Skip to menu Skip to content

Uber Self-Driving Pilot

Uber Self-Driving Pilot
Pittsburgh, United States
Project details


The Advanced Technologies Group (ATG), Uber’s self-driving vehicles arm, is currently testing its self-driving system on public roads in Pittsburgh, Pennsylvania, U.S. This on-road testing is focused on core self-driving system development. Vehicles are operated by two safety drivers, or Mission Specialists, who are full-time Uber ATG employees; rides to members of public are not currently offered.


The objective of this pilot is to test and gather data and insight in support of a safe self-driving system. The best way to harness the power of self-driving technology for broad public benefit is to deploy it in managed fleets of shared vehicles equipped with Level 4 capability.

This approach:

  • Improves access to technology which is otherwise prohibitively expensive for personal ownership and technologically more difficult to operate and maintain than a conventional vehicle, thereby familiarizing consumers and speeding adoption

  • Encourages a shift away from private car ownership, thereby reducing the size of the vehicle fleet and space required for parking

  • Manages the risk of increased Vehicle Miles Travelled and related sprawl, congestion, and environmental impacts by combining trips and using infrastructure more efficiently.

Regulatory Framework

The U.S. Department of Transportation’s (U.S. DOT’s) National Highway Traffic Safety Administration (NHTSA) issues Federal Motor Vehicle Safety Standards (FMVSS) and Regulations to which manufacturers of motor vehicles and items of motor vehicle equipment must conform and certify compliance.

The U.S. DOT and NHTSA have issued:

Sensor technologies used

1: Light Detection and Ranging (LIDAR) - LIDAR is a remote sensing method that uses light in the form of a pulsed laser to measure distances to actors and objects. Each upfitted XC90 is equipped with one, top-mounted LIDAR unit. Uber’s self-driving system utilizes a LIDAR unit with a range of over 100 meters (m).

2: Cameras - Each upfitted XC90 is equipped with cameras that provide high resolution, near-, medium-, and long-range imagery. There are cameras mounted in the sensor pod on top of the vehicle and around the vehicle for 360˚ coverage. The camera hardware and accompanying firmware are custom to the Uber self-driving system. Some of these cameras have a wide field of view and some have a narrow field of view. A system of cameras provides imagery to support near-range sensing of people and objects within 5m from vehicle, in particular to assist during pick up and drop off, lane changing, and parking.

3: Radar - Each upfitted XC90 is equipped with radars that provide object detection, ranging, and relative velocity of objects. Forward-facing radars are mounted below the headlamps, side-facing radars are mounted in the front and rear corners of the vehicle, and rear-facing radars are mounted near the ends of the bumper beam.

4: Global Positioning System (GPS) - The GPS system provides rough position to support localization, vehicle command, map data collect missions, and satellite measurements.

5: Self-Driving Computer - The self-driving computer is the main system computer running Perception, Prediction, Motion Planning, and other software. The computer hardware and firmware are custom to Uber’s self-driving system. The computer is liquid-cooled for high power heat rejection.

6: Telematics - Custom telematics hardware and software provide cellular data communication to support carrier network redundancy, secure mobile data traffic, and authenticated cloud communication.

Featured News & Publications

View all updates

Next initiative

Line 529, Ski

Ski, Norway
Go to next initiative


7 words explained


Also known as flocking. A collection of (automated) vehicles that travel together, actively coordinated in formation. Platoons decrease the distances between vehicles using electronic, and possibly mechanical, coupling. Platooning allows many vehicles to accelerate or brake simultaneously.

urban setting

High density environment with an efficient high capacity public transport system with good capillarity and high frequencies.

suburban setting

Medium density environment with a good public transport system with radial connections to the city center, but lower capillarity and frequencies. This setting includes suburban cities.

small cities

Small, isolated city with an own public transport system and <100K inhabitants.


Low-density environment, small cities and villages with poor public transport services mainly connecting the villages.

SAE level

The SAE (Society of Automotive Engineers) levels define the level of vehicle autonomy, or in other words, how much human intervention is still needed for an automated vehicle to operate. Currently, five SAE levels have been defined: Level 0: Automated system issues warnings and may momentarily intervene but has no sustained vehicle control. Level 1 (hands on): Driver and automatic system share vehicle control. The driver must be ready to retake full control at any time. Level 2 (hands off): The automated system takes full control of the vehicle (accelerating, braking, and steering). The driver must monitor the driving and be prepared to intervene immediately at any time if the automated system fails to respond properly. Level 3 (eyes off): The automated system takes full control of the vehicle (accelerating, braking, and steering). The driver must monitor the driving and be prepared to intervene immediately at any time if the automated system fails to respond properly. Level 4 (mind off): As level 3, but no driver attention is ever required for safety, e.g. the driver may safely go to sleep or leave the driver's seat. Level 5 (steering wheel optional): No human intervention is required at all. An example would be a robotic taxi.


Vehicle-to-everything (V2X) communication is the passing of information from a vehicle to any entity that may affect the vehicle, and vice versa.