Task planning for cooperating self-reconfigurable mobile fixtures

Abstract

The work solves the problem of task and motion planning of a self-reconfigurable fixture system. A feasible solution is a key requirement for the viability of such systems, which have raised hopes of overcoming the deficiencies that more traditional fixtures are recognized to have in the dynamic conditions of modern manufacturing, with its increasing emphasis on flexibility, adaptability, and automation. The paper proposes an application-independent approach for the generation of a time-relevant action plan for the locomotion, reconfiguration, and positioning of two or more mobile robotic fixtures. The fixture agents need to provide local support for a large workpiece during machining. The path-planning problem is converted into a constraint satisfaction problem (CSP). The proposed approach is called Triple-CSP, as it applies an incremental state search to solve three hierarchical path-planning tasks for the three components of each mobile fixture agent: a supporting head, a mobile base, and a parallel manipulator. A final time-related trajectory (time scaling of actions) for the agents' entire task execution is obtained. Thus, the planner takes into account all the relevant physical, geometrical, and time-related constraints.

Reinforcement learning based path planning of multiple agents of SwarmItFIX robot for fixturing operation in sheetmetal milling process

“…The existing hierarchical CSP approach which performs this coordination has the following issues that need to be addressed. 31,32…”

“…The existing hierarchical CSP approach which performs this coordination has the following issues that need to be addressed. 31,32 i. The hierarchical CSP approach only computes the goal positions of the SwarmItFIX base and not the sequence of locomotion.…”

Hybrid type multi-robot path planning of a serial manipulator and SwarmItFIX robots in sheet metal milling process

“…The serial manipulator's role is to perform the machining operation with end effector as the tool, whereas, the SwarmItFIX robots provide support from the bottom of the sheet metal. The geometrical and FEM constraints (unary and binary) help to obtain a safe distance to be maintained between two consecutive heads ( hh D n ) and between head and contour ( ch D m ) [15,16]. In this work, for the multi-robot path planning and decision-making problems of SwarmItFIX robots, a hierarchical decentralized static or offline strategy has been proposed.…”