Dynamic Neural Curiosity Enhances Learning Flexibility for Autonomous Goal Discovery

2024-11-29

arXiv.org

AI Summary

Autonomous goal discovery in robotics faces challenges in adaptively balancing exploration and exploitation. Method: Inspired by the locus coeruleus–norepinephrine system, we propose a neurocognitive framework integrating neural curiosity with dynamic attentional modulation. We introduce a unified dynamic neural field (DNF) model that jointly encodes curiosity, visual habituation, and cognitive persistence, synergistically coupled with forward/inverse MLP models, motor-driven stochastic exploration, and inhibition-of-return mechanisms to generate task-dependent learning trajectories and enable continuous exploration–exploitation regulation. Results: Evaluated on multi-difficulty object-pushing tasks, our approach significantly improves flexibility in goal discovery, generalization across visually similar objects, and robustness to environmental changes. It establishes an interpretable, tunable paradigm for unsupervised goal learning in embodied agents.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Learning to Search
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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.

Problem

• Enhancing autonomous goal discovery in robotics through curiosity
• Integrating attention and cognitive processes for learning flexibility
• Using dynamic neural fields to model exploration and exploitation

Innovation

• Dynamic neural fields model curiosity and attention
• Multi-layer perceptrons implement forward and inverse models
• Inhibition of return mechanism enables goal discovery