Current generation pedestrian crash avoidance systems can reduce vehicle-pedestrian collisions by 40 percent under certain conditions.
An independent evaluation of automatic emergency braking systems with pedestrian detection.
Made Public Date

Automatic Emergency Braking with Pedestrian Detection

Summary Information

Pedestrian Crash Avoidance Systems (PCAS) systems are an increasingly popular technology in newer cars. In theory these systems should either provide the driver with an explicit warning about the presence of a pedestrian or apply automatic braking when a collision with a pedestrian is imminent. However, these systems have acknowledged limitations and may not function as intended under real-world conditions.


To better understand how well these systems work under real-world conditions the American Automobile Association (AAA) tested PCAS on four 2019 model year vehicles, a Chevrolet Malibu with Front Pedestrian Braking, a Honda Accord with Honda Sensing, a Tesla Model 3 with Automatic Emergency Braking, and a Toyota Camry with Toyota Safety Sense.

Testing was a three step process. First researchers equipped each vehicle with on-board sensing units and cameras to "capture vehicle dynamics and position data" and verified the cars were in working order. Second, researchers drove the vehicles down a test track towards a simulated, moving pedestrian dummy, five different times for each vehicle. The stopping distance and alert time relative to the time before collision were recorded for each test run. Third, testers repeated this process under a variety of conditions including with two pedestrians in front of the vehicle, at night, and with smaller pedestrian (i.e. child sized) dummies.


In aggregate, when encountering an adult pedestrian in a perpendicular crossing scenario where a test vehicle traveling at 20 mi/h was provided with visual notification of an impending conflict, collision with an adult pedestrian target was avoided 40 percent of the time. During an additional 35 percent of the time, collisions were mitigated by an average speed of 4.4 mi/h.

When encountering a child pedestrian at 20 mi/h, a collision was avoided 11 percent of the time, in aggregate. During an additional 25 percent of the time, collisions were mitigated by an average speed of 5.9 mi/h.

When encountering a pedestrian immediately after a right curve, none of the test vehicles mitigated the impact speed during any of the five test runs.

When encountering two pedestrians alongside the roadway at 20 mi/h, a collision was avoided 20 percent of the time in aggregate. During an additional 35 percent of the time, collisions were mitigated by an average speed of 3.4 mi/h.