"It's not the Turing test just yet, but in one more domain, AI is becoming increasingly competitive with humans. This time around, it's in interplanetary trajectory optimization. From the European Space Agency comes the news that researchers from its Advanced Concepts Team have recently won the Gold 'Humies' award for their use of Evolutionary Algorithms to design a spacecraft's trajectory for exploring the Galilean moons of Jupiter (Io, Europa, Ganymede and Callisto). The problem addressed in the awarded article (PDF) was put forward by NASA/JPL in the latest edition of the Global Trajectory Optimization Competition. The team from ESA was able to automatically evolve a solution that outperforms all the entries submitted to the competition by human experts from across the world. Interestingly, as noted in the presentation to the award's jury (PDF), the team conducted their work on top of open-source tools (PaGMO / PyGMO and PyKEP)."
LeopoldS on 19 Jan 13nice - did not know about it. GTOC on steroids and with loads of cash. concerning this specific challenge and especially the last condition: doesn't this hint towards a flawed design? In addition to maximizing the total power output there are some constraints on the possible movements: Each SARJ and BGA is limited to a maximum angular velocity and to a maximum angular acceleration. Each SAW must produce at least some minimum average power over the orbit (which is different for each SAW). The sequence of positions must be cyclic, so it can be repeated on the next orbit. The maximum amount of BGA rotation is not limited, but exceeding a threshold will result in a score penalty. Some structural members of the SAW mast (called Longerons) have restrictions on how they can be shadowed.
Joris _ on 26 Jan 13The longerons will expand and contract with exposition to sun (I think whatever the material they are made of). Because you have 4 longerons in a mast, you just need to be carefull that the mast is well balanced, and that the 4 longerons support each other, basically, you need an even number of shadowed longerons, possibly 0 too. I would call this an operational constraint.
