weather, is often not feasible. In the first contribution of this thesis, we propose a robust

detection pipeline. In this chapter, we also collect a large-scale multi-view dataset for the

estimation systems into real-life mobile agents. This thesis proposes novel architectures

estimation, sensor fusion etc. Unfortunately, estimating uncertainty for VO is especially

In the last contribution of this thesis, we employ a pose graph optimisation technique to

crucial for systems that depend upon motion output, such as path planning, vehicle state

In the third contribution of this thesis, we introduce AFT-VO, a novel transformer-based

different sources. It can fuse signals from any number of sources and, more importantly,

with promising results. However, the nature of VO is that small errors in the estimation

cost-effective solution and are often already installed on modern vehicles. Traditional