Developmental Bayesian Optimization of Black-Box with Visual Similarity-Based Transfer Learning

TL;DR

This paper introduces a developmental Bayesian optimization framework that leverages visual similarity-based transfer learning to efficiently tune hyper-parameters of robotic systems, demonstrating significant improvements over traditional methods in simulation and real-world scenarios.

Contribution

The novel framework combines long-term memory, visual similarity, and Bayesian optimization for autonomous hyper-parameter tuning in robots, utilizing transfer learning from past experiences.

Findings

Robot optimized hyper-parameters in 40-68 trials.

Transfer learning based on visual similarity outperforms learning from scratch.

Achieved over 88% success rate with less than 2 hours of training.

Abstract

We present a developmental framework based on a long-term memory and reasoning mechanisms (Vision Similarity and Bayesian Optimisation). This architecture allows a robot to optimize autonomously hyper-parameters that need to be tuned from any action and/or vision module, treated as a black-box. The learning can take advantage of past experiences (stored in the episodic and procedural memories) in order to warm-start the exploration using a set of hyper-parameters previously optimized from objects similar to the new unknown one (stored in a semantic memory). As example, the system has been used to optimized 9 continuous hyper-parameters of a professional software (Kamido) both in simulation and with a real robot (industrial robotic arm Fanuc) with a total of 13 different objects. The robot is able to find a good object-specific optimization in 68 (simulation) or 40 (real) trials. In simulation, we demonstrate the benefit of the transfer learning based on visual similarity, as opposed to an amnesic learning (i.e. learning from scratch all the time). Moreover, with the real robot, we show that the method consistently outperforms the manual optimization from an expert with less than 2 hours of training time to achieve more than 88% of success.