This isn't my actual project just a discussion. I could never do this unless I won the lottery, too expensive of a venture.

My project was the orange topped pi. Which was a high battery life laptop basically running wheezing.
But the project is pretty well dead. Its been 4 months since I started it and without the orange pi hardware that is a dead end street.
The project was completed with a Raspberry pi 2 and ended up with 35 hours of run time playing videos on a single charge. But I cant exactly release a tutorial that was intended for an orange pi board without an orange pi board. and the raspberry pi one has been done before. The entire point of this was that it would have a solid state drive and only boot from the SD card. which required the SATA connector the orange pi had.

Really interesting discussion going on there. What are your plans for it? And speaking of stepper motors, why not servos? They're easier to control with fewer pins, and less costly as you don't need a separate driver. And as for the decision of using a SBC to control all that is.. bad, I'd recommend a MCU (a cortex M0 atleast)

well dude nice thinking.
1) I would like to tell you that you need to learn some of rotational motion physics as it will be highly useful in building all the necessary mechanics " determining torque
   and forces at different position in your suit".
2) you should not use stepper motor for this project as you might be needing a huge amount of torque at every step if you want you suit to carry you inside and just walk. ans in case if you add steel or metal parts its gonna be bulky so dont use steppers.
3) man first of all find a appropriate power source as i hd too may project all cancelled due to lack of power source. as if you are going to put a hell lot of your time making project and it works only for few minutes. you wont be looking forward to that. SO FIND A PROPER POWER SOURCE.

Servos would also be big bucks in cost because of the torque issue. Anything that strong is drop dead expensive.

Stepper is a good compromise. A hydroponic system for certain areas would work, and the new "electric muscles" would be a possible area of research as well.

Power source right here guys:

   One day soon though...one day soon

Numerous rehabilitation-robotic Program  devices have been developed since the late 90s, particularly for the neurorehabilitation of post-stroke patients (see review in Brewer et al. (2007)). Most of these devices guide the movement of the hand in one plane. Some robots can passively mobilize the limb of patients with poor recovery or can provide precisely controlled active assistance as a function of patient’s capacity. An advantage of robotic assistance is the possibility for patients to carry out a great number of movement repetitions, increasing the intensity of therapy. Recent extensive clinical testing of one of these devices, the InMotion© robot (which has been used in clinical practice for many years) has demonstrated its effectiveness with significant improvements in arm motor capacity after a program of robot therapy.