Real-time Eco-Driving Control in Electrified Connected and Autonomous Vehicles using Approximate Dynamic Programming

Connected and Automated Vehicles (CAVs), particularly those with a hybrid electric powertrain, have the potential to significantly improve vehicle energy savings in real-world driving conditions. In particular, the Eco-Driving problem seeks to design optimal speed and power usage profiles based on available information from connectivity and advanced mapping features to minimize the fuel consumption over an itinerary. This paper presents a hierarchical multi-layer Model Predictive Control (MPC) approach for improving the fuel economy of a 48V mild-hybrid powertrain in a connected vehicle environment. Approximate Dynamic Programming (ADP) is used to solve the Receding Horizon Optimal Control Problem (RHOCP), where the terminal cost for the RHOCP is approximated as the base-policy obtained from the long-term optimization. The controller was extensively tested virtually (using both deterministic and Monte Carlo simulations) across multiple real-world routes where energy savings of more than 20\% have been demonstrated. Further, the developed controller was deployed and tested at a proving ground in real-time on a test vehicle equipped with a rapid prototyping embedded controller. Real-time in-vehicle testing confirmed the energy savings observed in simulation and demonstrated the ability of the developed controller to be effective in real-time applications.

[1]  Guoyuan Wu,et al.  GlidePath: Eco-Friendly Automated Approach and Departure at Signalized Intersections , 2017, IEEE Transactions on Intelligent Vehicles.

[2]  Peng Hao,et al.  Prediction-Based Eco-Approach and Departure at Signalized Intersections With Speed Forecasting on Preceding Vehicles , 2019, IEEE Transactions on Intelligent Transportation Systems.

[3]  L. Johannesson,et al.  Approximate Dynamic Programming Applied to Parallel Hybrid Powertrains , 2008 .

[4]  S. Joe Qin,et al.  A survey of industrial model predictive control technology , 2003 .

[5]  Ardalan Vahidi,et al.  Fundamentals of energy efficient driving for combustion engine and electric vehicles: An optimal control perspective , 2019, Autom..

[6]  Huei Peng,et al.  Design and Comparison of Fuel-Saving Speed Planning Algorithms for Automated Vehicles , 2018, IEEE Access.

[7]  Francesco Borrelli,et al.  Control of Connected and Automated Vehicles: State of the Art and Future Challenges , 2018, Annu. Rev. Control..

[8]  Daniel Krajzewicz,et al.  SUMO (Simulation of Urban MObility) - an open-source traffic simulation , 2002 .

[9]  Giorgio Rizzoni,et al.  An Enhanced Driver Model for Evaluating Fuel Economy on Real-World Routes , 2019, IFAC-PapersOnLine.

[10]  J H Lee,et al.  Approximate dynamic programming approach for process control , 2010, ICCAS 2010.

[11]  Aonghus McNabola,et al.  A critical review and assessment of Eco-Driving policy & technology: Benefits & limitations , 2014 .

[12]  Francesco Borrelli,et al.  Robust Eco-Driving Control of Autonomous Vehicles Connected to Traffic Lights , 2018, 1802.05815.

[13]  D. Bertsekas.  Rollout Algorithms for Constrained Dynamic Programming , 2005 .

[14]  Daniel Krajzewicz,et al.  SUMO - Simulation of Urban MObility An Overview , 2011 .

[15]  Xun Gong,et al.  Sequential Optimization of Speed, Thermal Load, and Power Split in Connected HEVs* This paper is based upon the work supported by the United States Department of Energy (DOE) under award No. DE-AR0000797. , 2019, 2019 American Control Conference (ACC).

[16]  Alberto Bemporad,et al.  Predictive Control for Linear and Hybrid Systems , 2017 .

[17]  Sean P. Meyn,et al.  An analysis of reinforcement learning with function approximation , 2008, ICML '08.

