Drone Obstacle Avoidance
Researchers at the Robotics and Perception Group at the University of Zurich have created autonomous drones equipped with event-based cameras that can respond to changes in a scene on a per-pixel basis in microseconds. The time it takes any kind of robot to avoid an obstacle is constrained primarily by perception latency, or in other words, the sensor itself, which is why event cameras are a game changer, since they can collect data with a theoretical latency measured in nanoseconds. Read more for a video and additional information.

USPS Autonomous Trucks

TuSimple, a San Diego-based startup, announced today that its self-driving trucks will begin transporting mail between USPS facilities in Phoenix and Dallas to see how autonomous technology might improve delivery times and costs. However, there will be a safety driver behind the wheel to intervene if necessary and an engineer will ride in the passenger seat. If this test is successful, it would mark an achievement for the autonomous driving industry and a possible solution to the driver shortage and regulatory constraints faced by freight haulers across the country. This The pilot program will consist of five round trips, each totaling more than 2,100 miles or around 45 hours of driving. Read more for another video and additional information.

Audi AI:ME Hatchback

Revealed at Auto Shanghai 2019, the futuristic Audi AI:ME is an all-electric hatchback that just might be the perfect city car. The vehicle is powered by a 65 kWh battery pack, paired with a synchronous electric motor located at the rear axle, generating a combined 170 hp. What makes it so good for cruising the streets is its Level 4 autonomous driving system, which enables it to drive itself without driver input. The AI system is “capable of learning and thinking, while also being proactive and personal,” said the company. However, you’ll still find a steering wheel and pedals in case of emergency. Read more for another video, additional pictures and information.

NVIDIA Autonomous Summon Technology

Why valet park, when autonomous summon technology can have your car navigate parking lots or streets to pick you up? During the GPU Technology Conference last month, Clarion demonstrated its long-range autonomous summon technology, running on NVIDIA DRIVE AGX Xavier. Using just a smartphone, you can call a parked, driverless vehicle to a pick-up spot. It automatically navigates around pedestrians, other vehicles and obstacles on the route to smoothly meet its passengers. Read more for another video of the NVIDIA Drive AGX and additional information.

MUJI GACA Self-Driving Bus
Photo credit: Justin Hirvi | Bonzu / MUJI via Design Boom
Japanese retail company MUJI partnered with Finnish technology company Sensible 4 to create “GACHA,” an autonomous shuttle bus that can operate in all weather conditions. It’s set to launch in Finland later this spring, starting in the city of Espoo with the eventual goal of expanding to Helsinki, Vantaa, and other large cities later by the end of 2019. Read more for a video, additional pictures and information.

Microsoft MIT Artificial Intelligence Self-Driving Car
Microsoft has teamed up with MIT might to develop a model that uses artificial intelligence to catch virtual “blind spots”. Basically, the AI compares a human’s actions in a given situation to what it would have done, and modifies its behavior based on how closely it matches the response. Put simply, if a self-driving car doesn’t know how to pull over in an emergency situation, it could learn how to do so by simply observing a human driver moving to the side of the road. However, if the AI is wrong, a human driver can also step in to correct it. “The model helps autonomous systems better know what they don’t know. Many times, when these systems are deployed, their trained simulations don’t match the real-world setting [and] they could make mistakes, such as getting into accidents. The idea is to use humans to bridge that gap between simulation and the real world, in a safe way, so we can reduce some of those errors,” said first author Ramya Ramakrishnan from Computer Science and Artificial Intelligence Laboratory at MIT. Read more for a video and additional information.

Mercedes-Benz Nostalgia
Photo credit: Sehoon Hans Kim
Created by automotive designer Sehoon Hans Kim, the futuristic Mercedes-Benz Nostalgia Concept is all-electric and boasts autonomous technology that would make it nearly invulnerable to accidents. Instead of traditional headlights and taillights, this concept sports single lines of LEDs instead, drawing inspiration from the Mercedes Concept IAA. Read more for additional pictures and information/

Uber Engineer Coast to Coast Self Driving Car
Anthony Levandowski, a former Google and Uber engineer, has completed what he claims is the first US coast-to-coast drive completed entirely by self-driving technology. The 3,099 mile journey between San Francisco and New York was made in October, with him only taking charge of his vehicle to refuel and stop overnight. “I’ve admittedly grown frustrated  –  and at times impatient  – with the industry’s inability to deliver on its promises,” said Levandowski. Read more for a time-lapse video of his journey and additional information.

Rinspeed microSNAP

The Rinspeed microSNAP concept has leaked ahead of CES 2019 next month, and it’s essentially an autonomous electric vehicle designed purely for transporting goods and people. It rides on a skateboard chassis that holds the vehicle’s powertrain as we ll as autonomous driving system, and when the need arises, you’ll be able to easily swap different pods, whether it be for transportation or hauling materials. Read more for additional pictures and information.