This factsheet is based on past evaluation data contained in the ITS Knowledge Resources database at: www.itskrs.its.dot.gov. The database is maintained by the U.S. DOT’s ITS JPO Evaluation Program to support informed decision making regarding ITS investments by tracking the effectiveness of deployed ITS. The factsheet presents benefits, costs and lessons learned from past evaluations of ITS projects.
Autonomous vehicles also known as self-driving, driverless, or robotic vehicles are defined as computer-equipped vehicles that can be driven and operated without active control by a human driver. Using integrated sensor systems, complex algorithms, and automated vehicle (AV) technology, autonomous vehicles can plan routes, navigate through traffic, negotiate lane changes and turns, manage speeds, and assist with parking. With AV technology, a variety of new functions are expected over the next several years as connected vehicle (CV) applications are refined and implemented in accordance with governmental regulations and controls.
While not required for autonomous driving, CV applications are expected to enhance the operational capacity of autonomous vehicles networks and bring about a variety of benefits such as improved situational awareness for increased safety, improved fuel economy, reduced parking needs, and increased mobility for those unable to drive. To help realize these benefits, the United States Department of Transportation (USDOT) Intelligent Transportation Systems Joint Program Office (ITS JPO) has made Advancing Automation a key strategic priority.
As preliminary guidance, the National Highway Traffic Safety Administration (NHTSA) established the following framework that defines five levels of automation. 
- No Automation (Level 0): The driver is in complete and sole control of the primary vehicle controls – brake, steering, throttle, and motive power – at all times.
- Function-specific Automation (Level 1): Automation at this level involves one or more specific control functions.
- Combined Function Automation (Level 2): This level involves automation of at least two primary control functions designed to work in unison to relieve the driver of control of those functions.
- Limited Self-Driving Automation (Level 3): Vehicles at this level of automat ion enable the driver to cede full control of all safety-critical functions under certain traffic or environmental conditions, and while driving in those conditions, rely heavily on the vehicle to monitor for changes requiring transition back to driver control. The driver is expected to be available for occasional control, but with sufficiently comfortable transition time.
- Full Self-Driving Automation (Level 4): The vehicle is designed to perform all safety-critical driving functions and monitor roadway conditions for an entire trip. Such a design anticipates that the driver will provide destination or navigation input, but is not expected to be available for control at any time during the trip. This includes both occupied and unoccupied vehicles.
The design of an autonomous vehicle can vary greatly depending on the level of automation needed, but in general includes the following components.
- Lidar – Light detection and ranging (Lidar) sensors measure distance (50-100 meters) between the vehicle and nearby objects by emitting pulses of light from multiple rotating laser beams at a rate of more than one million measurements per second creating a 3D model of the space surrounding the vehicle accurate to approximately one centimeter.
- Radar – Radio detection and ranging (Radar) sensors measure distance (60-200 meters) between the vehicle and nearby objects located in front and back of the vehicle using directional wave radio signals.
- Ultrasonic – Ultrasonic sensors measure short distances (0-5 meters) between the sides or rear of a vehicle and nearby objects.
- Cameras – Cameras with streaming picture processing technology can gauge distances between the vehicle and other vehicles, read signs, and detect pedestrians.
- Navigation – In-vehicle navigation systems can use GPS, sensor enhanced maps, and positional information from ground-based radio beacons to support navigation under a variety of conditions.
- Computing hardware and software – Powerful computers and advanced algorithms can manage automated features using redundant control logic. User interfaces can support smooth transitions between different levels of automated control.
- Mechanical controllers and actuators – Automated control of brakes, throttle, steering, gear selection, and secondary controls (i.e., turn signals, hazard lights, headlights, door locks, ignition, and horn) will incorporate redundancy for safe operation and use reliable power supplies.
- Wireless communications – Dedicated Short Range Communications (DSRC) along with mobile communication networks, can support a wide variety of CV and AV applications.