1. This article presents the concepts to build, sense and control a completely untethered tensegrity robotic system called SUPERball.
2. The robot is designed to enable research into tensegrity robots for planetary landing and exploration as part of a NASA funded program.
3. Control policies are developed using Monte Carlo, evolutionary algorithms, and advanced supervised learning through Guided Policy Search.
The article appears to be reliable in terms of its content, as it provides detailed information about the design, building, testing, and control of the SUPERball robot. The authors provide evidence for their claims by citing relevant research papers and experiments conducted on the physical robot. Furthermore, they discuss potential risks associated with the use of the robot in planetary exploration missions.
However, there are some potential biases in the article that should be noted. For example, the authors focus mainly on the advantages of using tensegrity robots for planetary exploration without exploring any potential drawbacks or counterarguments. Additionally, they do not present both sides equally when discussing potential risks associated with using such robots in space missions; instead they focus mainly on how these risks can be mitigated rather than exploring why they exist in the first place.
In conclusion, while this article is generally reliable in terms of its content and provides evidence for its claims, there are some potential biases that should be taken into consideration when evaluating its trustworthiness and reliability.