Intrinsic Motivation and Mental Replay enable Efficient Online Adaptation in Stochastic Recurrent Networks

TL;DR

This paper introduces a bio-inspired stochastic recurrent neural network framework that enables robots to adapt quickly and efficiently to new environments through intrinsic motivation and mental replay, requiring minimal physical interactions.

Contribution

It presents a novel probabilistic online motion planning method with rapid adaptation capabilities using intrinsic motivation and mental replay in a stochastic recurrent neural network.

Findings

Rapid adaptation to unknown workspace constraints

Sample-efficient learning from few physical interactions

Effective online planning demonstrated on a KUKA LWR arm

Abstract

Autonomous robots need to interact with unknown, unstructured and changing environments, constantly facing novel challenges. Therefore, continuous online adaptation for lifelong-learning and the need of sample-efficient mechanisms to adapt to changes in the environment, the constraints, the tasks, or the robot itself are crucial. In this work, we propose a novel framework for probabilistic online motion planning with online adaptation based on a bio-inspired stochastic recurrent neural network. By using learning signals which mimic the intrinsic motivation signalcognitive dissonance in addition with a mental replay strategy to intensify experiences, the stochastic recurrent network can learn from few physical interactions and adapts to novel environments in seconds. We evaluate our online planning and adaptation framework on an anthropomorphic KUKA LWR arm. The rapid online adaptation is shown by learning unknown workspace constraints sample-efficiently from few physical interactions while following given way points.