As an offspring of the LARSEN team, HUCEBOT pursues the same goal of leveraging artificial intelligence and machine learning methods to advance robotics skills in terms of autonomy and interaction with the environment and humans.
Thanks to the diverse sets of skills of our team members, HUCEBOT first specializes in machine learning, the human-robot interaction, control research lines improving collaboration and translation into algorithms in order to control the robot’s movement and predict the human’s intent. Our team distinguishes itself by the quality of our software, models and algorithms, which simulate and control both humanoid robots and digital humans. Hucebot particularly takes great care in curating their tools for human-centered robots, i.e., robots that consider the human status and intention into their control and can physically assist them to the best of their capacity.
Objective
The goal of HUCEBOT is to improve the human well-being at work using human-centered robots by either physically assisting or replacing the human at work. While the first alternative uses collaborative robotics solutions such as exoskeletons to reduce the humans’ effort and minimize the risk of musculoskeletal disorders, the second replaces the human in dangerous and/or remote situations, using teleoperated robotic avatars that continuously interact with the operators and assist them in their remote operations. Our fundamental principle is that robots need to consider the human in their control, learning and adaptation processes.
Research Axes
Whole-body control
The first objective of HUCEBOT is to design whole-body control schemes and algorithms that enable humanoid robots, exoskeletons or digital human models to control their movements while interacting with the environment engaging multiple contacts, manipulating heavy payloads, and executing agile and dynamic tasks. We aim to design “human-aware” collaborative controllers: whole-body controllers that consider the human dynamics, and anticipate the human intents.
Digital human modeling and simulation
Our second objective is to develop algorithms for the physical simulation of humans interacting with robots. Here the challenge is to be able to simulate their mutual interaction and in particular the effect that the robot has on the human body, considering individual factors and aligning as much as possible the simulation to the reality.
Data-driven human motion prediction
We aim at developping machine learning algorithms to predict the human future movement or intention so that the robot can anticipate the motion of the human in time and thus better assist them. We aim at contributing to the numerous machine learning approaches by focusing on short predictions and work on models that quantify their uncertainty and express different possible futures.
Application Fields
Physical Assistance to Improve Ergonomics at Work
