Malleable Agents for Re-Configurable Robotic Manipulators

TL;DR

This paper introduces a deep reinforcement learning agent with sequence neural networks that can adapt to reconfigurable robotic arms with varying link numbers, enhancing flexibility and generalization in robotic manipulation.

Contribution

The paper presents a novel RL agent architecture with embedded sequence networks and domain randomization for adaptable control of reconfigurable robots.

Findings

Agent effectively transfers to different arm configurations

Network generalizes well to unseen link numbers

Simulation results demonstrate successful adaptation

Abstract

Re-configurable robots have more utility and flexibility for many real-world tasks. Designing a learning agent to operate such robots requires adapting to different configurations. Here, we focus on robotic arms with multiple rigid links connected by joints. We propose a deep reinforcement learning agent with sequence neural networks embedded in the agent to adapt to robotic arms that have a varying number of links. Further, with the additional tool of domain randomization, this agent adapts to different configurations. We perform simulations on a 2D N-link arm to show the ability of our network to transfer and generalize efficiently.