Analysis of individual driver velocity prediction using data-driven driver models with environmental features

Ziegmann, Johannes; Shi, Jieqing; Schnorer, Tobias; Endisch, Christian

doi:10.1109/ivs.2017.7995770

Cited by 14 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once θ θ θ yield , θ θ θ pass , θ θ θ front , θ θ θ back and ψ ψ ψ merging , ψ ψ ψ lane-keeping are acquired, we can obtain the conditional PDF defined in (2) via (3). With this PDF, probabilistic and interactive prediction of human drivers' behavior can be obtained.…”

Section: Test Resultsmentioning

confidence: 99%

“…Equation (3) suggests that in order to model the conditional PDF in (2) for interactive prediction, we need to model the hierarchical probabilistic models P (d M |ξ, ξH ) and p( ξM |d i M , ξ, ξH ) for each d i M ∈D M . We thus propose to apply inverse reinforcement learning hierarchically to learn all the models from observed demonstrations of human drivers.…”

Section: B Hierarchical Inverse Reinforcement Learningmentioning

confidence: 99%

See 1 more Smart Citation

Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning

Sun

Zhan

Tomizuka

2018

2018 21st International Conference on Intelligent Transportation Systems (ITSC)

119

View full text Add to dashboard Cite

Autonomous vehicles (AVs) are on the road. To safely and efficiently interact with other road participants, AVs have to accurately predict the behavior of surrounding vehicles and plan accordingly. Such prediction should be probabilistic, to address the uncertainties in human behavior. Such prediction should also be interactive, since the distribution over all possible trajectories of the predicted vehicle depends not only on historical information, but also on future plans of other vehicles that interact with it. To achieve such interaction-aware predictions, we propose a probabilistic prediction approach based on hierarchical inverse reinforcement learning (IRL). First, we explicitly consider the hierarchical trajectory-generation process of human drivers involving both discrete and continuous driving decisions. Based on this, the distribution over all future trajectories of the predicted vehicle is formulated as a mixture of distributions partitioned by the discrete decisions. Then we apply IRL hierarchically to learn the distributions from real human demonstrations. A case study for the ramp-merging driving scenario is provided. The quantitative results show that the proposed approach can accurately predict both the discrete driving decisions such as yield or pass as well as the continuous trajectories.

show abstract

Section: Test Resultsmentioning

confidence: 99%

Section: B Hierarchical Inverse Reinforcement Learningmentioning

confidence: 99%

Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning

Sun

Zhan

Tomizuka

2018

2018 21st International Conference on Intelligent Transportation Systems (ITSC)

119

View full text Add to dashboard Cite

show abstract

“…Typical speed prediction methods include State Vector Machine (SVM), Markov chain, and Artificial Intelligence (AI) methods, such as Genetic Algorithm (GA) and NN [30][31][32][33][34][35]. Korosh et al [36] estimated future vehicle speeds up to 30 s by combining the traveling route with the driving behavior model.…”

Section: Vehicle Velocity Forecast Based On Narx Networkmentioning

confidence: 99%

Predictive Energy Management Strategy for Range-Extended Electric Vehicles Based on ITS Information and Start–Stop Optimization with Vehicle Velocity Forecast

et al. 2022

View full text Add to dashboard Cite

Range-extended Electric Vehicles (REVs) have become popular due to their lack of emissions while driving in urban areas, and the elimination of range anxiety when traveling long distances with a combustion engine as the power source. The fuel consumption performance of REVs depends greatly on the energy management strategy (EMS). This article proposes a practical energy management solution for REVs based on an Adaptive Equivalent Fuel Consumption Minimization Strategy (A-ECMS), wherein the equivalent factor is dynamically optimized by the battery’s State of Charge (SoC) and traffic information provided by Intelligent Transportation Systems (ITS). Furthermore, a penalty function is incorporated with the A-ECMS strategy to achieve the quasi-optimal start–stop control of the range extender. The penalty function is designed based on more precise vehicle velocity forecasting through a nonlinear autoregressive network with exogeneous input (NARX). A model of the studied REV is established in the AVL Cruise environment and the proposed energy management strategy is set up in Matlab/Simulink. Lastly, the performance of the proposed strategy is evaluated over multiple Worldwide Light-duty Test Cycles (WLTC) and real-world driving cycles through model simulation. The simulation conditions are preset such that the range extender must be switched on to finish the planned route. Compared with the basic Charge-Depleting and Charge-Sustaining (CD-CS) strategy, the proposed A-ECMS strategy achieves a fuel-consumption benefit of up to 9%. With the implementation of range extender start–stop optimization, which is based on velocity forecasting, the fuel saving rate can be further improved by 6.7% to 18.2% compared to the base A-ECMS. The proposed strategy is energy efficient, with a simple structure, and it is intended to be implemented on the studied vehicle, which will be available on the market at the end of October 2022.

show abstract

“…Data-driven methods gained popularity in the last decade. Several methods are used and compared in [34]: kernel regression, neural networks, and nonlinear auto-regressive networks with exogenous inputs (NARX). In [35] the NARX based approach is compared with four stochastic prediction models: two of them relying on linear and Gaussian assumptions and the other two defined as non-parametric.…”

Section: Velocity Predictionmentioning

confidence: 99%

Battery Aging-Aware Online Optimal Control: An Energy Management System for Hybrid Electric Vehicles Supported by a Bio-Inspired Velocity Prediction

Valenti¹,

Pagot

Pascali

et al. 2021

IEEE Access

View full text Add to dashboard Cite

In this manuscript we address the problem of online optimal control for torque splitting in hybrid electric vehicles that minimises fuel consumption and preserves battery life. We divide the problem into the prediction of the future velocity profile (i.e. driver intention estimation) and the online optimal control of the hybrid powertrain following a Model Predictive Control (MPC) scheme. The velocity prediction is based on a bio-inspired driver model, which is compared on various datasets with two alternative prediction algorithms adopted in the literature. The online optimal control problem addresses both the fuel consumption and the preservation of the battery life using an equivalent cost given the estimated speed profile (i.e. guaranteeing the desired performance). The battery degradation is evaluated by means of a state-of-the-art electrochemical model. Both the predictor and the Energy Management System (EMS) are evaluated in simulation using real driving data divided into 30 driving cycles from 10 drivers characterised by different driving styles. A comparison of the EMS performances is carried out on two different benchmarks based on an offline optimization, in one case on the entire dataset length and in the second on an ideal prediction using two different receding horizon lengths. The proposed online system, composed by the velocity prediction algorithm and the optimal control MPC scheme, shows comparable performances with the previous ideal benchmarks in terms of fuel consumption and battery life preservation. The simulations show that the online approach is able to significantly reduce the capacity loss of the battery, while preserving the fuel saving performances INDEX TERMS hybrid electric vehicles (HEVs), online optimal control, velocity prediction algorithm, energy management system (EMS), battery electrochemical model

show abstract

Analysis of individual driver velocity prediction using data-driven driver models with environmental features

Cited by 14 publications

References 6 publications

Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning

Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning

Predictive Energy Management Strategy for Range-Extended Electric Vehicles Based on ITS Information and Start–Stop Optimization with Vehicle Velocity Forecast

Battery Aging-Aware Online Optimal Control: An Energy Management System for Hybrid Electric Vehicles Supported by a Bio-Inspired Velocity Prediction

Contact Info

Product

Resources

About