Spyndra is a quadruped robot for studying machine self-awareness. Utilizing minimal proprioceptive sensation to track its internal motor commands and record its own orientation and acceleration, the robot can learn about its physical form.
The robot has eight motors, an IMU, and runs Raspberry-PI 3. It requires non-intuitive motor commands in order to locomote, and thus provides an interesting challenge for gait learning algorithms. It is self-aware to the degree it can simulate itself, and that self-simulation is essentially the ability to predict sensations from actions.
The robot has eight high-torque metal gear analog servo motors (Power HD 1501MG) which directly drive each joint of the robot. The two-pronged femurs support both sides of the motors to prevent load paths orthogonal to the motors intended axis of motion. This design principle maximizes servo life and improves Spyndra’s overall robustness. The motors slide effortlessly into place in both the chassis and tibia, and are connected to the femur using standard servo horns. This direct drive, as opposed to Aracna’s linkage system, results in lowfriction/low hysteresis motion that can be more accurately represented in simulation.
Project by: Columbia University
Source: ShaSha Lee via Youtube channel
You want to see more interesting videos and pictures about engineering like this?
So check out @engineering_aviation
@engineering_aviation and you will see a new post about your passion.
We are looking forward to see you! ——————————————————————————————
All rights and credits reserved to the respective owner(s).
If you are the copyright owner of this video and would not like to have this content featured on this channel, direct message us to have us remove it.
#worldofengineering #machining #gear #metal #metalwork #automotiveengineering #aerospace #aerospaceengineering #mechanicalengineering #materialscience #metallurgy #fabrication #manufacturing #engineering_memes #engineeringlovers #engineeringlife #engineeringblog #engineeringfirstprinciples #engineer - 29 minutes ago