Category: Robots
-
Training robots. Training humans…
Multi-domain operations, the Army's future operating concept, requires autonomous agents with learning components to operate alongside the warfighter. New research reduces the unpredictability of current training reinforcement learning policies so that they are more practically applicable to physical systems, especially ground robots. (1) Robots can be trained. But is that an argument in favor of…
-
Creating. Roaming free. (Will you kill me?)
Robots exploring deep bodies of water can only go so far before needing to recharge and upload data. Purdue University engineers have designed a mobile docking station system that would help them go farther. (1) How proud we are when creating something. Especially when creating something autonomous. Something that will roam free and independent. So…
-
Touching with light…
In a lab at Columbia University, engineers have developed a strange yet clever way for robots to feel: Let’s call it the finger of light. It’s got a 3D-printed skeleton embedded with 32 photodiodes and 30 adjacent LEDs, over which is laid a squishy skin of reflective silicone, which keeps the device’s own light in…
-
Algorithms. Jail. Peoples’ lives.
An algorithm takes decisions about peoples’ live and decides whether and how they will potentially go to jail again. The algorithm is one of many making decisions about people’s lives in the United States and Europe. Local authorities use so-called predictive algorithms to set police patrols, prison sentences and probation rules. In the Netherlands, an…
-
Finding your way…
A team at Facebook AI has created a reinforcement learning algorithm that lets a robot find its way in an unfamiliar environment without using a map. (1) Finding your way without a map. Is there any other way? With a map, you will always return at home. But what is home? Were you not born…
You must be logged in to post a comment.