… inverse reinforcement learning (IRL) framework for trajectory … of the distribution of future
trajectories of the vehicle, encoding … at the same intersection depending on the vehicle’s speed. …

… Note that the trajectory includes multiple vehicles in the driving scene since we consider
interactions between agents. The state st is just a physical or partial observation that can be …

… Experiments are conducted at off-road environments using real driving trajectories and …
a deep inverse reinforcement learning framework for analyzing offroad autonomous vehicle …

… The main objective of this thesis is to investigate how reinforcement learning and inverse
reinforcement learning can be used in the field of motion prediction of the surrounding agents …

… Inverse Reinforcement Learning (IRL). Our planner, DriveIRL, generates a diverse set of
trajectory proposals, filters these trajectories … controller of our self-driving vehicle. We train our …

… and surrounding vehicles trajectories during the period. Surrounding vehicles’ location at
each moment t is used to generate a scene descriptor st, while the ego vehicle’s trajectory is …

… Stanford Drone Database (SDD): SDD consists of trajectories of pedestrians, bicyclists, and
vehicles on 60 different scenes on the Stanford University campus. All images are captured …

… trajectory prediction using B-spline curve representations of vehicle trajectories and inverse
reinforcement … B-spline curves were used to represent vehicle trajectories; a neural network …

… In this paper, we consider the problem of modeling trajectories of vehicles in a road network
which are observed by external sensors located on sparse fixed points on the street network…

… [37] applied an extended Kalman filter to predict the future trajectory of an autonomous
vehicle, and used a linear time-varying model predictive control scheme to determine the optimal …