Strategic Objectives
• Master the architecture of symbol grounding in real-world environments.
• Understand how robots bridge the gap between pixels and predicates.
• Explore the intersection of spatial reasoning and linguistic semantics.
• Implement robust frameworks for human-robot collaborative tasks.
The Core Challenge
Artificial intelligence can talk, but most systems lack a fundamental understanding of what 'heavy' feels like or where 'behind the chair' actually is.
01
The Essence of Grounding
02
The Embodied Mind
03
Visual Perception
04
Naming the World
05
Spatial Semantics
06
Mapping the Terrain
07
The Language of Action
08
Affordances and Interaction
09
Multimodal Fusion
10
Situational Context
11
Point of View
12
Knowledge Representation
13
Deep Learning for Grounding
14
Reinforcement Learning
15
Natural Language Understanding
16
Simultaneous Localization and Mapping
17
Human-Robot Dialogue
18
Proprioception and Haptics
19
Joint Attention
20
Sim-to-Real Transfer
21
The Future of Grounded AI
Explore Research Ecosystem
Available eBook Editions
Arabic
English
French
German
Italian
Japanese
Korean
Portuguese
Spanish
