Paper Abstract Robots require the ability to autonomously and continuously react to unexpected online changes in the task definition and in the environment, especially those cohabited with humans. To react to these changes, the task, from the current state up to the finish, must instantly be reconsidered. This implies a prohibitive re-computation cost.
This paper proposes a modular control architecture based on Model Predictive Control, that offers a good compromise between optimally achieving the task and the required computation time, by only reconsidering the near future.
[Read More]
AUCTUS is an Inria Project team in collaboration with ENSC. The general objective of the team is to design robotic assistance systems or collaborative robots for Humans at work, in particular in the industrial sector.
The increase of the physical and cognitive capacities of the Homo Faber through the development of tools knows a new golden age by the advent of the collaborative robotics coupled with the artificial intelligence. Man is able to share with a machine his movement, his motor intelligence, but also his decisions. The challenge is then to design the machine part of the cybernetic couple for the successful realization of a task, while preserving the man in his physical and cognitive integrity and in his capacity of adaptation and decision.
The robotics community still tends to separate the cognitive (HRI) and physical (pHRI) aspects of human/robot interaction. One of the main challenges is to characterize the task as well as mechanical, physiological and cognitive capacities of humans in the form of physical constraints or objectives for the design of cobotized workstations. This design is understood in a large sense: the choice of the robot’s architecture (cobot, exoskeleton, etc.), the dimensional design (human/robot workspace, trajectory calculation, etc.), the coupling mode (comanipulation, teleoperation, etc.) and control. The approach then requires the contributions of the human and social sciences to be considered in the same way as those of exact sciences. The topics considered are broad, ranging from cognitive sciences, ergonomics, human factors, biomechanics and robotics.
Scientific Axes
- Analysis and modeling of behavior
- Links between Human Sciences and Artificial Intelligence
- Set analysis of postures, gestures and human movements
- Operator / robot coupling
- Optimizing the performance of an operator / robot couple
- Mediation of perceptions of an operator / robot couple
- Design of collaborative robots and robotic assistance systems
- Architectural design
- Control design
- Methodological support: experiments and technological developments
- Innovative sensors
- Experiments
Latest News
Paper Abstract Efficient workspace sharing of collaborative robots and human operators remains an unsolved problem in the industry. This problem goes beyond the use of a priori or a posteriori safety measures and has to be tackled at the control level. To address the need of adaptation to human presence as well as to endow the robot with the ability to adapt interactively to new Cartesian targets, a linear Model Predictive Controller is proposed in this paper.
[Read More]
Abstract Inverse optimal control (IOC) is a framework used in many fields, especially in robotics and human motion analysis. In this context, many methods of resolution have been proposed in the literature. This article presents the Projected Inverse Optimal Control (PIOC), an approach that puts forward a simple and comprehensive view of IOC methods. Especially, we explain how the presence of uncertainties can be properly addressed in our view. Thus, this article highlights how classical methods can be understood as projections of trajectories in the solution space of the underlying Direct Optimal Control (DOC) problem.
[Read More]
Reachable space of robotic manipulators has complex geometry and is often hard to characterise, therefore it is usually calculated in advance by the robot manufacturers and given as an image in their datasheets (as shown on the image on the right). However these images are hard to exploit as they are not analytical solutions to this problem. Even if we would have an analytical solution to this problem it would still not include in its consideration robot’s dynamics, its payload or its actuator torque limits.
[Read More]
The aim of this project is to use pieces of softwares developed at Auctus to manipulate LEGO. This work can be related to experiments for Benjamin Camblor’s thesis and the PacBot project.
Live demonstration Here is a video of a manipulation demo. The robot realizes three tasks:
Remove a single LEGO on a tower Put LEGO on the plate Put LEGO on another LEGO All this work is done using the softwares developed at Auctus, namely :
[Read More]