaw angle, velocity, and yaw rate, which are necessary for a path following control for an autonomous vehicle, is discussed. The synthesis of the vehicle’s observer model is a trade-off between modelling complexity and performance. To cope with the vehicle still stand situations, the framework provides an automatic event handling functionality. Moreover, by means of an efficient root search algorithm, map-based information on the current road boundaries can be determined. An extended moving horizon state estimation algorithm enables the incorporation of delayed low bandwidth Global Navigation Satellite System (GNSS) measurements—including out of sequence measurements—as well as the possibility to limit the vehicle position change through the knowledge of the road boundaries. Finally, different moving horizon observer configurations are assessed in a comprehensive case study, which are compared to a conventional extended Kalman filter. These rely on real-world experiment data from vehicle testdrive experiments, which show very promising results for the proposed approach.

show abstract

“…to decrease travel time. Simultaneously the maneuverable robotic electric vehicle research platform ROboMObil was used to achieve the energy saving [26]. On the other hand, resource allocation is another approach to improve both mobility and environmental impacts.…”

Section: ) Environmental Impacts Benefitsmentioning

confidence: 99%

Performance Measurement Evaluation Framework and Co-Benefit\/Tradeoff Analysis for Connected and Automated Vehicles (CAV) Applications: A Survey

Tian

Boriboonsomsin

et al. 2018

IEEE Intell. Transport. Syst. Mag.

View full text Add to dashboard Cite

A number of Connected and/or Automated Vehicle (CAV) applications have recently been designed to improve the performance of our transportation system. Safety, mobility and environmental sustainability are three cornerstone performance metrics when evaluating the benefits of CAV applications. These metrics can be quantified by various measures of effectiveness (MOEs). Most of the existing CAV research assesses the benefits of CAV applications on only one (e.g., safety) or two (e.g., mobility and environment) aspects, without holistically evaluating the interactions among the three types of MOEs. This paper first proposes a broad classification of CAV applications, i.e., vehicle-centric, infrastructure-centric, and traveler-centric. Based on a comprehensive literature review, a number of typical CAV applications have been examined in great detail, where a categorized analysis in terms of MOEs is performed. Finally, several conclusions are drawn, including the identification of influential factors on system performance, and suggested approaches for obtaining co-benefits across different types of MOEs.

show abstract

Experimental investigation of online path planning for electric vehicles

Cited by 15 publications

References 12 publications

Reinforcement Learning-based Path Following Control for a Vehicle with Variable Delay in the Drivetrain

Reinforcement Learning-based Path Following Control for a Vehicle with Variable Delay in the Drivetrain

Nonlinear Constrained Moving Horizon Estimation Applied to Vehicle Position Estimation

Performance Measurement Evaluation Framework and Co-Benefit\/Tradeoff Analysis for Connected and Automated Vehicles (CAV) Applications: A Survey

Contact Info

Product

Resources

About