Know your limits! Optimize the robot's behavior through self-awareness

TL;DR

This paper presents a deep-learning system that enables humanoid robots to self-assess and adapt their behaviors for improved safety and task execution by predicting their performance and selecting optimal reference motions.

Contribution

The authors introduce the Self-AWare (SAW) model that predicts robot performance and selects optimal behaviors, enhancing robot autonomy and safety in real-world tasks.

Findings

SAW can anticipate falls with 99.29% accuracy.

The system effectively ranks multiple reference motions for optimal task execution.

Integration of motion generation, control, and self-awareness improves robot adaptability.

Abstract

As humanoid robots transition from labs to real-world environments, it is essential to democratize robot control for non-expert users. Recent human-robot imitation algorithms focus on following a reference human motion with high precision, but they are susceptible to the quality of the reference motion and require the human operator to simplify its movements to match the robot's capabilities. Instead, we consider that the robot should understand and adapt the reference motion to its own abilities, facilitating the operator's task. For that, we introduce a deep-learning model that anticipates the robot's performance when imitating a given reference. Then, our system can generate multiple references given a high-level task command, assign a score to each of them, and select the best reference to achieve the desired robot behavior. Our Self-AWare model (SAW) ranks potential robot behaviors based on various criteria, such as fall likelihood, adherence to the reference motion, and smoothness. We integrate advanced motion generation, robot control, and SAW in one unique system, ensuring optimal robot behavior for any task command. For instance, SAW can anticipate falls with 99.29% accuracy. For more information check our project page: https://evm7.github.io/Self-AWare