VASO paper evaluates formally verifiable physical-AI skills on Clearpath Jackal
VASO introduces a verification-guided framework that evolves reusable robot-skill contracts using formal counterexamples and evaluates it on Clearpath Jackal and PX4.
Evidence notes
- The framework couples a formal interface for model checking with a planner-facing interface for generating executable physical behaviors.
- When a generated skill or plan violates temporal specifications, VASO turns the counterexample trace into textual feedback that updates the skill while keeping foundation-model weights frozen.
- On Clearpath Jackal and PX4 quadcopter tasks, the paper reports 97.2% formal-specification compliance using fewer than 100 optimization samples.
Company overview
Clearpath Robotics builds unmanned ground vehicles and mobile robot platforms for research, development and field robotics, including Jackal, Husky and related robot bases.