NEXTCAR Self-driving Car in Action Advances the Future Internet of Cars
Traffic congestion around the world is worsening, according to transport data firm INRIX. In the U.S. alone, Americans wasted an average of 97 hours in traffic in 2018 – that’s two precious weekends worth of time. Captivity in traffic also costs them nearly $87 billion in 2018, an average of $1,348 per driver. Clearly, the need for smart transportation is reaching a fervor, not only to alleviate the mental and financial state of drivers, but to address the significant economic toll on affected cities.
Fortunately, development of intelligent mobility technologies is advancing. Two years after receiving a NEXTCAR grant to develop smart car technology, Boston University researchers have taken to the streets for live testing of the NEXTCAR self-driving car. The testing, conducted in Mcity, Ann Arbor, MI last summer, included the first on-road demonstration of BU-developed self-driving car algorithms.
The testing was conducted by CISE faculty affiliate Christos Cassandras, Head of the Division of Systems Engineering and Professor of Electrical and Computer Engineering, and Arian Houshmand, PhD Candidate, Systems Engineering, in collaboration with researchers from University of Delaware, University of Michigan, Oak Ridge National Laboratory, and Bosch as a corporate partner. The work is part of a $3.36 million grant from the Energy Department’s Advanced Research Projects Agency-Energy (ARPA-E) NEXTCAR program, which aims to ease traffic congestion and air pollution by developing energy-efficient smart vehicle technology.
“The goal is to design control and optimization technologies that enable a plug-in hybrid electric vehicle (PHEV) to communicate with other cars and city infrastructure and act on that information,” says Prof. Cassandras, Co-Principal Investigator. “By providing cars with situational self-awareness, they will be able to efficiently calculate the best possible route, accelerate and decelerate as needed, and manage their powertrain. This is important work toward advancing our vision to create an ‘Internet of Cars,’ in which connected and self-driving cars operate seamlessly with each other and traffic infrastructure, improving fuel efficiency and safety, and reducing traffic congestion and pollution.”
Today’s commercially-available self-driving cars rely on costly sensors, specifically radar, camera, and LIDAR (light) to operate semi-autonomously. In the NEXTCAR project, BU researchers with project collaborators are looking to go beyond that by developing decision-making algorithms to improve the autonomous operation of a single hybrid vehicle as well as algorithms for communications between vehicles and their environment, enabling self-driving cars to cooperate and interact within their socio-cyber-physical environment.
Through “Eco-Routing,” algorithmic decisions for how much gas or electricity is expended, and when to expend the energy are made. With “Cooperative Adaptive Cruise Control” algorithms, the researchers are working to enable communication among vehicles and their environment, such as traffic lights. With these approaches, the researchers are focused on minimizing travel time between points, the energy used to get there, as well as the resulting air pollution.
“Currently, a conventional car’s awareness of its surrounding relies completely on the eyes and ears of the driver operating it,” explains Cassandras. “But humans are terrible drivers. Humans get distracted and tired, and can’t always react quickly to sudden changes. We are creating novel technologies that can improve safety by eliminating total reliance on human factors. Working with our NEXTCAR collaborators, we are advancing technologies that will allow the CAV to access, process, and make decisions off of information in its environment.”
In live testing this summer, the researchers demonstrated the algorithms using a 2016 Audi A3 e-tron, on which they tested multiple algorithms in a variety of scenarios across Mcity. They also used VISSIM simulation software to demonstrate cooperative adaptive cruise control functions. During testing, the team demonstrated that the BU-developed algorithms could be successfully implemented on real cars. The Audi successfully received information about its surroundings and made continuous control decisions. The researchers also demonstrated a total efficiency savings of more than 20 percent.
Because connected and autonomous vehicles have emerged with the rise of recent technology, “they provide the most intriguing opportunity to improve traffic flow and reshape the driving cycle of a typical commute,” said Houshmand. “If cars can communicate with each other and make collaborative decisions, there would be less reliance on sensors, which are very expensive.”
Adds Houshmand, “It is really exciting for me to deal with the challenges that arise from real-time implementation of codes in the car and learn how to resolve them. It is definitely a great experience for me as a PhD student and I am very glad that I had the opportunity to be a part of this team.” Learn more about Houshmand’s experience in developing NEXTCAR self-driving car technology.
Learn more about the UTOPIAN VEHICLE (Ultimately Transformed and Optimized Powertrain Integrated with Automated and Novel Vehicular and Highway Connectivity Leveraged for Efficiency) project by watching this movie.
Allie Antonevich contributed reporting to this story.