Dynamic motion learning for multi-DOF flexible-joint robots using active–passive motor babbling through deep learning

Abstract

This paper proposes a learning strategy for robots with flexible joints having multi-degrees of freedom in order to achieve dynamic motion tasks. In spite of there being several potential benefits of flexible-joint robots such as exploitation of intrinsic dynamics and passive adaptation to environmental changes with mechanical compliance, controlling such robots is challenging because of increased complexity of their dynamics. To achieve dynamic movements, we introduce a twophase learning framework of the body dynamics of the robot using a recurrent neural network motivated by a deep learning strategy. The proposed methodology comprises a pre-training phase with motor babbling and a fine-tuning phase with additional learning of the target tasks. In the pretraining phase, we consider active and passive exploratory motions for efficient acquisition of body dynamics. In the fine-tuning phase, the learned body dynamics are adjusted for specific tasks. We demonstrate the effectiveness of the proposed methodology in achieving dynamic tasks involving constrained movement requiring interactions with the environment on a simulated robot model and an actual PR2 robot both of which have a compliantly actuated seven degree-of-freedom arm. The results illustrate a reduction in the required number of training iterations for task learning and generalization capabilities for untrained situations.

A Review of Principal Component Analysis Algorithm for Dimensionality Reduction

“…[8]. Machine learning (ML) encompasses more and more research areas per year, including, for example, bioinformatics [9], [10], biochemistry [11], [12], meteorology of medicine [13]- [16], economics [17]- [19], aquaculture [20], chemo-ecology [21], robotics [22]- [25], and climatology [26], [27].…”

Language Grounding with 3D Objects

“…Unlike 2D internet images, physical objects can be picked up and moved by robot agents. Agents can perform information-seeking behaviors on objects to improve their world [15,16,17] and language understanding [18,19]. Such world interaction is inextricable from language grounding [20], motivating language annotations for higher-fidelity referents than static images.…”

A model-based PID-like motion control method for flexible-joint manipulator with harmonic drives

“…Apart from these methods, some investigators have sought to control flexible manipulators using intelligent techniques, 23 e.g. fuzzy control method, 24 reinforcement learning control, 25 deep-learning 26 etc.…”