'Ambidextrous' robot could speed up online order processing

Scientists have showcased an'ambidextrous' robot that can learn different ways of moving their arms grippers to pick up objects in the most effective way. Researchers have created a system that allows robots with multiple arms to analyse and rapidly decide which grips would work best to pick up an object. The latest invention could help speed up processing in warehouses for e-commerce orders, as two separate orders can be process efficiently at the same time. Scientists have showcased an'ambidextrous' robot that can learn different ways of moving their arms grippers to pick up objects in the most effective way. It uses a'reward function' assigned to each type of gripper which the robot and then calculates the probability of each type of grip succeeding on a specific item.