Creativity in Robot Manipulation with Deep Reinforcement Learning

TL;DR

This paper demonstrates that deep reinforcement learning enables robots to develop creative, human-like manipulation strategies and exhibit persistence and discernment in complex tasks.

Contribution

It shows that DRL can lead to innovative robot behaviors and decision-making in challenging manipulation scenarios, highlighting its potential for advanced robotic control.

Findings

Robots perform successfully in complex manipulation tasks.

Robots develop creative and non-intuitive solutions.

Robots show persistence and discernment in task execution.

Abstract

Deep Reinforcement Learning (DRL) has emerged as a powerful control technique in robotic science. In contrast to control theory, DRL is more robust in the thorough exploration of the environment. This capability of DRL generates more human-like behaviour and intelligence when applied to the robots. To explore this capability, we designed challenging manipulation tasks to observe robots strategy to handle complex scenarios. We observed that robots not only perform tasks successfully, but also transpire a creative and non intuitive solution. We also observed robot's persistence in tasks that are close to success and its striking ability in discerning to continue or give up.