-
Precision home robots learn with real-to-sim-to-real
At the top of many automation wish lists is a particularly time-consuming task: chores.ย The moonshot of many roboticists is cooking up the proper hardware and software combination so that a machine can learn โgeneralistโ policies (the rules and strategies that guide robot behavior) that work everywhere, under all conditions.ย Realistically, though, if you have a…
-
A better way to control shape-shifting soft robots
Imagine a slime-like robot that can seamlessly change its shape to squeeze through narrow spaces, which could be deployed inside the human body to remove an unwanted item. While such a robot does not yet exist outside a laboratory, researchers are working to develop reconfigurable soft robots for applications in health care, wearable devices, and…
-
New method uses crowdsourced feedback to help train robots
To teach an AI agent a new task, like how to open a kitchen cabinet, researchers often use reinforcement learning โ a trial-and-error process where the agent is rewarded for taking actions that get it closer to the goal. In many instances, a human expert must carefully design a reward function, which is an incentive…