We address the problem of segmenting anomalies and unusual obstacles in road scenes for the purpose of self-driving safety.
The objects in question are not present in the common training sets as it is not feasible to collect and annotate examples for every ...
Forecasting pedestrians' future motions is essential for autonomous driving systems to safely navigate in urban areas. However, existing prediction algorithms often overly rely on past observed trajectories and tend to fail around abrupt dynamic changes, s ...
The field of artificial intelligence is set to fuel the future of mobility by driving forward the transition from advanced driver-assist systems to fully autonomous vehicles (AV). Yet the current technology, backed by cutting-edge deep learning techniques, ...
The safety of existing bridges may be assessed using data from monitoring. The fatigue damage induced during observation period is extrapolated to the total service duration of a structure, and the reserve capacity is estimated. However, due to the randomn ...
This dissertation introduces traffic forecasting methods for different network configurations and data availability.
Chapter 2 focuses on single freeway cases.
Although its topology is simple, the non-linearity of traffic features makes this prediction sti ...
Moving walkways are pedestrian dedicated hardware which generally decrease pedestrian travel time. We propose the utilization of these devices to dynamically control pedestrian flows in order to improve pedestrian dynamics. Three variations of a control st ...
Safety is still the main issue of autonomous driving, and in order to be globally deployed, they need to predict pedestrians' motions sufficiently in advance. While there is a lot of research on coarse-grained (human center prediction) and fine-grained pre ...
