Collision Probability Map for Motion Prediction of Surrounding Vehicles using Sensing Uncertainty 2020-01-0697
Intelligent driving assistant systems have been studied meticulously for autonomous driving. When the systems have the responsibility for driving itself, such as in an autonomous driving system, it should be aware of its’ surroundings including moving vehicles and must be able to evaluate collision risk for the ego vehicle's planned motion. However, when recognizing surrounding vehicles using a sensor, the measured information has uncertainty because of many reasons, such as noise and resolution.
Many previous studies evaluated the collision risk based on the probabilistic theorem which the noise is modeled as a probability density function. However, the previous probabilistic solutions could not assess the collision risk and predict the motion of surrounding vehicles at the same time even though the motion is possible to be changed by the estimated collision risk.
Thus, this paper proposes the collision probability map to simultaneously predict the motions of surrounding vehicles and evaluate the collision risk based on the measurement uncertainty. This map makes the algorithm to consider the sensing uncertainty while predicting the motion of surrounding vehicle because this map is generated using the uncertainty of measured information. Since the collision probability map is used for motion prediction of surrounding vehicles, the map is generated in the perspective of surrounding vehicles.
The proposed algorithm was evaluated in the scenario, lane changing to a side lane when another vehicle was approaching from behind. Each experimental scenario, we compared the estimated collision risk for safer vs. more dangerous ego driving routes. According to the experimental results, the proposed algorithm provides the advantage for estimating the risks of collision because it predicts the interaction-aware longitudinal motion of the surrounding vehicles while also estimating the collision risk between the ego vehicle and the surrounding vehicles.
Minchul Lee, Myoungho Sunwoo, Kichun Jo