Bicycle computers and apps record, at minimum, positional data over time, and
these data are commonly used in accident reconstruction to understand the
behavior of the bicycle and rider prior to an incident in question. These
positional data are obtained using the Global Positioning System (GPS), and
while their absolute positional accuracy has been the subject of prior research,
their accuracy at detecting and reporting particular movements is less studied.
To improve the accident reconstruction industry’s understanding of these
devices’ performance, this research aims to statistically quantify the temporal
and positional accuracy of these devices reporting the onset of a lateral
deviation or lane change. Controlled testing was performed and recorded with
several commercially available bicycle GPS computers and apps, which were
compared to a RaceLogic VBox 3i ADAS with Real-Time Kinematics (RTK) corrections
from a RaceLogic Base Station. Three separate test bouts were performed, with
each test bout consisting of 30 or 32 repeats of three different lateral
deviation maneuvers. The bicycle GPS computers were individually synchronized to
the RaceLogic data by offsetting their time to minimize the mean-square
positional error across the entire test bout, which enabled calculation of the
50th percentile and 95th percentile absolute positional errors for each device.
A custom script was then used to programmatically detect the start of each
lateral deviation, and then, confidence intervals were calculated to estimate
the probability of each GPS device reporting the start of the lateral deviation
with zero lead or lag, with 1 s of lag, or with 0 or 1 s of lag based on the
relative timestamps and positional data. All three of the tested bicycle GPS
computers had a probability of at least 0.5 of reporting the onset of sharp
lateral movements with zero lead or lag based on the time data, while only two
of the devices maintained a similarly high probability for the position-based
data. The iPhone 17 Pro had a probability greater than 0.6 of detecting the
onset of both gradual and sharp lateral movements with 1 s of lag for both the
time-based and position-based data. And across all lateral movement types, all
devices had a probability of at least 0.6 of reporting the onset of lateral
movement with either 0 or 1 s of lag.