Event
New Framework Enables Pretrained Robot Models to Satisfy STL Constraints at Execution Time
1 reports · 1 sources
Sadık Bera Yüksel and Derya Aksaray propose a specification-aware action distribution optimization framework that enforces a class of signal temporal logic (STL) constraints at execution time without modifying the parameters of pretrained robot foundation models. At each decision step, the method rolls out the remaining horizon via forward dynamics and computes a minimally modified action distribution that satisfies hard STL feasibility constraints. The authors state that they validated the approach in simulation with a current state-of-the-art robot foundation model across multiple environments and complex specifications; no real-robot experiments were reported.
Report timeline
- Specification-aware action distribution optimization framework for robotics foundation models
The paper proposes a specification-aware action distribution optimization framework that enforces a class of Signal Temporal Logic (STL) constraints at execution time without modifying the parameters of a pretrained robotics foundation model. At each decision step, the method reasons over the remaining horizon via forward dynamics propagation to compute a minimally modified action distribution that satisfies a hard STL feasibility constraint, and it is validated in simulation with state-of-the-art robotics foundation models across multiple environments and complex specifications.
arXiv cs.RO ·
Related topics
Interest trend
- Current
- 3
- Peak
- 4Nov 4 01:00
- Past 24 hours
- –
The trend compares participants observed throughout the same period, so its range may be smaller than the current interest count. Move or tap to inspect each hour; use the arrow keys on a keyboard.