Development and evaluation of a curve rollover warning system for trucks

Truck accidents involving rollover have extremely high fatality rates. About half of all truck drivers killed in accidents last year were involved in a rollover. Freightliner's Rollover Stability Advisor alerts drivers to potential rollover situations, training them to avoid excessive rollover risk In this paper, we describe work that extends the Rollover Stability Advisor to predict rollover situations in advance, giving drivers time to slow down before they are in danger. In an empirical evaluation of the rollover prediction accuracy on a sharp curve, we found that 50% of the dangerous passes could be predicted 5 seconds or longer in advance of the maximum rollover risk, and only 10% of the safe passes wrongly predicted a rollover risk. We feel that these are encouraging first results, and further refinement of the algorithms will yield even better results.