Specification-Aware Distribution Shaping for Robotics Foundation Models
This work tackles safety and constraint satisfaction for robotics foundation models, which is an incremental improvement for ensuring reliable robot deployment.
The paper addresses the lack of formal safety guarantees in robotics foundation models by proposing a specification-aware action distribution optimization framework that enforces Signal Temporal Logic constraints during execution without modifying the model's parameters, validated in simulation across multiple environments and complex specifications.
Robotics foundation models have demonstrated strong capabilities in executing natural language instructions across diverse tasks and environments. However, they remain largely data-driven and lack formal guarantees on safety and satisfaction of time-dependent specifications during deployment. In practice, robots often need to comply with operational constraints involving rich spatio-temporal requirements such as time-bounded goal visits, sequential objectives, and persistent safety conditions. In this work, we propose a specification-aware action distribution optimization framework that enforces a broad class of Signal Temporal Logic (STL) constraints during execution of a pretrained robotics foundation model without modifying its parameters. At each decision step, the method computes a minimally modified action distribution that satisfies a hard STL feasibility constraint by reasoning over the remaining horizon using forward dynamics propagation. We validate the proposed framework in simulation using a state-of-the-art robotics foundation model across multiple environments and complex specifications.