REAL-X -- Robot open-Ended Autonomous Learning Architectures: Achieving Truly End-to-End Sensorimotor Autonomous Learning Systems

TL;DR

This paper introduces the REAL-X benchmark for open-ended robot learning and presents architectures capable of autonomous sensorimotor learning, demonstrating promising results in complex, realistic scenarios.

Contribution

It studies the challenges of open-ended learning benchmarks and proposes adaptive robot architectures that can handle multiple complex learning tasks.

Findings

REAL-X architectures solve various benchmark tasks effectively.

The benchmark tests exploration, generalisation, and autonomous skill acquisition.

REAL-X achieves high performance in demanding conditions.

Abstract

Open-ended learning is a core research field of developmental robotics and AI aiming to build learning machines and robots that can autonomously acquire knowledge and skills incrementally as infants and children. The first contribution of this work is to study the challenges posed by the previously proposed benchmark `REAL competition' aiming to foster the development of truly open-ended learning robot architectures. The competition involves a simulated camera-arm robot that: (a) in a first `intrinsic phase' acquires sensorimotor competence by autonomously interacting with objects; (b) in a second `extrinsic phase' is tested with tasks unknown in the intrinsic phase to measure the quality of knowledge previously acquired. This benchmark requires the solution of multiple challenges usually tackled in isolation, in particular exploration, sparse-rewards, object learning, generalisation, task/goal self-generation, and autonomous skill learning. As a second contribution, we present a set of `REAL-X' robot architectures that are able to solve different versions of the benchmark, where we progressively release initial simplifications. The architectures are based on a planning approach that dynamically increases abstraction, and intrinsic motivations to foster exploration. REAL-X achieves a good performance level in very demanding conditions. We argue that the REAL benchmark represents a valuable tool for studying open-ended learning in its hardest form.