Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
1714663 | Acta Astronautica | 2014 | 20 Pages |
•We present a single camera structure from motion and inertial measurement data fusion algorithm.•Inertial measurements allow scale ambiguity to be overcome.•Focus is on accurate estimation of motion and sparse landing site structure.•No prior knowledge of landing site is assumed.•Very promising results are obtained for deliberately challenging scenarios.
Robotic planetary surface exploration missions are becoming much more ambitious in their science goals as they attempt to answer the bigger questions relating to the possibility of life elsewhere in our solar system. Answering these questions will require scientifically rich landing sites. Such sites are unlikely to be located in relatively flat regions that are free from hazards, therefore there is a growing need for next generation entry descent and landing systems to possess highly sophisticated navigation capabilities coupled with active hazard avoidance that can enable a pin-point landing. As a first step towards achieving these goals, a multi-source, multi-rate data fusion algorithm is presented that combines single camera recursive feature-based structure from motion (SfM) estimates with measurements from an inertial measurement unit in order to overcome the scale ambiguity problem by directly estimating the unknown scale factor. This paper focuses on accurate estimation of absolute motion parameters, as well as the estimation of sparse landing site structure to provide a starting point for hazard detection. We assume no prior knowledge of the landing site terrain structure or of the landing craft motion in order to fully assess the capabilities of the proposed algorithm to allow a pin-point landing on distant solar system bodies where accurate knowledge of the desired landing site may be limited. We present results using representative synthetic images of deliberately challenging landing scenarios, which demonstrates that the proposed method has great potential.