Gunther Krehl

TL;DR: In this article, the occupancy state of each grid cell in a robot's environment is estimated by estimating the occupancy states of the grid cells in the robot's own environment map, which is a well-established approach for environment perception in robotic and automotive applications.

TL;DR: This paper presents a method to fuse laser and radar measurement data with the Bayesian occupancy filter, and shows that the doppler information of radar measurements significantly improves the dynamic estimation of the grid map, reduces ghost movements, and in general leads to a faster convergence of theynamic estimation.

TL;DR: In this article, the authors define the state of multiple grid cells as a random finite set, which allows to model the environment as a stochastic, dynamic system with multiple obstacles, observed by an external measurement system, and motivate an original filter called the probability hypothesis density / multi-instance Bernoulli (PHD/MIB) filter.

TL;DR: This work adapts the idea of simultaneous grid cell tracking and object shape estimation into the grid map domain and proposes “self-localizing tracklets”, which are individual particle filter based estimators that are used for two main tasks: stabilizing the position estimation accuracy of dynamic cells with respect to the object boundary, and estimating a better object shape.

TL;DR: A particle-based multiple model approach is presented for the dynamic occupancy grid system and the corresponding results are given in a typical vehicle driving scenario.