[18]  Stefano Di Cairano,et al.  Cloud-Based Velocity Profile Optimization for Everyday Driving: A Dynamic-Programming-Based Solution , 2014, IEEE Transactions on Intelligent Transportation Systems.

[19]  Erik Hellström,et al.  Design of an efficient algorithm for fuel-optimal look-ahead control , 2010 .

[20]  Lino Guzzella,et al.  Vehicle Propulsion Systems , 2013 .

[21]  Giorgio Rizzoni,et al.  Estimation of Fuel Economy on Real-World Routes for Next-Generation Connected and Automated Hybrid Powertrains , 2020 .

[22]  Dennis A. Guenther,et al.  Design and Operation of a Brake and Throttle Robot , 2009 .

[23]  Matthew Younkins,et al.  Electrified Dynamic Skip Fire (eDSF): Design and Benefits , 2018 .

[24]  Anna G. Stefanopoulou,et al.  Recursive least squares with forgetting for online estimation of vehicle mass and road grade: theory and experiments , 2005 .

[25]  John N. Tsitsiklis,et al.  Neuro-Dynamic Programming , 1996, Encyclopedia of Machine Learning.

[26]  P. Schrimpf,et al.  Dynamic Programming , 2011 .

[27]  Marcello Canova,et al.  A GPU Implementation of a Look-Ahead Optimal Controller for Eco-Driving Based on Dynamic Programming , 2021, 2021 European Control Conference (ECC).

[28]  H.K. Fathy,et al.  Online vehicle mass estimation using recursive least squares and supervisory data extraction , 2008, 2008 American Control Conference.

[29]  Hong Chen,et al.  Optimal Energy Management for HEVs in Eco-Driving Applications Using Bi-Level MPC , 2017, IEEE Transactions on Intelligent Transportation Systems.

[30]  Dimitri P. Bertsekas,et al.  Dynamic Programming and Optimal Control, Two Volume Set , 1995 .

[31]  Chao Sun,et al.  Optimal Eco-Driving Control of Connected and Autonomous Vehicles Through Signalized Intersections , 2020, IEEE Internet of Things Journal.

[32]  Giorgio Rizzoni,et al.  In-Vehicle Test Results for Advanced Propulsion and Vehicle System Controls Using Connected and Automated Vehicle Information , 2021 .

[33]  Ziyou Gao,et al.  Energy-efficient metro train rescheduling with uncertain time-variant passenger demands: An approximate dynamic programming approach , 2016 .

[34]  Peng Hao,et al.  Eco-Approach and Departure (EAD) Application for Actuated Signals in Real-World Traffic , 2016 .

[35]  Antonio Sciarretta,et al.  Optimal Ecodriving Control: Energy-Efficient Driving of Road Vehicles as an Optimal Control Problem , 2015, IEEE Control Systems.

[36]  Francesco Borrelli,et al.  Real-time Ecological Velocity Planning for Plug-in Hybrid Vehicles with Partial Communication to Traffic Lights , 2019, 2019 IEEE 58th Conference on Decision and Control (CDC).

[37]  Mark A. Shost,et al.  Design and Benefits of Dynamic Skip Fire Strategies for Cylinder Deactivated Engines , 2013 .

[38]  Marcello Canova,et al.  Energy Management of Hybrid Electric Vehicles via Deep Q-Networks , 2020, 2020 American Control Conference (ACC).

[39]  Shreshta Rajakumar Deshpande,et al.  Benchmarking Fuel Economy of Connected and Automated Vehicles in Real World Driving Conditions via Monte Carlo Simulation , 2020 .

[40]  Guoyuan Wu,et al.  Power-Based Optimal Longitudinal Control for a Connected Eco-Driving System , 2016, IEEE Transactions on Intelligent Transportation Systems.

[41]  R. Trigui,et al.  Vehicle trajectory optimization for hybrid vehicles taking into account battery state-of-charge , 2012, 2012 IEEE Vehicle Power and Propulsion Conference.