אירועים והרצאות בפקולטה למדעי המחשב ע"ש הנרי ומרילין טאוב

Simultaneous localization and mapping (SLAM) is essential in numerous robotics applications such as autonomous navigation. Traditional SLAM approaches infer the metric state of the robot (position and orientation) along with a metric map of the environment. While existing algorithms exhibit good results, they are still sensitive to measurement noise, sensors quality, data association and are still computationally expensive. Computational load is especially problematic in active planning. Alternatively, we note that some navigation and mapping missions can be achieved using only qualitative geometric information, an approach known as qualitative spatial reasoning (QSR). In this work we contribute a novel probabilistic qualitative SLAM approach, which extends the state of the art to make a more complete qualitative geometry SLAM solution. We show how to infer the qualitative state of the camera poses (localization), incorporate new types of probabilistic connections between views, and how to propagate information in a qualitative map enabling improved estimation as well as estimating unseen map nodes. Our method is particularly appealing in scenarios with a small number of salient landmarks, sparse landmark tracks and low quality sensors. It may also enable light qualitative active planning. We evaluate our approach in simulation and in a real-world dataset, and show its superior performance and low complexity compared to state of the art.