Google Hopes to Hasten Robot Learning through Shared Information

Robot Learning pic

Robot Learning
Image: research.googleblog.com

Valerie Varnuska, a resident of Westbury, NY, has an interest in machinery and robotics. Valerie Varnuska enjoys seeing the unique ways robots can walk and the developments made in the movement of robotic hands.

In a recent blog post written by Google Brain Team’s Sergey Levine, Timothy Lillicrap, and Mrinal Kalakrishnan, a plan was revealed for speeding up the process of robotic learning. The plan relies on sharing information among robots, which should ease the burden of teaching individual robots the same set of tasks.

By using cloud robotics combined with deep neural networks, it is expected that robots will be able to learn for themselves instead of being programmed. This will hasten the learning process and make it more effective, especially when complex tasks are involved. (Hopefully, they will build in from inception, a secure way for humans to have the capability of overriding any robot “decisions.”)

To support the plan, a series of studies was done that looked at the effectiveness of neural networks and cloud learning in three different scenarios. The first scenario taught robots basic motor skills through trial-and-error.

The robots attempted to open a door multiple times and then sent data about their performances to a server. This data built a new neural network that was updated and sent back to the robots.

Meanwhile, the second scenario created internal models of objects and behaviors in addition to the trial-and-error method. The third scenario involved humans teaching skills to robots. In all three tests, when data was shared among the robots, all the robots’ learning processes were accelerated.

Advertisements

The Unique Connection between Smell and Memories

Smell and Memory pic

Smell and Memory
Image: health.howstuffworks.com

Possessing a unique range of interests, Valerie Varnuska enjoys everything from trains and robotics to nature and travel. The Westbury, NY, resident is often reminded of her past through unique smells. When she smells fresh tar, Valerie Varnuska is reminded of summer road trips. The smell of skunk reminds her of fun hikes she has taken with friends.

The human sense of smell is linked to memory more closely than most of the other senses. When a new smell is received, the olfactory bulb processes it before sending it to the brain.

The olfactory bulb is connected to the hippocampus and amygdala, two components in the brain that are heavily involved in memory and emotion. This connection makes it easier for the brain to associate specific emotions and memories with certain smells.

Since no other senses pass through the hippocampus and amygdala, smell possesses the unique ability to invoke strong memories. This powerful association between smells and memories can be both a benefit and a hindrance.

Smells have been said to bring about the feeling of going back in time. As a result, emotions and memories can be recreated through smells.