Advancing the physical intelligence and performance of roBOTs towards human-like bi-manual objects MANipulation
Pioneering Bimanual Mobile Robots for Challenging Work Environments
Project Summary
MANiBOT aims to empower bi-manual, mobile, service robots with superior physical capabilities able to perform a wide variety of manipulation tasks, with highly diverse objects, in a human-like manner and performance, in diverse, challenging environments.
The project seeks to revolutionise the robotics landscape by enhancing robot's handling skills, including simple grasping, pick-and-place operations, bi-manual and non-prehensile manipulation, and ensuring adaptive responses to changing environments or to the properties of objects.
To achieve these capabilities, innovations will be developed in the fields of advanced environment understanding, efficient manipulation techniques, robot cognitive functions and physical intelligence. The researchers will implement their solutions with a focus on baggage handling and supermarket shelves’ restocking, with piloting of robots in relevant environments.
Why MANiBOT?
Despite advances in robotic perception, understanding and control, collaborative service robots still demonstrate limited physical performance compared to that of humans. This is particularly the case when it comes to the sought-after capability of safe and efficient robot-environment interaction with diverse object manipulation in real, human-populated spaces. Because of this, the uptake of such robots in key sectors is still limited compared to their vast potential uses.
Industrial-grade robots demonstrate a high physical performance with fast, dexterous and robust object handling, resembling that of humans or beyond, but only in the context of handling well- known, modelled objects, in controlled environments.
Despite advances in robotic perception, understanding and control, collaborative service robots still demonstrate limited physical performance compared to that of humans. This is particularly the case when it comes to the sought-after capability of safe and efficient robot-environment interaction with diverse object manipulation in real, human-populated spaces. Because of this, the uptake of such robots in key sectors is still limited compared to their vast potential uses.
Industrial-grade robots demonstrate a high physical performance with fast, dexterous and robust object handling, resembling that of humans or beyond, but only in the context of handling well- known, modelled objects, in controlled environments.
Empowering service robots with advanced physical functionalities, capabilities, and efficiency that can allow them to achieve a wide variety of manipulation tasks in real-world environments, in a bi- manual, human-like manner and performance remains an open challenge and needs major advances on a series of interdisciplinary research topics.
Once achieved, these advances will boost these robots’ usage and their impact in new, major sectors of industry and services, from logistics, transport and retail, to agri-food, healthcare, and manufacturing unlocking their true potential.
Our Innovations
MANiBOT researchers will advance and bring together technologies ranging from multimodal perception, cognition and control to novel cognitive mechatronics. The project will develop:
New environment understanding and object/pose recognition methods
empowered through an adaptive, context-aware fusion of vision, proximity and tactile sensing. This will allow fast and effective manipulation, even of unknown objects, in environments with a human presence.
A novel suite of manipulation primitives
including non-prehensile manipulations. This will allow the transfer of diverse objects with various sizes, weights, shapes, materials and rigidities from a mobile robot, even within significant spatial constraints.
Innovative cognitive mechatronics
fusing advanced tactile and proximity sensors with the bi- manual mobile manipulator. Energy efficiency and autonomy will be optimized, including HRI capabilities for trustworthy and efficient operation.
A new approach for
robot cognitive functions
based on multi-level robot cycles that allow learning, composing and swiftly adapting robot behaviours. This will enable complex manipulations, covering key topics of sequential manipulation of multiple objects, to achieve complex goals.
Our Innovations
MANiBOT researchers will advance and bring together technologies ranging from multimodal perception, cognition and control to novel cognitive mechatronics. The project will develop:
New environment understanding and object/pose recognition methods
empowered through an adaptive, context-aware fusion of vision, proximity and tactile sensing. This will allow fast and effective manipulation, even of unknown objects, in environments with a human presence.
A novel suite of manipulation primitives
including non-prehensile manipulations. This will allow the transfer of diverse objects with various sizes, weights, shapes, materials and rigidities from a mobile robot, even within significant spatial constraints.
Innovative cognitive mechatronics
fusing advanced tactile and proximity sensors with the bi- manual mobile manipulator. Energy efficiency and autonomy will be optimized, including HRI capabilities for trustworthy and efficient operation.
A new approach for
robot cognitive functions
based on multi-level robot cycles that allow learning, composing and swiftly adapting robot behaviours. This will enable complex manipulations, covering key topics of sequential manipulation of multiple objects, to achieve complex goals.
Partners
