Dynamic Neural Curiosity Enhances Learning Flexibility for Autonomous Goal Discovery
This work addresses the challenge of enabling robots to autonomously learn new goals, which is an incremental advancement in robotics and AI.
The paper tackles the problem of autonomous goal discovery in robotics by proposing a dynamic neural curiosity model that integrates curiosity, attention, and cognitive processes, resulting in a robot that demonstrates varied learning trajectories and effective switching between exploration and exploitation for tasks like pushing objects in different directions.
The autonomous learning of new goals in robotics remains a complex issue to address. Here, we propose a model where curiosity influence learning flexibility. To do so, this paper proposes to root curiosity and attention together by taking inspiration from the Locus Coeruleus-Norepinephrine system along with various cognitive processes such as cognitive persistence and visual habituation. We apply our approach by experimenting with a simulated robotic arm on a set of objects with varying difficulty. The robot first discovers new goals via bottom-up attention through motor babbling with an inhibition of return mechanism, then engage to the learning of goals due to neural activity arising within the curiosity mechanism. The architecture is modelled with dynamic neural fields and the learning of goals such as pushing the objects in diverse directions is supported by the use of forward and inverse models implemented by multi-layer perceptrons. The adoption of dynamic neural fields to model curiosity, habituation and persistence allows the robot to demonstrate various learning trajectories depending on the object. In addition, the approach exhibits interesting properties regarding the learning of similar goals as well as the continuous switch between exploration and exploitation.