Avular Autopilot Inference

This page offers an introduction to Avular’s autonomy stack, called Autopilot Inference. It starts with the motivation for giving a robot autonomous capabilities, followed by an overall design of the software functionalities that provide these autonomous capabilities to our robots. The functionalities are then explained via examples of the robot either planning and executing its operation, which will also cover the behavior that can be expected from the robot.

Direct control or autonomous

Robots can be equipped with varying levels of autonomy. Avular is developing a software stack called Autopilot Inference to facilitate this. Autonomy is beneficial when users prefer to issue high-level commands rather than continuously control the robot, allowing them to focus on other tasks.

The level of autonomy determines the robot's decision-making capabilities:

• No Autonomy: The robot requires continuous direct control by the user, who must make all operational decisions.
• Lower Autonomy: The robot's decision-making is more restricted, either due to limited capabilities or user preference.
• Higher Autonomy: The robot can independently make decisions, reducing the need for user intervention to prevent downtime.

Info

Please continue to the autonomous capabilities of the Autopilot Inference.