As realistic as some robots can look, it can be obvious that they are still robots namely due to their movements which can come across looking unnatural. This is because unlike humans, robots do not possess the muscles nor the thought processes needed to move more naturally, but researchers at Virginia Tech are hoping to change that.
The researchers are looking to develop a series of algorithms which when combined with sensors, will help robots move with gaits that are more natural-looking and similar to real animals. The idea is that the algorithms will mimic how vertebrates move and balance themselves, which is through oscillating neurons in the spinal cord.
The end result is a robot dog who can walk and run in a way that comes off looking more natural. That being said, while initial tests have proven to be positive, the researchers caution that it will probably be a while before we see any real-world applications.
According to one of the researchers, Kaveh Hamed, he is constantly asking himself, “Are the algorithms we’re using actually bio-inspired? Are they actually acting like dogs? We are trying to do the math. But it must be bio-inspired. We must look at animals and then correct our algorithms — to see how they react to this scenario and how our control algorithms react.”