Building geometric feature based maps for indoor service robots

A temporal potential function approach for path planning in dynamic environments

“…Feature maps [8] contain representations of the typical features of the local environment of the agent. These features include the agent, straight walls and polyhedral objects.…”

“…Some of the issues with creating feature maps arise due to limited sensor range, limited field of view, occlusions and noisy data [8]. One method to overcome these is to use Probabilistic frameworks for localization.…”

Recent Developments in Bit-Parallel Algorithms

“…Using the MCP approach we have solved the global localization problem using real data from our interactive tour-guide robot called Urbano (see figure 11). The reference maps were built in real time with an EKF based SLAM algorithm (Rodriguez-Losada et al 2006). This time comparisons between BE-MCP and MCS were carried out under different levels of noise, in a map composed by approximately 350 features, with observation sets made up of between 25 and 30 observations.…”

Consistent Map Building Based on Sensor Fusion for Indoor Service Robot

“…The EKF-SLAM (DurrantWhyte & ) is based on robot state estimation. However, EKF-SLAM will fail in large environments caused by inconsistent estimation problem from the linearization process (Rodriguez-Losada et al, 2006) (Shoudong & Gamini, 2007). A full SLAM algorithm is using sequential Monte Carlo sampling method to calculate robot state as particle filter (Montemerlo et al, 2002) (Montemerlo et al, 2003).…”