Self-learning and adaptation in a sensorimotor framework
This work addresses the challenge of autonomous robot learning and adaptation in dynamic environments, representing an incremental improvement by combining existing methods like Gaussian processes and RRT* for enhanced performance.
The authors tackled the problem of enabling robots to autonomously learn sensorimotor patterns for task completion by predicting action sequences based on learned contingencies, achieving results such as high-dimensional control (10x15 dimensions), short training times (less than 12 seconds), and real-time adaptation capabilities.
We present a general framework to autonomously achieve a task, where autonomy is acquired by learning sensorimotor patterns of a robot, while it is interacting with its environment. To accomplish the task, using the learned sensorimotor contingencies, our approach predicts a sequence of actions that will lead to the desirable observations. Gaussian processes (GP) with automatic relevance determination is used to learn the sensorimotor mapping. In this way, relevant sensory and motor components can be systematically found in high-dimensional sensory and motor spaces. We propose an incremental GP learning strategy, which discerns between situations, when an update or an adaptation must be implemented. RRT* is exploited to enable long-term planning and generating a sequence of states that lead to a given goal; while a gradient-based search finds the optimum action to steer to a neighbouring state in a single time step. Our experimental results prove the successfulness of the proposed framework to learn a joint space controller with high data dimensions (10$\times$15). It demonstrates short training phase (less than 12 seconds), real-time performance and rapid adaptations capabilities.