Robotics and autonomous systems often utilize a two-tier neuro-symbolic architecture where the first tier uses neural perception modules, such as convolutional neural networks, vision transformers, or event-based sensors, to segment scenes and instantiate logical atoms, while the second tier uses a symbolic task and motion planner to synthesize policies and enforce safety invariants.

Authors

• Person: Not available Organization: Springer
  A Comprehensive Review of Neuro-symbolic AI for Robustness ...

Sources

• A Comprehensive Review of Neuro-symbolic AI for Robustness ... link.springer.com Springer via serper

Referenced by nodes (5)

• neuro-symbolic integration concept
• robotics concept
• Autonomous systems concept
• neural perception module concept
• Convolutional Neural Networks concept