Differentiable SpaTiaL is the first fully tensorized, end-to-end differentiable symbolic spatio-temporal logic framework that enables gradient-based trajectory optimization and parameter learning for robotic manipulation under geometric and temporal constraints.
Recurrent neural network controllers for signal temporal logic specifications subject to safety constraints
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Differentiable SpaTiaL: Symbolic Learning and Reasoning with Geometric Temporal Logic for Manipulation Tasks
Differentiable SpaTiaL is the first fully tensorized, end-to-end differentiable symbolic spatio-temporal logic framework that enables gradient-based trajectory optimization and parameter learning for robotic manipulation under geometric and temporal constraints.