FAST SOLVING FOR LOOP CLOSURE

摘要

The subject disclosure is generally directed towards a relatively fast and accurate technology that corrects mobile device (e.g., mobile robot) mapping data into corrected map data based upon detection of loop closure. A variation of stochastic gradient descent (with constraints in a deterministic order) may be used in a first correction phase to provide an updated graph in a relatively fast manner by operating in a relative state space. A graph-based variant of Gauss-Seidel that operates in a global state space may be used in a later phase to refine the updated graph into a more exact graph.

主权项

1. A method comprising, collecting data corresponding to mobile device movement into a pose graph, receiving an indication that loop closure has occurred, optimizing the pose graph including processing the pose graph based upon stochastic gradient descent, including iterating to update states in a relative state space, and outputting an updated pose graph.