Experimental protocol and results for a representative subject. This subject (30 year old male) participated in each of the three experimental protocols – A: Assistance-as-needed (AAN), B: AAN with Noise Insensitivity, and C: AAN with Improper Parameter Selection. For each protocol, the subject first adapted to the virtual impairment without assistance (steps 191–290). The after effect of adaptation, indicative of internal model formation, is apparent at step 291 in A, B, and C. Then, following a period in which adaptation was washed out (steps 291–390), the subject adapted again to the virtual impairment (steps 391–591), but with the form of robotic assistance associated with the particular protocol. In all three protocols, the step height errors when the virtual impairment was turned on were much smaller (step 391, A, B, C). The robot assistance decreased for the basic AAN algorithm, but not all the way to zero (E, trace labelled "A"). The robot assistance decreased to zero for the AAN with Noise Insensitivity algorithm (E, trace labelled "B"). The robot took over the task for the AAN with Improper Parameter Selection algorithm (i.e. with fR > fH) (E, trace labelled "C"). Note that the virtual impairment force (D) was unexpectedly turned on or off ("catch trials") to measure direct effects (steps 40–140) and after effects (steps 491–591).