Predictive data-driven vehicle dynamics and powertrain control: from ECU to the cloud

Predictive data-driven vehicle dynamics and powertrain control: from ECU to the cloud

A team led by Professor Francesco Borrelli has been awarded $3.33 million from the U.S. Department of Energy’s Advanced Research Projects Agency-Energy (ARPA-E). The goal is to reduce the energy consumption of vehicles, coordinating vehicle dynamics and powertrain controls, and leveraging driving automation and connectivity.

The team also includes ME Professors Roberto Horowitz and Karl Hedrick, CEE Professor Scott Moura, Dr. Jacopo Guanetti (Postdoc in MPC Lab), as well as Hyundai Motor Company and Sensys Networks as industrial partners. The objective is to develop an innovative control platform for autonomous Plug-in Hybrid Electric Vehicles (PHEVs). The predictive control platform will optimize PHEV performance in real-world driving conditions, accounting for short-, medium-, and long-term targets, and crowdsourcing data from surrounding vehicles, infrastructure, and the cloud. Taking the human driver out of the loop, driving automation enables energy-optimal speed profiles. The surrounding environment will be estimated from data, exploiting on-board sensors and vehicle-to-vehicle, vehicle-to-infrastructure, and vehicle-to-cloud communication. Connectivity to the cloud will grant access to maps and traffic data, but will also assist the on-board ECU in intensive computations. Performance improvement will be demonstrated through experiments, covering approach and departure at signalized intersections, cooperative adaptive cruise control and speed harmonization. The control platform will seamlessly handle a broad spectrum of scenarios including urban driving, highway driving, and eco-routing.

This award comes from ARPA-E’s NEXT-Generation Energy Technologies for Connected and Automated On-Road Vehicles (NEXTCAR) program, which seeks to optimize vehicle dynamics and powertrain operation, leveraging connectivity and driving automation. NEXTCAR projects will enable better coordination of vehicle-level and powertrain-level actions, improving the energy efficiency of the individual vehicles and, ultimately, the overall fleet.

   
  
 
 
  
    
  
 Normal 
 0 
 
 
 14 
 
 
 false 
 false 
 false 
 
 EN-US 
 X-NONE 
 X-NONE 
 
  
  
  
  
  
  
  
  
  
 
 
  
  
  
  
  
  
  
  
  
  
  
  
    
  
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
  
   
 
 /* Style Definitions */
 table.MsoNormalTable
	{mso-style-name:"Table Normal";
	mso-tstyle-rowband-size:0;
	mso-tstyle-colband-size:0;
	mso-style-noshow:yes;
	mso-style-priority:99;
	mso-style-parent:"";
	mso-padding-alt:0cm 5.4pt 0cm 5.4pt;
	mso-para-margin-top:0cm;
	mso-para-margin-right:0cm;
	mso-para-margin-bottom:10.0pt;
	mso-para-margin-left:0cm;
	line-height:115%;
	mso-pagination:widow-orphan;
	font-size:11.0pt;
	font-family:"Calibri",sans-serif;
	mso-ascii-font-family:Calibri;
	mso-ascii-theme-font:minor-latin;
	mso-hansi-font-family:Calibri;
	mso-hansi-theme-font:minor-latin;
	mso-bidi-font-family:"Times New Roman";
	mso-bidi-theme-font:minor-bidi;
	mso-ansi-language:EN-US;
	mso-fareast-language:EN-US;}
 
  Predictive eco-approach/departure at signalized intersections

Predictive eco-approach/departure at signalized intersections

   
  
 
 
  
    
  
 Normal 
 0 
 
 
 14 
 
 
 false 
 false 
 false 
 
 EN-US 
 X-NONE 
 X-NONE 
 
  
  
  
  
  
  
  
  
  
 
 
  
  
  
  
  
  
  
  
  
  
  
  
    
  
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
  
   
 
 /* Style Definitions */
 table.MsoNormalTable
	{mso-style-name:"Table Normal";
	mso-tstyle-rowband-size:0;
	mso-tstyle-colband-size:0;
	mso-style-noshow:yes;
	mso-style-priority:99;
	mso-style-parent:"";
	mso-padding-alt:0cm 5.4pt 0cm 5.4pt;
	mso-para-margin-top:0cm;
	mso-para-margin-right:0cm;
	mso-para-margin-bottom:10.0pt;
	mso-para-margin-left:0cm;
	line-height:115%;
	mso-pagination:widow-orphan;
	font-size:11.0pt;
	font-family:"Calibri",sans-serif;
	mso-ascii-font-family:Calibri;
	mso-ascii-theme-font:minor-latin;
	mso-hansi-font-family:Calibri;
	mso-hansi-theme-font:minor-latin;
	mso-bidi-font-family:"Times New Roman";
	mso-bidi-theme-font:minor-bidi;
	mso-ansi-language:EN-US;
	mso-fareast-language:EN-US;}
 
  Predictive eco-CAAC and SPD-HARM

Predictive eco-CAAC and SPD-HARM

Predictive Control Framework for Driver Steering Assistance

Predictive Control Framework for Driver Steering Assistance

Learning MPC for the Berkeley Autonomous Racing Car (BARC)

Learning MPC for the Berkeley Autonomous Racing Car (BARC)