A rigorous formalization of desired system requirements is indispensable when performing
any verification task. This often limits the application of verification techniques, as writing …

We address the problem of teaching a deep reinforcement learning (RL) agent to follow
instructions in multi-task environments. Instructions are expressed in a well-known formal …

Temporal Logic (TL) can be used to rigorously specify complex high-level specification for
systems in many engineering applications. The translation between natural language (NL) …

To make robots accessible to a broad audience, it is critical to endow them with the ability to
take universal modes of communication, like commands given in natural language, and …

We study the generalization abilities of language models when translating natural language
into formal specifications with complex semantics. In particular, we fine-tune language …

Grounding navigational commands to linear temporal logic (LTL) leverages its unambiguous
semantics for reasoning about long-horizon tasks and verifying the satisfaction of temporal …

This is a demonstration of our newly released Python package NL2LTL which leverages the
latest in natural language understanding (NLU) and large language models (LLMs) to …

Text-based games present a unique class of sequential decision making problem in which
agents interact with a partially observable, simulated environment via actions and …

While safe reinforcement learning (RL) holds great promise for many practical applications
like robotics or autonomous cars, current approaches require specifying constraints in …

Cooking recipes are especially challenging to translate to robot plans as they feature rich
linguistic complexity, temporally-extended interconnected tasks, and an almost infinite space …