← Back to Benchmarks
simmediumroboticsmetric · varies
Modernising Reinforcement Learning-Based Navigation for Embodied Semantic Scene Graph Generation
Description
Semantic world models enable embodied agents to reason about objects, relations, and spatial context beyond purely geometric representations. In Organic Computing, such models are a key enabler for objective-driven self-adaptation under uncertainty and resource constraints. The core challenge is to acquire observations maximising model quality and downstream usefulness within a limited action budget. Semantic scene graphs (SSGs) provide a structured and compact representation for this purpose.