A Behavior Architecture for Fast Humanoid Robot Door Traversals

TL;DR

An architecture which incorporates GPU accelerated perception and a tree based interactive behavior coordination system with a whole body motion and walking controller and operator-robot interdependence analysis charts to explore how human cognition is combined with artificial intelligence to produce complex robot behavior.

Abstract

Towards the role of humanoid robots as squad mates in urban operations and other domains, we identified doors as a major area lacking capability development. In this paper, we focus on the ability of humanoid robots to navigate and deal with doors. Human-sized doors are ubiquitous in many environment domains and the humanoid form factor is uniquely suited to operate and traverse them. We present an architecture which incorporates GPU accelerated perception and a tree based interactive behavior coordination system with a whole body motion and walking controller. Our system is capable of performing door traversals on a variety of door types. It supports rapid authoring of behaviors for unseen door types and techniques to achieve re-usability of those authored behaviors. The behaviors are modelled using trees and feature logical reactivity and action sequences that can be executed with layered concurrency to increase speed. Primitive actions are built on top of our existing whole body controller which supports manipulation while walking. We include a perception system using both neural networks and classical computer vision for door mechanism detection outside of the lab environment. We present operator-robot interdependence analysis charts to explore how human cognition is combined with artificial intelligence to produce complex robot behavior. Finally, we present and discuss real robot performances of fast door traversals on our Nadia humanoid robot. Videos online at https://www.youtube.com/playlist?list=PLXuyT8w3JVgMPaB5nWNRNHtqzRK8i68dy.

Figures (23)

• Figure 1: The Nadia humanoid robot performing a right pull lever handle door traversal using cycloidal drive forearms and Sake grippers. Corresponding video: 2024NadiaRightPullLeverHandleCycloidLowRes.mp4
• Figure 2: An all inclusive overview of the parts involved in this work.
• Figure 3: The general structure of a tree for door traversals. A high level node triages control to subtrees for particular door types and takes action in failure scenarios to retry set of actions or change strategy.
• Figure 4: To achieve layered, concurrent execution while maintaining a sequence structure, each node has a pointer to a node to execute after. When an action is next for execution, it can start when the action it's waiting for is complete. The first part of a left pull handle door is illustrated as an example.
• Figure 5: An illustration of how we apply sequential composition. During authoring, actions are carefully placed in an order in which the Cartesian result of the action informs the robot about the state of the environment such that it can automatically decide to proceed or not. When control is insufficient, the state will not fall into the stable region of the next action and a high level node will either retry or employ alternative strategies.