Deep learning model predictive control for autonomous driving in unknown environment
In this paper, a dynamic obstacle avoidance Model Predictive Control
(MPC) method is introduced for autonomous driving which uses deep
learning technique for velocity-dependent collision avoidance in
unknown environments. The goal of the method is to control an
autonomous vehicle in order to perform different traffic maneuvers in
a safe way with maximum comfort of passengers, and in minimum possible
time, accounting for maneuvering capabilities, vehicle dynamics, and
in the presence of traffic rules, road boundaries and static and
dynamic unknown obstacles.
Here, by defining local coordinates and collision regions, the
dynamic collision avoidance problem is translated into a static
collision avoidance problem which makes the method easier and faster
to be solved in dynamical environments.
In order to provide safety, an ensemble of deep neural networks are
used in order to estimate the probability of collision and to form an
uncertainty-dependent collision cost. The collision cost is a product
of the probability of collision and vehicle's velocity in the
directions with high collision-risk. Our dynamic obstacle avoidance
optimization method minimizes the velocity in the obstacle cones where
the probability of collision is high or in unfamiliar environments,
and increases the velocity when probability and variation in predicted
values of the ensemble are low. In our method, predicted trajectory
from MPC is used in learning part in order to assign labels. This
property makes it possible to predict the collision in advance.
Simulation results show that the proposed method has good adaptability
to an unknown environment.
Fatemeh Mohseni, Sergii Voronov and Erik Frisk
Senast uppdaterad: 2021-11-10