Future transportation promises greater safety, information resources and much faster connectivity to prevent injuries from traffic crashes and improve the commuting experience. Drones, driverless cars, and Artificial Intelligence (AI) will seamlessly coordinate and transport goods and people for very little cost. The demands for faster, more efficient commuting options are driving the development of flying taxis for urban areas.
Gridlock in many urban areas like Brazil, have spawned innovations in flying taxis and the ways Artificial Intelligence is being embedded in our personal vehicles and mass transit. In Sao Paulo, Brazil traffic congestion led to helicopters as another alternative for professionals to get to work over the past decade. With commuters making over 1,300 helicopter take-offs and landings in a single day, Sao Paulo has become the largest user of helicopters in South America.
Several companies including Uber, Tesla and Amazon with its recent purchase of Zoox, a ride hailing passenger vehicle technology company, have invested in developing autonomous passenger vehicles including flying cars that can be used as taxis. These autonomous cars are expected to dramatically reduce the number of highway deaths and injuries while lowering the costs of shipping and transportation.
In June, 2020 Waymo and Uber presented research to improve the reliability — and safety — of their self-driving systems. Waymo principal scientist Drago Anguelov detailed ViDAR, a camera and range-centric framework covering scene geometry, semantics, and dynamics. Raquel Urtasun, chief scientist at Uber’s Advanced Technologies Group, demonstrated a pair of technologies that leverage vehicle-to-vehicle communication for navigation, traffic modeling, and more.
VIDAR, a Waymo collaborative project with Google Brian, infers structure from motion. It learns 3D geometry from image sequences — i.e., frames captured by car-mounted cameras — by exploiting motion parallax, a change in position caused by movement. Given a pair of images and lidar data, ViDAR can predict future camera viewpoints and depth data. Vidar uses shutter timings to avoid a “jello effect” often found in handheld or moving camera shots greatly improving accuracy.
Advancements like these along with new 5G chips and AI will turn autonomous vehicles into mobile data centers, allowing driverless cars to make real-time, complex decisions and opening up exciting possibilities for the automobile industry used for vehicle-to-vehicle (V2V) and vehicle-to-everything (V2X) connectivity. In addition, the technology’s real time access to rapidly changing data will make these vehicles safer than ones operated by people today. These investments promise to improve the safety, communications and convenience of personal vehicles.
Similar work is underway to apply AI and autonomous features to trucking companies to improve the efficiency and value to the supply chain. One example, “TuSimple is a global self-driving truck company. Based in San Diego and operating self-driving trucks out of Tucson, Arizona, TuSimple is developing a commercial-ready Level 4 (SAE) fully-autonomous driving solution for the logistics industry. TuSimple’s trucks are the first and only capable of self-driving from depot-to-depot and do so every day for its customers. The company is driven by a mission to increase safety, decrease transportation costs, and reduce carbon emissions.”
Although the implications of how these autonomous vehicles will improve our ability to get around and reduce the time and cost of goods isn’t clear, they provide the potential for faster, more efficient and less expensive transportation while improving the quality of air and life.
