Abstract
A person-following robot is under development for astronaut assistance on the Chinese Space Station. Real-time astronaut detection and tracking are the most important prerequisites for in-cabin flying assistant robots so that they can follow a specific astronaut and offer him/her assistance. In the limited space in the space station cabin, astronauts stand close to each other when working collaboratively; thus, large regions of their bodies tend to overlap in the image. In addition, because astronauts wear the same clothes most of the time, it is difficult to distinguish an individual astronaut using human body features. In this paper, we distinguish the astronauts by tracking their heads in the image. A deep learning model trained using big data is proposed for effective head detection. In addition, a motion model based on spatial clues is combined with the head detection results to track astronauts in the scene. A complete pipeline of the algorithm has been implemented and run efficiently on the Tegra X2 embedded AI microprocessor. A set of experiments were carried out and successfully validated the effectiveness of the proposed tracking algorithm. This algorithm is a step toward the implementation of robot assistants, especially in resource-limited environments.
Highlights
Operating on near-Earth orbit for more than ten years, the Chine Space Station will support the development and testing of a number of advanced and core technologies in the field of space science
The network can detect human heads of various sizes and at different orientations in the image. These results demonstrate that the head detection network has good generalization ability, obtaining stable and accurate head detection results
EXPERIMENTS AND RESULTS In the experiments described the overall pipeline of astronaut tracking algorithm was implemented and transferred to the Tegra X2 embedded AI platform for online application
Summary
Operating on near-Earth orbit for more than ten years, the Chine Space Station will support the development and testing of a number of advanced and core technologies in the field of space science. Improvements in astronaut work efficiency are important for space missions. To assist the astronauts and improving their work efficiency, several in-cabin assistant robots have been proposed for or even sent to the International Space Station (ISS). Typical examples are PSA [1] and Astrobee [2], made by NASA’s Ames Research Center, SPHERES [3] and smart SPHERES [4], made by MIT, IntBall [5], made by JAXA, CIMON, made by Airbus and IBM, and AAR [6], [7], made by the Chinese Academy of Sciences. Int-Ball and Cimon have been sent to the ISS for verification. Int-Ball was maneuvered by controllers and researchers on the ground, taking over photography duties
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
