REAL-X -- Robot open-Ended Autonomous Learning Architectures: Achieving Truly End-to-End Sensorimotor Autonomous Learning Systems
This work addresses the problem of developing truly end-to-end sensorimotor autonomous learning systems for developmental robotics and AI, providing a valuable benchmark and architectures for the research community.
This paper tackles the challenges of the REAL competition, a benchmark for open-ended learning in robots, which involves an intrinsic phase of autonomous sensorimotor learning and an extrinsic phase of testing on unknown tasks. The authors propose REAL-X, a set of robot architectures based on planning with dynamic abstraction and intrinsic motivations, which successfully solves different versions of the benchmark under demanding conditions.
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.