VASO paper evaluates formally verifiable physical-AI skills on Clearpath Jackal
Evidence notes
- The VASO paper introduces a self-evolving robot-skill method that turns formal-verification counterexamples into updates for reusable skill contracts.
- The paper evaluates Clearpath Jackal and PX4 quadcopter tasks and reports 97.2% formal-specification compliance using fewer than 100 optimization samples.
Company context
Clearpath Robotics builds unmanned ground vehicles and mobile robot platforms for research, development and field robotics, including Jackal, Husky and related robot bases.