Issue link: https://htpgraphics.uberflip.com/i/1385717
RAIN PROGRESS // The RAIN project gave the possibility to pursue all the stages of this research activity. In the first months of the RAIN project, meetings with experts and possible end-users were useful to highlight the challenges about grasping and manipulation tasks in hazardous environments. After that it was possible to start the research and development process to design the algorithm to improve the grasping and manipulation capability of robotic devices in constrained environments in collaboration with the Italian Institute of Technology. A fundamental part of the activity concerned the integration of a preliminary teleoperation setup with robotic manipulation system and virtual reality system. Finally, a virtual reality user interface was designed to allow the operator to select optimal or sub- optimal reliable grasping poses for a given constrained environment. All these research steps allow the proposal of a novel solution to a practical problem. My solution identifies feasible grasping poses with minimal human intervention, the operator must provide the requested inputs and they must start the algorithm. When all the grasping poses are identified the operator selects the desired one. The proposed strategy could be exploited in the majority of robotic manipulation systems actively used in the nuclear industry, where rigid robots with rigid grippers are used in legacy setups or where soft robots cannot be used. UNIQUENESS // This work presents a strategy to compute the optimal trade-off between grasping posture and contact forces in a constrained environment by minimising a novel cost index that includes the desired contact point positions to plan grasping poses. A novel holistic approach, which considers the constraints of the workspace, is achieved by designing an optimisation algorithm with: (i) a suitable cost index that evaluates the grasping pose quality and contact force distribution, (ii) modelling the environmental limitations using linear and nonlinear functions, which relate to a collision between the manipulation system and the limited workspace. REMOTE HANDLING 57 Although testing in the experimental setup uses a two- finger gripper configuration, the procedure presented can be generalised to hands with multiple fingers. The results show that the work is well suited to applications with limited workspace such as a robot working within a glovebox. It is worthy to note that this work provides an algorithm to synthesise grasping poses for objects with known geometrical and physical models. FUTURE ASPIRATIONS // The research activity that was accomplished in the RAIN Hub could be a profitable starting point for future R&D activities. The designed strategy could be extended with teams and experts around planning, machine learning and/or vision algorithms to increase the usability and the capability of the proposed solution. Even if the mentioned strategy is proposed to be used in a known environment, future studies could investigate how to extend this approach to be used in environments with unknown or non-modelled components. My approach aims to solve a real practical problem as grasping and manipulation in constrained environment as gloveboxes, for this reason, nuclear or chemical facilities could benefit from the outcomes of this research; therefore, activities to evaluate the integration in a real production plant or setup could be useful. The collaboration with Italian Institute of Technology highlighted the possibility to use other novel robotic platforms to execute and support nuclear decommissioning tasks, future research activities could explore and additionally test these new technologies in order to be used in a real working scenario.