To end the paper, we briefly use the evolved DSM robot controller to consolidate two of the points made earlier pertaining to fault tolerance.
Firstly, notice that the contents of the RAM were directly encoded bit-for-bit onto the genotype. A genetic mutation in the RAM coding region causes one of the bits in the RAM to be inverted: the same effect as a single-stuck-at (SSA) fault in the RAM's memory array. By the argument of Section 14, there should therefore be a tendency for the evolved controller to be tolerant to such SSA faults. Fig. 8 shows that the evolved wall-avoider DSM is indeed quite robust to adverse SSA faults -- observation of the robot's qualitative behaviour bears this out -- but it is not known how much is due to the action of evolution, and how much is simply a property of the DSM architecture. The 32 possible adverse SSA faults were each emulated in turn by writing the opposite value to that specified by the genotype to the RAM bit in question. For each fault, the DSM was then used to control the robot (in the virtual environment) for sixteen 90-second runs from the same starting position, and the average fitness was measured to give the data in the figure. The results are in accord with the theory, but gathering sufficient data from the real robot actually to verify the theory would be prohibitively time-consuming: hence the ongoing study using NK landscapes mentioned in Section 14.
The second experiment was to introduce the SSA fault marked with an arrow in Fig. 8 as a permanent feature in the DSM, and then to allow the already-evolved population to evolve further. At first, the fitness of the population was significantly lowered, with none of the individuals performing as well as the best of the population used to, but after 10 generations the mean and best fitnesses of the population had recovered to their previous values. This approach to fault-tolerance (proposed in Section 16 above) would be useful when transferring the evolved controller from one piece of hardware to another, or to cope with long-lasting faults within one.
Figure 8: Sensitivity to adverse SSA faults.