Multi-sensor localization - Visual Odometry as a low cost proprioceptive sensor

摘要: Ego-localization is a key issue for most autonomous robots and vehicles. Indeed, the ability to take proper decision (avoidance, path-finding, etc.) relies on knowledge of one's particular environment one hand its relative positioning in this other hand. As such, has been addressed multiple times past few years. This work extends multi-sensor fusion framework order advantage Visual Odometry (VO), as low cost proprioceptive sensor with same result than an expensive INS sensor. In particular, it shown that VO helps determine course vehicle limit overall drift system similar behavior classical but localization filter.