全方位画像上の床領域のモデル照合とデッドレコニングに基づく移動ロボットの自己位置推定(機械力学,計測,自動制御)

概要

論文の詳細を見る
A self-localization scheme for mobile robots based on model-fitting of a floor region captured by omni-directional vision is proposed to deal with quantization errors in these vision images, which has previously limited the utility of omni-directional vision. The self-localization method allows for better estimates of values by integrating the omni-directional imaging and the dead reckoning using the Kalman filter. The algorithm and experimental results using an actual robot are presented, and the robustness of the system is discussed based on error recovery when the robot position changes due to collision with other objects and human intervention in the real world.
一般社団法人日本機械学会の論文
2003-02-25