Creating High-capacity Ride-Sharing With Autonomous Transportation

Original

Image source: Uber

Ride-sharing services are transforming urban mobility by providing timely and convenient transportation to anybody, anywhere, and anytime.  Thanks to the global popularity of apps like Lyft and Uber, there are now hundreds of thousands of ride-share drivers, millions of users and billions in VC funding for apps and companies in the industry, despite the dominating companies being only 4-5 years old.

Javier Alonso-Mora, Assistant Professor at Delft University of Technology, is working on autonomous mobile robots, with a special emphasis in multi-robot systems and robots that interact with other robots and humans. He and his department contribute novel methods and solutions in the areas of motion planning and multi-robot control, moving towards the smart cities of the future where these technologies and methods can be applied in self-driving cars, automated factories, aerial vehicles and human-swarm interaction.

At the Machine Intelligence in Autonomous Vehicles Summit this week (28-29 June), Javier will explore real-time high-capacity ride-sharing and planning in intelligent autonomous transportation system. I spoke to Javier to learn more about his work, ahead of the summit in Amsterdam.

How did you begin your work in autonomous vehicles?

During my doctoral studies I worked on coordination and control of teams of mobile robots. This experience introduced me to the field. I am interested on autonomous vehicles for a few reasons, namely that they have the potential of saving lives, as well as increase the freedom and mobility of people who can not drive. And also because they are complex and smart machines! My work on mobility on demand stems from a desire to have more efficient and affordable public transportation.

What are the key factors that have enabled recent advancements in developing algorithms for ride-sharing?

Some factors are the maturity of underlying algorithms and tools (such as constrained optimization and machine learning), an increase in computational power, and a clear application with ride-sharing companies.

What are the key challenges you are facing in progressing ride-sharing in autonomous systems?

One big challenge is creating the autonomous cars themselves. A fully autonomous car which is reliable and safe under all conditions is extremely challenging. From a fleet management point of view, challenges include efficient large scale methods for routing and assignment, as well as accurate prediction of demand and travel time.

What developments can we expect to see in urban mobility in the next 5 years?

More efficient and on-demand transportation, which provides reliable and convenient urban mobility. Some autonomous fleets in controlled or semi-controlled environments.

Outside of your own field, what area of machine learning advancements excites you most?

The field of machine learning is intriguing and exciting. We have seen great developments, from computers that can beat humans in complex games, to algorithms capable of learning and interpreting huge amounts of data.


Javier Alonso-Mora will be speaking at the Machine Intelligence in Autonomous Vehicles Summit in Amsterdam this week, 28-29 June, taking place alongside the Machine Intelligence Summit. View more information here.

Opinions expressed in this interview may not represent the views of RE•WORK. As a result some opinions may even go against the views of RE•WORK but are posted in order to encourage debate and well-rounded knowledge sharing, and to allow alternate views to be presented to our community.

Can't make it to Amsterdam? Find out more about our upcoming events, and register for Early Bird passes to the Deep Learning Summit London, 21 & 22 September.

Original

Machine Learning Smart Transport Connected Car Autonomous Vehicles Summit Intelligent Automated Systems Autonomous Vehicles Computer Vision


0 Comments

    As Featured In

    Original
    Original
    Original
    Original
    Original
    Original

    Partners & Attendees

    Intel.001
    Nvidia.001
    Graphcoreai.001
    Ibm watson health 3.001
    Facebook.001
    Acc1.001
    Rbc research.001
    Twentybn.001
    Forbes.001
    Maluuba 2017.001
    Mit tech review.001
    Kd nuggets.001